SlideShare ist ein Scribd-Unternehmen logo
1 von 32
Downloaden Sie, um offline zu lesen
From RNN to neural networks for cyclicFrom RNN to neural networks for cyclic
undirected graphsundirected graphs
Nathalie Vialaneix, INRAE/MIATNathalie Vialaneix, INRAE/MIAT
WG GNN, May 7th, 2020WG GNN, May 7th, 2020
1 / 321 / 32
To start: a briefoverviewofthis talk...To start: a briefoverviewofthis talk...
2 / 322 / 32
Topic
(What is this presentation about?)
How to use (deep) NN for processing relational (graph) data?
I will first start by describing Recurrent Neural Network (RNN) and their
limits to process graphs
Then, I will present two alternatives able to address these limits
I will try to stay non technical (so potentially too vague) to focus on the
most important take home messages
3 / 32
Description ofthe purpose ofthe methods
Data: a graph , with a set of vertices with labels
and a set of edges that can also be labelled
The graph can be directed or undirected, with or without
cycles.
Purpose: find a method (a neural network with weights , ) that is able
to process these data (using the information about the relations / edges
between vertices) to obtain:
make a prediction for every node in the graph,
or make a prediction for the graph itself,
learning dataset: a collection of graphs or a graph (that can be
disconnected) associated to predictions or
G V = {x1 , . . . xn}
l(xi ) ∈ R
p
E = (ej)j=1,…,m
l(ej) ∈ R
q
w ϕw
ϕw(xi )
ϕw(G)
y(G) yi
4 / 32
The basis ofthe work: RNN for structured dataThe basis ofthe work: RNN for structured data
5 / 325 / 32
Framework
Reference: [Sperduti & Starita, 1997]
basic description of standard RNN
adaptations to deal with directed acyclic graphs (DAG)
output is obtained at the graph level ( )
The article also mentions way to deal with cycles and other types of learning
that the standard back-propagation that I'll describe
ϕw(G)
6 / 32
Fromstandard neuron to recurrent neuron
standard neuron
where are the inputs of the neuron (often: the neurons in the previous
layer).
o = f (
r
∑
j=1
wjvj)
vj
7 / 32
Fromstandard neuron to recurrent neuron
recurrent neuron
where is the self weight.
o(t) = f (
r
∑
j=1
wjvj + wSo(t − 1))
wS
8 / 32
Using that type ofrecurrent neuron for DAGencoding
(for a DAG with a supersource, here )
where is the position of the vertex within the children of (it means
that the DAG is a positional DAG).
x5
o(xi ) = f (∑
p
j=1
wjlj(xi ) + ∑
xi→x
i
′
^wn(i
′
) o(xi
′ ))
n(i
′
) i
′
xi
9 / 32
Using that type ofrecurrent neuron for DAGencoding
(for a DAG with a supersource, here )
We have:
(and similarly for and )
x5
o(x8 ) = f (∑
p
j=1
wjlj(x8 )) x7 x2
10 / 32
Using that type ofrecurrent neuron for DAGencoding
(for a DAG with a supersource, here )
We have:
(and similarly for )
x5
o(x9 ) = f (∑
p
j=1
wjlj(x9 ) + ^w1 o(x8 )) x3
11 / 32
Using that type ofrecurrent neuron for DAGencoding
(for a DAG with a supersource, here )
We have:
x5
o(x10 ) = f (∑
p
j=1
wjlj(x10 ) + ^w1 o(x3 ))
12 / 32
Using that type ofrecurrent neuron for DAGencoding
(for a DAG with a supersource, here )
We have:
x5
o(x11 ) = f (∑
p
j=1
wjlj(x11 ) + ^w1 o(x2 ) + ^w2 o(x7 ) + ^w3 o(x9 ) + ^w4 o(x10 ))
13 / 32
Using that type ofrecurrent neuron for DAGencoding
(for a DAG with a supersource, here )
We have:
x5
o(x5 ) = f (∑
p
j=1
wjlj(x5 ) + ^w1 o(x11 ))
14 / 32
Using that type ofrecurrent neuron for DAGencoding
Learning can be performed by back-propagation:
for a given set of weights , recursively compute the outputs on the
graph structure
reciprocally, compute the gradient from the output, recursively on the
graph structure
(w, ^w)
15 / 32
Generalization: cascade correlation for networks
Idea: make several layer of outputs such that depends
on , (as for the previous case) and also on (but
these values are "frozen").
o
1
(x), … , o
r
(x) o
l
(x)
l(x) (o
l
′
(x
′
))x→x
′
, l
′
≤l (o
l
′
(x))l
′
<l
16 / 32
Main limits
Since the approach explicitely relies on the DAG order to successively
compute the output of the nodes, it is not adapted to undirected or cyclic
graphs
Also, the positional assumption of the neighbor of a given node (that an
objective "order" exist between neighbors) is not easily met in real-world
applications
Can only compute prediction for graphs (not for nodes)
Note: The method is tested (in this paper) on logic problems (not described
here)
17 / 32
A rst approach using contraction maps by ScarselliA rst approach using contraction maps by Scarselli etet
al.al., 2009, 2009
18 / 3218 / 32
Overviewofthe method
is able to deal with undirected and cyclic graphs
does not require a positional assumption on the neighbors of a given
node
can be used to make a prediction at a graph and node levels
Main idea: use a "time"-dependant update of the neurons and use restriction
on the weights to constrain the NN to be a contraction map so that the fixed
point theorem can be applied
19 / 32
For each node , we define:
a neuron value expressed as:
an output value obtained from
