SlideShare ist ein Scribd-Unternehmen logo
1 von 39
Downloaden Sie, um offline zu lesen
Weisfeiler and Leman Go Neural: Higher-order
Graph Neural Networks
Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric
Lenssen, Gaurav Rattan, Martin Grohe
November 12, 2018
TU Dortmund University,
RWTH Aachen University,
McGill University
Motivation
Question
How similar are two graphs?
(a) Sildenafil (b) Vardenafil
1
High-level View: Supervised Graph Classification
2
High-level View: Supervised Graph Classification
⊆ H
φ: G → H
2
High-level View: Supervised Graph Classification
⊆ H
φ: G → H
2
Talk Structure
1 State-of-the-art methods for graph classification
2 Relationship between 1-WL kernel and Graph Neural Networks
3 Higher-order graph properties
4 Experimental results
3
Supervised Graph Classification: The State-of-the-Art
Kernel Methods
Find predefined substructures
and count them somehow:
• Shortest-paths or random
walks
• Motifs
• h-neighborhoods around
vertices
• Spectral Approaches
4
Supervised Graph Classification: The State-of-the-Art
Kernel Methods
Find predefined substructures
and count them somehow:
• Shortest-paths or random
walks
• Motifs
• h-neighborhoods around
vertices
• Spectral Approaches
Neural Methods
Parameterized neighborhood
aggregation function
f
(t)
v = 𝜎(W1 f
(t−1)
v + W2
∑︁
w∈N(v)
f
(t−1)
w )
and learn parameters W1 and W2
together with the parameters of
the classifier
4
Example: Weisfeiler-Lehman Subtree Kernel
Example (Weisfeiler-Lehman Subtree Kernel)
Graph kernel based on heuristic for graph isomorphism testing
Iteration: Two vertices get identical colors iff their colored
neighborhoods are identical
N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt.
“Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561
5
Example: Weisfeiler-Lehman Subtree Kernel
Example (Weisfeiler-Lehman Subtree Kernel)
Graph kernel based on heuristic for graph isomorphism testing
Iteration: Two vertices get identical colors iff their colored
neighborhoods are identical
𝜑(G1) = ( )
(a) G1
𝜑(G2) = ( )
(b) G2
N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt.
“Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561
5
Example: Weisfeiler-Lehman Subtree Kernel
Example (Weisfeiler-Lehman Subtree Kernel)
Graph kernel based on heuristic for graph isomorphism testing
Iteration: Two vertices get identical colors iff their colored
neighborhoods are identical
𝜑(G1) = (2, 2, 2, )
(a) G1
𝜑(G2) = (1, 1, 3, )
(b) G2
N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt.
“Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561
5
Example: Weisfeiler-Lehman Subtree Kernel
Example (Weisfeiler-Lehman Subtree Kernel)
Graph kernel based on heuristic for graph isomorphism testing
Iteration: Two vertices get identical colors iff their colored
neighborhoods are identical
𝜑(G1) = (2, 2, 2, 2, 2, 2, 0, 0)
(a) G1
𝜑(G2) = (1, 1, 3, 2, 0, 1, 1, 1)
(b) G2
N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt.
“Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561
5
Relationship between 1-WL and GNN
1-WL coloring
c(t)
(v) = hash
(︁
c(t−1)
(v), {{c(t−1)
(w) | w ∈ N(v)}}
)︁
6
Relationship between 1-WL and GNN
1-WL coloring
c(t)
(v) = hash
(︁
c(t−1)
(v), {{c(t−1)
(w) | w ∈ N(v)}}
)︁
General form of GNNs
h(t)
(v) = f
W
(t)
1
merge
(︁
h(t−1)
(v), f
W
(t)
2
aggr
(︀
{{h(t−1)
(w) | w ∈ N(v)}}
)︀)︁
6
Relationship between 1-WL and GNN
1-WL coloring
c(t)
(v) = hash
(︁
c(t−1)
(v), {{c(t−1)
(w) | w ∈ N(v)}}
)︁
General form of GNNs
h(t)
(v) = f
W
(t)
1
merge
(︁
h(t−1)
(v), f
W
(t)
2
aggr
(︀
{{h(t−1)
(w) | w ∈ N(v)}}
)︀)︁
Both methods aggregate colors/features of neighbors
6
Relationship between 1-WL and GNN
1-WL coloring
c(t)
(v) = hash
(︁
c(t−1)
(v), {{c(t−1)
(w) | w ∈ N(v)}}
)︁
General form of GNNs
h(t)
(v) = f
W
(t)
1
merge
(︁
h(t−1)
(v), f
W
(t)
2
aggr
(︀
{{h(t−1)
(w) | w ∈ N(v)}}
)︀)︁
Both methods aggregate colors/features of neighbors
Theorem (Informal)
GNNs cannot be more expressive than 1-WL in terms of
distinguishing non-isomorphic graphs.
6
Relationship between 1-WL and GNN
1-WL coloring
c(t)
(v) = hash
(︁
c(t−1)
(v), {{c(t−1)
(w) | w ∈ N(v)}}
)︁
General form of GNNs
h(t)
(v) = f
W
(t)
1
merge
(︁
h(t−1)
(v), f
W
(t)
2
aggr
(︀
{{h(t−1)
(w) | w ∈ N(v)}}
)︀)︁
7
Relationship between 1-WL and GNN
1-WL coloring
c(t)
(v) = hash
(︁
c(t−1)
(v), {{c(t−1)
(w) | w ∈ N(v)}}
)︁
General form of GNNs
h(t)
(v) = f
W
(t)
1
merge
(︁
h(t−1)
(v), f
W
(t)
2
aggr
(︀
{{h(t−1)
(w) | w ∈ N(v)}}
)︀)︁
Insight
GNNs are as powerful as 1-WL if f
W
(t)
1
merge and f
W
(t)
2
aggr are injective
Theorem (Informal)
There exists a GNN architecture and corresponding weights such
that it reaches an equivalent coloring as 1-WL.
7
Relationship between 1-WL and GNN
Theorem (Informal)
There exists a GNN architecture and corresponding weights such
that it reaches an equivalent coloring as 1-WL.
8
Relationship between 1-WL and GNN
Theorem (Informal)
There exists a GNN architecture and corresponding weights such
that it reaches an equivalent coloring as 1-WL.
1-WL GNN
∇
8
Relationship between 1-WL and GNN
Theorem (Informal)
There exists a GNN architecture and corresponding weights such
that it reaches an equivalent coloring as 1-WL.
1-WL GNN
∇
Take Away
GNNs have the same power as 1-WL in distinguishing
non-isomorphic graphs.
8
Relationship between 1-WL and GNN
Theorem (Informal)
There exists a GNN architecture and corresponding weights such
that it reaches an equivalent coloring as 1-WL.
1-WL GNN
∇
Take Away
GNNs have the same power as 1-WL in distinguishing
non-isomorphic graphs. Limits of 1-WL are well understood.
V. Arvind, J. Köbler, G. Rattan, and O. Verbitsky. “On the Power of Color
Refinement”. In: Symposium on Fundamentals of Computation
Theory. 2015, pp. 339–350
8
Limits of GNNs
Observation
GNNs cannot distinguish very basic graph properties, e.g.,
• Cycle-free vs. cyclic graphs
• Triangle counts
• Regular graphs
9
Limits of GNNs
Observation
GNNs cannot distinguish very basic graph properties, e.g.,
• Cycle-free vs. cyclic graphs
• Triangle counts
• Regular graphs
Observation
Higher-order graph properties play an important role for the
characterization of real-world networks.
9
Higher-order Graph Properties
Challenge
Incorporate more higher-order graph properties into Graph