this neuron value as:
(that can be
combined into a graph output
value if needed)
Basic neuron equations
xi
vi = fw (l(xi ), {l(xi , xu )}xu ∈N (xi)
,
{vu }xu ∈N (xi)
, {l(xu )}xu ∈N (xi)
)
oi = gw(vi , l(xi ))
20 / 32
For each node , we define:
a neuron value expressed as:
an output value obtained from
this neuron value as:
(that can be
combined into a graph output
value if needed)
In a compressed version, this gives:
and .
Basic neuron equations
xi
vi = fw (l(xi ), {l(xi , xu )}xu ∈N (xi)
,
{vu }xu ∈N (xi)
, {l(xu )}xu ∈N (xi)
)
oi = gw(vi , l(xi ))
V = Fw(V , l) O = Gw(V , l)
21 / 32
Making the process recurrent...
The neuron value is made "time" dependent with:
Equivalently, ) so, provided that is a contraction map,
converges to a fixed point. (a sufficient condition is that the norm of
is bounded by )
v
t
i
= fw (l(xi ), {l(xi , xu )}xu ∈N (xi)
, {v
t−1
u }xu ∈N (xi)
, {l(xu )}xu ∈N (xi)
)
V
t+1
= Fw(V
t
, l) Fw
(V
t
)t
∇V Fw(V , l) μ < 1
22 / 32
What are and ?
is a fully-connected MLP
is decomposed into
and is trained as a 1 hidden layer MLP.
Rk: another version is provided in which is obtained as a linear function in
which the intercept and the slope are estimated by MLP.
fw gw
gw
vi = fw(l(xi ), . . . )
∑
xu ∈N (xi)
hw(l(xi ), l(xi , xu ), vu , l(xu ))
hw
hw
23 / 32
Training ofthe weights
The weights of the two MLP are trained by the minimization of
but, to ensure that the resulting is a contraction
map, the weights of are penalized during the training:
with for a given and .
The training is performed by gradient descent where the gradient is obtained
by back-propagation.
BP is simplified using the fact that tends to a fixed point.
∑
n
i=1
(yi − gw(v
T
i
))
2
Fw
Fw
n
∑
i=1
(yi − gw(v
T
i
))
2
+ βL (|∇V Fw|)
L(u) = u − μ μ ∈]0, β > 0
(v
t
i
)t
24 / 32
Applications
The method is illustrated on different types of problems:
the subgraph matching problem (finding a subgraph matching a target
graph in a large graph) in which the prediction is made at the node level
(does it belong to the subgraph or not?)
recover the mutagenic compounds into nitroaromatic compounds
(molecules used as intermediate subproducts in many industrial
reactions). Compounds are described by the graph molecule with
(qualitative and numerical) informations attached to the nodes
web page ranking in which the purpose is to predict a Google page rank
derived measure from a network of 5,000 web pages
25 / 32
A second approach using constructive architecture byA second approach using constructive architecture by
MicheliMicheli etal.etal., 2009, 2009
26 / 3226 / 32
Overviewofthe method
is able to deal with undirected and cyclic graphs (but no label on the
edges)
does not require a positional assumption on the neighbors of a given
node
can be used to make a prediction at a graph and node levels (probably,
though it is made explicit for the graph level)
Main idea: define an architecture close to "cascade correlation network" with
some "frozen" neurones that are not updated. The architecture is hierarchical
and adaptive, in the sense that it stops growing when a given accuracy is
achieved.
27 / 32
Neuron equations
Similarly as previously, neurons are computed in a recurrent way that
depends on "time". The neuron state at time for vertex depends on its
label and of the neuron state of the neighboring neurons at all past times:
Rk:
a stationnary assumption (the weights do not depend on the node nor on
the edge) is critical to obtain a simple enough formulation
contrary to RNN or to the previous version, are not updated: the
layer are trained one at a time and once the training is finished, the
neuron states are considered "frozen" (which is a way to avoid problem
with cycles)
t xi
v
t
i
= f (∑
j
w
t
j
lj(xi ) + ∑
t
′
<t
^w
tt
′
∑
xu ∈N (xi)
v
t
′
u )
(v
t
′
u )t
′
<t
28 / 32
Combining neuron outputs into a prediction
output of layer : where is a normalization factor
(equal to 1 or to the number of nodes for instance)
output of the network:
t ϕ
t
w(G) = ∑
n
i=1
v
t
i
1
C
C
Φw(G) = f (∑
t
w
t
ϕ
t
w(G))
29 / 32
Training
Training is also performed by minimization of the squared error but:
not constraint is needed on weights
back-propagation is not performed through unfolded layers
Examples
QSPR/QSAR task that consists in transforming information on molecular
structure into information on chemical properties. Here: prediction of
boiling point value
classification of cyclic/acyclic graphs
30 / 32
That's all for now...That's all for now...
... questions?... questions?
31 / 3231 / 32
References
Micheli A (2009) Neural networks for graphs: a contextual constructive approach. IEEE
Transactions on Neural Networks, 20(3): 498-511
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network
model. IEEE Transactions on Neural Networks, 20(1): 61-80
Sperduti A, Starita A (1997) Supervised neural network for the classification of structures.
IEEE Transactions on Neural Networks, 8(3): 714-735
32 / 32

Weitere ähnliche Inhalte

Was ist angesagt?

Quantitative Propagation of Chaos for SGD in Wide Neural Networks
Quantitative Propagation of Chaos for SGD in Wide Neural NetworksQuantitative Propagation of Chaos for SGD in Wide Neural Networks
Quantitative Propagation of Chaos for SGD in Wide Neural NetworksValentin De Bortoli
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Mostafa G. M. Mostafa
 
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Universitat Politècnica de Catalunya
 
Reproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfishReproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfishtuxette
 
An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...
An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...
An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...NTNU
 
Particle Filters and Applications in Computer Vision
Particle Filters and Applications in Computer VisionParticle Filters and Applications in Computer Vision
Particle Filters and Applications in Computer Visionzukun
 
Investigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysisInvestigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysistuxette
 
A discussion on sampling graphs to approximate network classification functions
A discussion on sampling graphs to approximate network classification functionsA discussion on sampling graphs to approximate network classification functions
A discussion on sampling graphs to approximate network classification functionsLARCA UPC
 
Continuous and Discrete-Time Analysis of SGD
Continuous and Discrete-Time Analysis of SGDContinuous and Discrete-Time Analysis of SGD
Continuous and Discrete-Time Analysis of SGDValentin De Bortoli
 
Kernel methods for data integration in systems biology
Kernel methods for data integration in systems biologyKernel methods for data integration in systems biology
Kernel methods for data integration in systems biologytuxette
 
Graph Kernels for Chemical Informatics
Graph Kernels for Chemical InformaticsGraph Kernels for Chemical Informatics
Graph Kernels for Chemical InformaticsMukund Raj
 
An introduction to deep learning
An introduction to deep learningAn introduction to deep learning
An introduction to deep learningVan Thanh
 
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task LearningMasahiro Suzuki
 
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...준식 최
 
(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot LearningMasahiro Suzuki
 

Was ist angesagt? (20)

Gtti 10032021
Gtti 10032021Gtti 10032021
Gtti 10032021
 
Quantitative Propagation of Chaos for SGD in Wide Neural Networks
Quantitative Propagation of Chaos for SGD in Wide Neural NetworksQuantitative Propagation of Chaos for SGD in Wide Neural Networks
Quantitative Propagation of Chaos for SGD in Wide Neural Networks
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)
 
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
 
Iclr2016 vaeまとめ
Iclr2016 vaeまとめIclr2016 vaeまとめ
Iclr2016 vaeまとめ
 
Reproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfishReproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfish
 
An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...
An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...
An Importance Sampling Approach to Integrate Expert Knowledge When Learning B...
 