Neural Networks.
10
Higher-order Graph Properties
Challenge
Incorporate more higher-order graph properties into Graph
Neural Networks.
1-WL GNN
k-WL k-GNN
∇
Global
Global
∇
10
Higher-order Graph Properties
Challenge
Incorporate more higher-order graph properties into Graph
Neural Networks.
1-WL GNN
k-WL k-GNN
∇
Global
Global
∇
Idea: k-WL
Color subgraphs instead of vertices, and define neighborhoods
between them.
10
k-dimensional Weisfeiler-Lehman
k-dimensional Weisfeiler-Lehman
• Colors vertex tuples from Vk
• Two tuples v, w are i-neighbors if vj = wj for all j ̸= i
v1 v2 v3
v4 v5 v6
11
k-dimensional Weisfeiler-Lehman
k-dimensional Weisfeiler-Lehman
• Colors vertex tuples from Vk
• Two tuples v, w are i-neighbors if vj = wj for all j ̸= i
v1 v2 v3
v4 v5 v6
11
k-dimensional Weisfeiler-Lehman
k-dimensional Weisfeiler-Lehman
• Colors vertex tuples from Vk
• Two tuples v, w are i-neighbors if vj = wj for all j ̸= i
v1 v2 v3
v4 v5 v6
Idea of the Algorithm
Initially Two tuples get the same color if the induced
subgraphs are isomorphic
11
k-dimensional Weisfeiler-Lehman
k-dimensional Weisfeiler-Lehman
• Colors vertex tuples from Vk
• Two tuples v, w are i-neighbors if vj = wj for all j ̸= i
v1 v2 v3
v4 v5 v6
Idea of the Algorithm
Initially Two tuples get the same color if the induced
subgraphs are isomorphic
Iteration Two tuples get same color iff they have the same
colored neighborhood
11
k-GNN
Idea
Derive k-dimensional Graph Neural Network
ft
S = 𝜎(W1ft−1
S + W2
∑︁
T∈N(S)
ft−1
T ),
where S is a subgraph of the input graph of size k.
12
k-GNN
Idea
Derive k-dimensional Graph Neural Network
ft
S = 𝜎(W1ft−1
S + W2
∑︁
T∈N(S)
ft−1
T ),
where S is a subgraph of the input graph of size k.
Challenges
• Scalability
• GPU memory consumption
12
Hierarchical k-GNN
Idea
Learn features for subgraphs in a hierarchical way
13
Hierarchical k-GNN
Idea
Learn features for subgraphs in a hierarchical way
1-GNN
. . .
2-GNN
. . .
3-GNN
. . .
MLP
Pool
Pool
Pool
Learning higher-order graph properties
13
Experimental Results
PRO IMDB-M NCI1 PTC-FM MUTAG
0
20
40
60
80
100
Accuracy[%]
1-GNN
1-k-GNN
Figure 3: Classification: Improvement on smaller benchmark datasets
14
Experimental Results
U0 ZPVE H
0.00
0.25
0.50
0.75
1.00
1.25
1.50
1.75
2.00
Errornormalizedto1-GNN(lowerisbetter)
1-k-GNN
1-GNN
MPNN
DTNN
Figure 4: Regression (QM9 data set): Gain over 1-GNN baseline
15
Conclusion
1 Relationship between 1-WL kernel and Graph Neural Networks
• GNN are a differentiable version of 1-WL
• GNNs and 1-WL are equally powerful
2 Higher-order graph embeddings
• k-dimensional GNN
• Hierarchical Variant
3 Experimental results
• Good results for large datasets with continuous node labels
16
Conclusion
1 Relationship between 1-WL kernel and Graph Neural Networks
• GNN are a differentiable version of 1-WL
• GNNs and 1-WL are equally powerful
2 Higher-order graph embeddings
• k-dimensional GNN
• Hierarchical Variant
3 Experimental results
• Good results for large datasets with continuous node labels
Collection of graph classification benchmarks
graphkernels.cs.tu-dortmund.de
16