Particle Filters and Applications in Computer Vision
Particle Filters and Applications in Computer VisionParticle Filters and Applications in Computer Vision
Particle Filters and Applications in Computer Vision
 
Polynomial Matrix Decompositions
Polynomial Matrix DecompositionsPolynomial Matrix Decompositions
Polynomial Matrix Decompositions
 
Investigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysisInvestigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysis
 
A discussion on sampling graphs to approximate network classification functions
A discussion on sampling graphs to approximate network classification functionsA discussion on sampling graphs to approximate network classification functions
A discussion on sampling graphs to approximate network classification functions
 
Continuous and Discrete-Time Analysis of SGD
Continuous and Discrete-Time Analysis of SGDContinuous and Discrete-Time Analysis of SGD
Continuous and Discrete-Time Analysis of SGD
 
Estimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample SetsEstimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample Sets
 
Kernel methods for data integration in systems biology
Kernel methods for data integration in systems biologyKernel methods for data integration in systems biology
Kernel methods for data integration in systems biology
 
Graph Kernels for Chemical Informatics
Graph Kernels for Chemical InformaticsGraph Kernels for Chemical Informatics
Graph Kernels for Chemical Informatics
 
An introduction to deep learning
An introduction to deep learningAn introduction to deep learning
An introduction to deep learning
 
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
 
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
 
Bayesian Core: Chapter 8
Bayesian Core: Chapter 8Bayesian Core: Chapter 8
Bayesian Core: Chapter 8
 
(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning
 

Ähnlich wie From RNN to neural networks for cyclic undirected graphs

MVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsMVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsElvis DOHMATOB
 
Graph Neural Network in practice
Graph Neural Network in practiceGraph Neural Network in practice
Graph Neural Network in practicetuxette
 
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...ieijjournal
 
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...ieijjournal
 
Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3Fabian Pedregosa
 
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)Universitat Politècnica de Catalunya
 
Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...
Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...
Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...Steven Duplij (Stepan Douplii)
 
Anomaly detection using deep one class classifier
Anomaly detection using deep one class classifierAnomaly detection using deep one class classifier
Anomaly detection using deep one class classifier홍배 김
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Valentin De Bortoli
 
A Fast Near Optimal Vertex Cover Algorithm (NOVCA)
A Fast Near Optimal Vertex Cover Algorithm (NOVCA)A Fast Near Optimal Vertex Cover Algorithm (NOVCA)
A Fast Near Optimal Vertex Cover Algorithm (NOVCA)Waqas Tariq
 
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)Universitat Politècnica de Catalunya
 
Fast Object Recognition from 3D Depth Data with Extreme Learning Machine
Fast Object Recognition from 3D Depth Data with Extreme Learning MachineFast Object Recognition from 3D Depth Data with Extreme Learning Machine
Fast Object Recognition from 3D Depth Data with Extreme Learning MachineSoma Boubou
 
Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...
Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...
Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...AIST
 
Convolution Neural Networks
Convolution Neural NetworksConvolution Neural Networks
Convolution Neural NetworksAhmedMahany
 
Robust Super-Resolution by minimizing a Gaussian-weighted L2 error norm
Robust Super-Resolution by minimizing a Gaussian-weighted L2 error normRobust Super-Resolution by minimizing a Gaussian-weighted L2 error norm
Robust Super-Resolution by minimizing a Gaussian-weighted L2 error normTuan Q. Pham
 
1 hofstad
1 hofstad1 hofstad
1 hofstadYandex
 

Ähnlich wie From RNN to neural networks for cyclic undirected graphs (20)

MVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsMVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priors
 
Graph Neural Network in practice
Graph Neural Network in practiceGraph Neural Network in practice
Graph Neural Network in practice
 
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
PixelCNN, Wavenet, Normalizing Flows - Santiago Pascual - UPC Barcelona 2018
 
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
 
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
FITTED OPERATOR FINITE DIFFERENCE METHOD FOR SINGULARLY PERTURBED PARABOLIC C...
 
Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3
 
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
 
Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...
Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...
Steven Duplij, Raimund Vogl, "Polyadic Braid Operators and Higher Braiding Ga...
 
Anomaly detection using deep one class classifier
Anomaly detection using deep one class classifierAnomaly detection using deep one class classifier
Anomaly detection using deep one class classifier
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
A Fast Near Optimal Vertex Cover Algorithm (NOVCA)
A Fast Near Optimal Vertex Cover Algorithm (NOVCA)A Fast Near Optimal Vertex Cover Algorithm (NOVCA)
A Fast Near Optimal Vertex Cover Algorithm (NOVCA)
 
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
 
Fast Object Recognition from 3D Depth Data with Extreme Learning Machine
Fast Object Recognition from 3D Depth Data with Extreme Learning MachineFast Object Recognition from 3D Depth Data with Extreme Learning Machine
Fast Object Recognition from 3D Depth Data with Extreme Learning Machine
 
Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...
Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...
Andrey V. Savchenko - Sequential Hierarchical Image Recognition based on the ...
 
project final
project finalproject final
project final
 
UofT_ML_lecture.pptx
UofT_ML_lecture.pptxUofT_ML_lecture.pptx
UofT_ML_lecture.pptx
 
Convolution Neural Networks
Convolution Neural NetworksConvolution Neural Networks
Convolution Neural Networks
 