Weitere ähnliche Inhalte

Was ist angesagt?

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringConvolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringSOYEON KIM
 
Representation learning on graphs
Representation learning on graphsRepresentation learning on graphs
Representation learning on graphsDeakin University
 
[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)Donghyeon Kim
 
Graph kernels
Graph kernelsGraph kernels
Graph kernelsLuc Brun
 
Improving Machine Learning using Graph Algorithms
Improving Machine Learning using Graph AlgorithmsImproving Machine Learning using Graph Algorithms
Improving Machine Learning using Graph AlgorithmsNeo4j
 
Graph Convolutional Neural Networks
Graph Convolutional Neural Networks Graph Convolutional Neural Networks
Graph Convolutional Neural Networks 신동 강
 
Deep Generative Models
Deep Generative Models Deep Generative Models
Deep Generative Models Chia-Wen Cheng
 
Image-to-Image Translation
Image-to-Image TranslationImage-to-Image Translation
Image-to-Image TranslationJunho Kim
 
Graph Neural Network (한국어)
Graph Neural Network (한국어)Graph Neural Network (한국어)
Graph Neural Network (한국어)Jungwon Kim
 
Graph Neural Networks.pptx
Graph Neural Networks.pptxGraph Neural Networks.pptx
Graph Neural Networks.pptxKumar Iyer
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...Shuhei Yoshida
 
Network embedding
Network embeddingNetwork embedding
Network embeddingSOYEON KIM
 
Introduction to Transformers for NLP - Olga Petrova
Introduction to Transformers for NLP - Olga PetrovaIntroduction to Transformers for NLP - Olga Petrova
Introduction to Transformers for NLP - Olga PetrovaAlexey Grigorev
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative ModelsMLReview
 
Graph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype PredictionGraph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype Predictiontuxette
 
Basic Generative Adversarial Networks
Basic Generative Adversarial NetworksBasic Generative Adversarial Networks
Basic Generative Adversarial NetworksDong Heon Cho
 
Graph Neural Network in practice
Graph Neural Network in practiceGraph Neural Network in practice
Graph Neural Network in practicetuxette
 
Generative Adversarial Networks (GANs) - Ian Goodfellow, OpenAI
Generative Adversarial Networks (GANs) - Ian Goodfellow, OpenAIGenerative Adversarial Networks (GANs) - Ian Goodfellow, OpenAI
Generative Adversarial Networks (GANs) - Ian Goodfellow, OpenAIWithTheBest
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural NetworksPyData
 

Was ist angesagt? (20)

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringConvolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
 
Representation learning on graphs
Representation learning on graphsRepresentation learning on graphs
Representation learning on graphs
 
Gnn overview
Gnn overviewGnn overview
Gnn overview
 
[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)[기초개념] Graph Convolutional Network (GCN)
[기초개념] Graph Convolutional Network (GCN)
 
Graph kernels
Graph kernelsGraph kernels
Graph kernels
 
Improving Machine Learning using Graph Algorithms
Improving Machine Learning using Graph AlgorithmsImproving Machine Learning using Graph Algorithms
Improving Machine Learning using Graph Algorithms
 
Graph Convolutional Neural Networks
Graph Convolutional Neural Networks Graph Convolutional Neural Networks
Graph Convolutional Neural Networks
 
Deep Generative Models
Deep Generative Models Deep Generative Models
Deep Generative Models
 
Image-to-Image Translation
Image-to-Image TranslationImage-to-Image Translation
Image-to-Image Translation
 
Graph Neural Network (한국어)
Graph Neural Network (한국어)Graph Neural Network (한국어)
Graph Neural Network (한국어)
 
Graph Neural Networks.pptx
Graph Neural Networks.pptxGraph Neural Networks.pptx
Graph Neural Networks.pptx
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gen...
 