Robust Super-Resolution by minimizing a Gaussian-weighted L2 error norm
Robust Super-Resolution by minimizing a Gaussian-weighted L2 error normRobust Super-Resolution by minimizing a Gaussian-weighted L2 error norm
Robust Super-Resolution by minimizing a Gaussian-weighted L2 error norm
 
MUMS: Bayesian, Fiducial, and Frequentist Conference - Model Selection in the...
MUMS: Bayesian, Fiducial, and Frequentist Conference - Model Selection in the...MUMS: Bayesian, Fiducial, and Frequentist Conference - Model Selection in the...
MUMS: Bayesian, Fiducial, and Frequentist Conference - Model Selection in the...
 
1 hofstad
1 hofstad1 hofstad
1 hofstad
 

Mehr von tuxette

Racines en haut et feuilles en bas : les arbres en maths
Racines en haut et feuilles en bas : les arbres en mathsRacines en haut et feuilles en bas : les arbres en maths
Racines en haut et feuilles en bas : les arbres en mathstuxette
 
Méthodes à noyaux pour l’intégration de données hétérogènes
Méthodes à noyaux pour l’intégration de données hétérogènesMéthodes à noyaux pour l’intégration de données hétérogènes
Méthodes à noyaux pour l’intégration de données hétérogènestuxette
 
Méthodologies d'intégration de données omiques
Méthodologies d'intégration de données omiquesMéthodologies d'intégration de données omiques
Méthodologies d'intégration de données omiquestuxette
 
Projets autour de l'Hi-C
Projets autour de l'Hi-CProjets autour de l'Hi-C
Projets autour de l'Hi-Ctuxette
 
Can deep learning learn chromatin structure from sequence?
Can deep learning learn chromatin structure from sequence?Can deep learning learn chromatin structure from sequence?
Can deep learning learn chromatin structure from sequence?tuxette
 
Multi-omics data integration methods: kernel and other machine learning appro...
Multi-omics data integration methods: kernel and other machine learning appro...Multi-omics data integration methods: kernel and other machine learning appro...
Multi-omics data integration methods: kernel and other machine learning appro...tuxette
 
ASTERICS : une application pour intégrer des données omiques
ASTERICS : une application pour intégrer des données omiquesASTERICS : une application pour intégrer des données omiques
ASTERICS : une application pour intégrer des données omiquestuxette
 
Autour des projets Idefics et MetaboWean
Autour des projets Idefics et MetaboWeanAutour des projets Idefics et MetaboWean
Autour des projets Idefics et MetaboWeantuxette
 
Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...
Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...
Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...tuxette
 
Apprentissage pour la biologie moléculaire et l’analyse de données omiques
Apprentissage pour la biologie moléculaire et l’analyse de données omiquesApprentissage pour la biologie moléculaire et l’analyse de données omiques
Apprentissage pour la biologie moléculaire et l’analyse de données omiquestuxette
 
Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...
Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...
Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...tuxette
 
Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...
Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...
Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...tuxette
 
Journal club: Validation of cluster analysis results on validation data
Journal club: Validation of cluster analysis results on validation dataJournal club: Validation of cluster analysis results on validation data
Journal club: Validation of cluster analysis results on validation datatuxette
 
Overfitting or overparametrization?
Overfitting or overparametrization?Overfitting or overparametrization?
Overfitting or overparametrization?tuxette
 
Selective inference and single-cell differential analysis
Selective inference and single-cell differential analysisSelective inference and single-cell differential analysis
Selective inference and single-cell differential analysistuxette
 
SOMbrero : un package R pour les cartes auto-organisatrices
SOMbrero : un package R pour les cartes auto-organisatricesSOMbrero : un package R pour les cartes auto-organisatrices
SOMbrero : un package R pour les cartes auto-organisatricestuxette
 
Graph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype PredictionGraph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype Predictiontuxette
 
Explanable models for time series with random forest
Explanable models for time series with random forestExplanable models for time series with random forest
Explanable models for time series with random foresttuxette
 
Présentation du projet ASTERICS
Présentation du projet ASTERICSPrésentation du projet ASTERICS
Présentation du projet ASTERICStuxette
 
Présentation du projet ASTERICS
Présentation du projet ASTERICSPrésentation du projet ASTERICS
Présentation du projet ASTERICStuxette
 

Mehr von tuxette (20)

Racines en haut et feuilles en bas : les arbres en maths
Racines en haut et feuilles en bas : les arbres en mathsRacines en haut et feuilles en bas : les arbres en maths
Racines en haut et feuilles en bas : les arbres en maths
 
Méthodes à noyaux pour l’intégration de données hétérogènes
Méthodes à noyaux pour l’intégration de données hétérogènesMéthodes à noyaux pour l’intégration de données hétérogènes
Méthodes à noyaux pour l’intégration de données hétérogènes
 
Méthodologies d'intégration de données omiques
Méthodologies d'intégration de données omiquesMéthodologies d'intégration de données omiques
Méthodologies d'intégration de données omiques
 
Projets autour de l'Hi-C
Projets autour de l'Hi-CProjets autour de l'Hi-C
Projets autour de l'Hi-C
 
Can deep learning learn chromatin structure from sequence?
Can deep learning learn chromatin structure from sequence?Can deep learning learn chromatin structure from sequence?
Can deep learning learn chromatin structure from sequence?
 
Multi-omics data integration methods: kernel and other machine learning appro...
Multi-omics data integration methods: kernel and other machine learning appro...Multi-omics data integration methods: kernel and other machine learning appro...
Multi-omics data integration methods: kernel and other machine learning appro...
 
ASTERICS : une application pour intégrer des données omiques
ASTERICS : une application pour intégrer des données omiquesASTERICS : une application pour intégrer des données omiques
ASTERICS : une application pour intégrer des données omiques
 
Autour des projets Idefics et MetaboWean
Autour des projets Idefics et MetaboWeanAutour des projets Idefics et MetaboWean
Autour des projets Idefics et MetaboWean
 
Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...
Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...
Rserve, renv, flask, Vue.js dans un docker pour intégrer des données omiques ...
 
Apprentissage pour la biologie moléculaire et l’analyse de données omiques
Apprentissage pour la biologie moléculaire et l’analyse de données omiquesApprentissage pour la biologie moléculaire et l’analyse de données omiques
Apprentissage pour la biologie moléculaire et l’analyse de données omiques
 
Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...
Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...
Quelques résultats préliminaires de l'évaluation de méthodes d'inférence de r...
 
Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...
Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...
Intégration de données omiques multi-échelles : méthodes à noyau et autres ap...
 
Journal club: Validation of cluster analysis results on validation data
Journal club: Validation of cluster analysis results on validation dataJournal club: Validation of cluster analysis results on validation data
Journal club: Validation of cluster analysis results on validation data
 
Overfitting or overparametrization?
Overfitting or overparametrization?Overfitting or overparametrization?
Overfitting or overparametrization?
 
Selective inference and single-cell differential analysis
Selective inference and single-cell differential analysisSelective inference and single-cell differential analysis
Selective inference and single-cell differential analysis
 
SOMbrero : un package R pour les cartes auto-organisatrices
SOMbrero : un package R pour les cartes auto-organisatricesSOMbrero : un package R pour les cartes auto-organisatrices
SOMbrero : un package R pour les cartes auto-organisatrices
 
Graph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype PredictionGraph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype Prediction
 
Explanable models for time series with random forest
Explanable models for time series with random forestExplanable models for time series with random forest
Explanable models for time series with random forest
 
Présentation du projet ASTERICS
Présentation du projet ASTERICSPrésentation du projet ASTERICS
Présentation du projet ASTERICS
 
Présentation du projet ASTERICS
Présentation du projet ASTERICSPrésentation du projet ASTERICS
Présentation du projet ASTERICS
 

Kürzlich hochgeladen

Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |aasikanpl
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhousejana861314
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfSumit Kumar yadav
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Patrick Diehl
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCEPRINCE C P
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsSumit Kumar yadav
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisDiwakar Mishra
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 

Kürzlich hochgeladen (20)

Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhouse
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questions
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 

From RNN to neural networks for cyclic undirected graphs

  • 1. From RNN to neural networks for cyclicFrom RNN to neural networks for cyclic undirected graphsundirected graphs Nathalie Vialaneix, INRAE/MIATNathalie Vialaneix, INRAE/MIAT WG GNN, May 7th, 2020WG GNN, May 7th, 2020 1 / 321 / 32
  • 2. To start: a briefoverviewofthis talk...To start: a briefoverviewofthis talk... 2 / 322 / 32
  • 3. Topic (What is this presentation about?) How to use (deep) NN for processing relational (graph) data? I will first start by describing Recurrent Neural Network (RNN) and their limits to process graphs Then, I will present two alternatives able to address these limits I will try to stay non technical (so potentially too vague) to focus on the most important take home messages 3 / 32
  • 4. Description ofthe purpose ofthe methods Data: a graph , with a set of vertices with labels and a set of edges that can also be labelled The graph can be directed or undirected, with or without cycles. Purpose: find a method (a neural network with weights , ) that is able to process these data (using the information about the relations / edges between vertices) to obtain: make a prediction for every node in the graph, or make a prediction for the graph itself, learning dataset: a collection of graphs or a graph (that can be disconnected) associated to predictions or G V = {x1 , . . . xn} l(xi ) ∈ R p E = (ej)j=1,…,m l(ej) ∈ R q w ϕw ϕw(xi ) ϕw(G) y(G) yi 4 / 32
  • 5. The basis ofthe work: RNN for structured dataThe basis ofthe work: RNN for structured data 5 / 325 / 32
  • 6. Framework Reference: [Sperduti & Starita, 1997] basic description of standard RNN adaptations to deal with directed acyclic graphs (DAG) output is obtained at the graph level ( ) The article also mentions way to deal with cycles and other types of learning that the standard back-propagation that I'll describe ϕw(G) 6 / 32
  • 7. Fromstandard neuron to recurrent neuron standard neuron where are the inputs of the neuron (often: the neurons in the previous layer). o = f ( r ∑ j=1 wjvj) vj 7 / 32
  • 8. Fromstandard neuron to recurrent neuron recurrent neuron where is the self weight. o(t) = f ( r ∑ j=1 wjvj + wSo(t − 1)) wS 8 / 32
  • 9. Using that type ofrecurrent neuron for DAGencoding (for a DAG with a supersource, here ) where is the position of the vertex within the children of (it means that the DAG is a positional DAG). x5 o(xi ) = f (∑ p j=1 wjlj(xi ) + ∑ xi→x i ′ ^wn(i ′ ) o(xi ′ )) n(i ′ ) i ′ xi 9 / 32
  • 10. Using that type ofrecurrent neuron for DAGencoding (for a DAG with a supersource, here ) We have: (and similarly for and ) x5 o(x8 ) = f (∑ p j=1 wjlj(x8 )) x7 x2 10 / 32
  • 11. Using that type ofrecurrent neuron for DAGencoding (for a DAG with a supersource, here ) We have: (and similarly for ) x5 o(x9 ) = f (∑ p j=1 wjlj(x9 ) + ^w1 o(x8 )) x3 11 / 32
  • 12. Using that type ofrecurrent neuron for DAGencoding (for a DAG with a supersource, here ) We have: x5 o(x10 ) = f (∑ p j=1 wjlj(x10 ) + ^w1 o(x3 )) 12 / 32
  • 13. Using that type ofrecurrent neuron for DAGencoding (for a DAG with a supersource, here ) We have: x5 o(x11 ) = f (∑ p j=1 wjlj(x11 ) + ^w1 o(x2 ) + ^w2 o(x7 ) + ^w3 o(x9 ) + ^w4 o(x10 )) 13 / 32
  • 14. Using that type ofrecurrent neuron for DAGencoding (for a DAG with a supersource, here ) We have: x5 o(x5 ) = f (∑ p j=1 wjlj(x5 ) + ^w1 o(x11 )) 14 / 32
  • 15. Using that type ofrecurrent neuron for DAGencoding Learning can be performed by back-propagation: for a given set of weights , recursively compute the outputs on the graph structure reciprocally, compute the gradient from the output, recursively on the graph structure (w, ^w) 15 / 32
  • 16. Generalization: cascade correlation for networks Idea: make several layer of outputs such that depends on , (as for the previous case) and also on (but these values are "frozen"). o 1 (x), … , o r (x) o l (x) l(x) (o l ′ (x ′ ))x→x ′ , l ′ ≤l (o l ′ (x))l ′ <l 16 / 32
  • 17. Main limits Since the approach explicitely relies on the DAG order to successively compute the output of the nodes, it is not adapted to undirected or cyclic graphs Also, the positional assumption of the neighbor of a given node (that an objective "order" exist between neighbors) is not easily met in real-world applications Can only compute prediction for graphs (not for nodes) Note: The method is tested (in this paper) on logic problems (not described here) 17 / 32
  • 18. A rst approach using contraction maps by ScarselliA rst approach using contraction maps by Scarselli etet al.al., 2009, 2009 18 / 3218 / 32
  • 19. Overviewofthe method is able to deal with undirected and cyclic graphs does not require a positional assumption on the neighbors of a given node can be used to make a prediction at a graph and node levels Main idea: use a "time"-dependant update of the neurons and use restriction on the weights to constrain the NN to be a contraction map so that the fixed point theorem can be applied 19 / 32
  • 20. For each node , we define: a neuron value expressed as: an output value obtained from this neuron value as: (that can be combined into a graph output value if needed) Basic neuron equations xi vi = fw (l(xi ), {l(xi , xu )}xu ∈N (xi) , {vu }xu ∈N (xi) , {l(xu )}xu ∈N (xi) ) oi = gw(vi , l(xi )) 20 / 32
  • 21. For each node , we define: a neuron value expressed as: an output value obtained from this neuron value as: (that can be combined into a graph output value if needed) In a compressed version, this gives: and . Basic neuron equations xi vi = fw (l(xi ), {l(xi , xu )}xu ∈N (xi) , {vu }xu ∈N (xi) , {l(xu )}xu ∈N (xi) ) oi = gw(vi , l(xi )) V = Fw(V , l) O = Gw(V , l) 21 / 32
  • 22. Making the process recurrent... The neuron value is made "time" dependent with: Equivalently, ) so, provided that is a contraction map, converges to a fixed point. (a sufficient condition is that the norm of is bounded by ) v t i = fw (l(xi ), {l(xi , xu )}xu ∈N (xi) , {v t−1 u }xu ∈N (xi) , {l(xu )}xu ∈N (xi) ) V t+1 = Fw(V t , l) Fw (V t )t ∇V Fw(V , l) μ < 1 22 / 32
  • 23. What are and ? is a fully-connected MLP is decomposed into and is trained as a 1 hidden layer MLP. Rk: another version is provided in which is obtained as a linear function in which the intercept and the slope are estimated by MLP. fw gw gw vi = fw(l(xi ), . . . ) ∑ xu ∈N (xi) hw(l(xi ), l(xi , xu ), vu , l(xu )) hw hw 23 / 32
  • 24. Training ofthe weights The weights of the two MLP are trained by the minimization of but, to ensure that the resulting is a contraction map, the weights of are penalized during the training: with for a given and . The training is performed by gradient descent where the gradient is obtained by back-propagation. BP is simplified using the fact that tends to a fixed point. ∑ n i=1 (yi − gw(v T i )) 2 Fw Fw n ∑ i=1 (yi − gw(v T i )) 2 + βL (|∇V Fw|) L(u) = u − μ μ ∈]0, β > 0 (v t i )t 24 / 32
  • 25. Applications The method is illustrated on different types of problems: the subgraph matching problem (finding a subgraph matching a target graph in a large graph) in which the prediction is made at the node level (does it belong to the subgraph or not?) recover the mutagenic compounds into nitroaromatic compounds (molecules used as intermediate subproducts in many industrial reactions). Compounds are described by the graph molecule with (qualitative and numerical) informations attached to the nodes web page ranking in which the purpose is to predict a Google page rank derived measure from a network of 5,000 web pages 25 / 32
  • 26. A second approach using constructive architecture byA second approach using constructive architecture by MicheliMicheli etal.etal., 2009, 2009 26 / 3226 / 32
  • 27. Overviewofthe method is able to deal with undirected and cyclic graphs (but no label on the edges) does not require a positional assumption on the neighbors of a given node can be used to make a prediction at a graph and node levels (probably, though it is made explicit for the graph level) Main idea: define an architecture close to "cascade correlation network" with some "frozen" neurones that are not updated. The architecture is hierarchical and adaptive, in the sense that it stops growing when a given accuracy is achieved. 27 / 32
  • 28. Neuron equations Similarly as previously, neurons are computed in a recurrent way that depends on "time". The neuron state at time for vertex depends on its label and of the neuron state of the neighboring neurons at all past times: Rk: a stationnary assumption (the weights do not depend on the node nor on the edge) is critical to obtain a simple enough formulation contrary to RNN or to the previous version, are not updated: the layer are trained one at a time and once the training is finished, the neuron states are considered "frozen" (which is a way to avoid problem with cycles) t xi v t i = f (∑ j w t j lj(xi ) + ∑ t ′ <t ^w tt ′ ∑ xu ∈N (xi) v t ′ u ) (v t ′ u )t ′ <t 28 / 32
  • 29. Combining neuron outputs into a prediction output of layer : where is a normalization factor (equal to 1 or to the number of nodes for instance) output of the network: t ϕ t w(G) = ∑ n i=1 v t i 1 C C Φw(G) = f (∑ t w t ϕ t w(G)) 29 / 32
  • 30. Training Training is also performed by minimization of the squared error but: not constraint is needed on weights back-propagation is not performed through unfolded layers Examples QSPR/QSAR task that consists in transforming information on molecular structure into information on chemical properties. Here: prediction of boiling point value classification of cyclic/acyclic graphs 30 / 32
  • 31. That's all for now...That's all for now... ... questions?... questions? 31 / 3231 / 32
  • 32. References Micheli A (2009) Neural networks for graphs: a contextual constructive approach. IEEE Transactions on Neural Networks, 20(3): 498-511 Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Transactions on Neural Networks, 20(1): 61-80 Sperduti A, Starita A (1997) Supervised neural network for the classification of structures. IEEE Transactions on Neural Networks, 8(3): 714-735 32 / 32