Network embedding
Network embeddingNetwork embedding
Network embedding
 
Introduction to Transformers for NLP - Olga Petrova
Introduction to Transformers for NLP - Olga PetrovaIntroduction to Transformers for NLP - Olga Petrova
Introduction to Transformers for NLP - Olga Petrova
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative Models
 
Graph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype PredictionGraph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype Prediction
 
Basic Generative Adversarial Networks
Basic Generative Adversarial NetworksBasic Generative Adversarial Networks
Basic Generative Adversarial Networks
 
Graph Neural Network in practice
Graph Neural Network in practiceGraph Neural Network in practice
Graph Neural Network in practice
 
Generative Adversarial Networks (GANs) - Ian Goodfellow, OpenAI
Generative Adversarial Networks (GANs) - Ian Goodfellow, OpenAIGenerative Adversarial Networks (GANs) - Ian Goodfellow, OpenAI
Generative Adversarial Networks (GANs) - Ian Goodfellow, OpenAI
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 

Ähnlich wie Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...ssuser2624f71
 
Spatial patterns in evolutionary games on scale-free networks and multiplexes
Spatial patterns in evolutionary games on scale-free networks and multiplexesSpatial patterns in evolutionary games on scale-free networks and multiplexes
Spatial patterns in evolutionary games on scale-free networks and multiplexesKolja Kleineberg
 
Graph theory concepts complex networks presents-rouhollah nabati
Graph theory concepts   complex networks presents-rouhollah nabatiGraph theory concepts   complex networks presents-rouhollah nabati
Graph theory concepts complex networks presents-rouhollah nabatinabati
 
Quantum persistent k cores for community detection
Quantum persistent k cores for community detectionQuantum persistent k cores for community detection
Quantum persistent k cores for community detectionColleen Farrelly
 
Minimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applicationsMinimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applicationsLuis Galárraga
 
The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics
The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics
The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics Kolja Kleineberg
 
ON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRY
ON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRYON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRY
ON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRYFransiskeran
 
Skiena algorithm 2007 lecture10 graph data strctures
Skiena algorithm 2007 lecture10 graph data strcturesSkiena algorithm 2007 lecture10 graph data strctures
Skiena algorithm 2007 lecture10 graph data strctureszukun
 
On algorithmic problems concerning graphs of higher degree of symmetry
On algorithmic problems concerning graphs of higher degree of symmetryOn algorithmic problems concerning graphs of higher degree of symmetry
On algorithmic problems concerning graphs of higher degree of symmetrygraphhoc
 
A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...
A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...
A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...cseiitgn
 
NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...
NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...
NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...ssuser4b1f48
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsMathias Niepert
 
Neo4j MeetUp - Graph Exploration with MetaExp
Neo4j MeetUp - Graph Exploration with MetaExpNeo4j MeetUp - Graph Exploration with MetaExp
Neo4j MeetUp - Graph Exploration with MetaExpAdrian Ziegler
 
Spectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structuresSpectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structuresDavid Gleich
 

Ähnlich wie Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks (20)

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
 
Spatial patterns in evolutionary games on scale-free networks and multiplexes
Spatial patterns in evolutionary games on scale-free networks and multiplexesSpatial patterns in evolutionary games on scale-free networks and multiplexes
Spatial patterns in evolutionary games on scale-free networks and multiplexes
 
Graph theory concepts complex networks presents-rouhollah nabati
Graph theory concepts   complex networks presents-rouhollah nabatiGraph theory concepts   complex networks presents-rouhollah nabati
Graph theory concepts complex networks presents-rouhollah nabati
 
Spectral graph theory
Spectral graph theorySpectral graph theory
Spectral graph theory
 
Slides4
Slides4Slides4
Slides4
 
Quantum persistent k cores for community detection
Quantum persistent k cores for community detectionQuantum persistent k cores for community detection
Quantum persistent k cores for community detection
 
Minimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applicationsMinimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applications
 
The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics
The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics
The Hidden Geometry of Multiplex Networks @ Next Generation Network Analytics
 
ON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRY
ON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRYON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRY
ON ALGORITHMIC PROBLEMS CONCERNING GRAPHS OF HIGHER DEGREE OF SYMMETRY
 
Skiena algorithm 2007 lecture10 graph data strctures
Skiena algorithm 2007 lecture10 graph data strcturesSkiena algorithm 2007 lecture10 graph data strctures
Skiena algorithm 2007 lecture10 graph data strctures
 
On algorithmic problems concerning graphs of higher degree of symmetry
On algorithmic problems concerning graphs of higher degree of symmetryOn algorithmic problems concerning graphs of higher degree of symmetry
On algorithmic problems concerning graphs of higher degree of symmetry
 
A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...
A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...
A Quest for Subexponential Time Parameterized Algorithms for Planar-k-Path: F...
 
NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...
NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...
NS-CUK Seminar: S.T.Nguyen, Review on "Make Heterophily Graphs Better Fit GNN...
 
Module 22-graphs
Module 22-graphsModule 22-graphs
Module 22-graphs
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
 
Neo4j MeetUp - Graph Exploration with MetaExp
Neo4j MeetUp - Graph Exploration with MetaExpNeo4j MeetUp - Graph Exploration with MetaExp
Neo4j MeetUp - Graph Exploration with MetaExp
 
Spectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structuresSpectral clustering with motifs and higher-order structures
Spectral clustering with motifs and higher-order structures
 
Lgm saarbrucken
Lgm saarbruckenLgm saarbrucken
Lgm saarbrucken
 
Quantitative Redistricting Workshop - Machine Learning for Fair Redistricting...
Quantitative Redistricting Workshop - Machine Learning for Fair Redistricting...Quantitative Redistricting Workshop - Machine Learning for Fair Redistricting...
Quantitative Redistricting Workshop - Machine Learning for Fair Redistricting...
 
Graph Theory
Graph TheoryGraph Theory
Graph Theory
 

Kürzlich hochgeladen

GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)Areesha Ahmad
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professormuralinath2
 
300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptxryanrooker
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformationAreesha Ahmad
 
biology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGYbiology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGY1301aanya
 
Introduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxIntroduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxrohankumarsinghrore1
 
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)AkefAfaneh2
 
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryFAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryAlex Henderson
 
Use of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxUse of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxRenuJangid3
 
Grade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsGrade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsOrtegaSyrineMay
 
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flypumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flyPRADYUMMAURYA1
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...Scintica Instrumentation
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)Areesha Ahmad
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxSuji236384
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceAlex Henderson
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxseri bangash
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticssakshisoni2385
 
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Silpa
 

Kürzlich hochgeladen (20)

GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
biology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGYbiology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGY
 
Introduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxIntroduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptx
 
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)COMPUTING ANTI-DERIVATIVES(Integration by SUBSTITUTION)
COMPUTING ANTI-DERIVATIVES (Integration by SUBSTITUTION)
 
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryFAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
 
Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Use of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxUse of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptx
 
Grade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsGrade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its Functions
 
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit flypumpkin fruit fly, water melon fruit fly, cucumber fruit fly
pumpkin fruit fly, water melon fruit fly, cucumber fruit fly
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical Science
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptx
 
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICEPATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
 

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

  • 1. Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe November 12, 2018 TU Dortmund University, RWTH Aachen University, McGill University
  • 2. Motivation Question How similar are two graphs? (a) Sildenafil (b) Vardenafil 1
  • 3. High-level View: Supervised Graph Classification 2
  • 4. High-level View: Supervised Graph Classification ⊆ H φ: G → H 2
  • 5. High-level View: Supervised Graph Classification ⊆ H φ: G → H 2
  • 6. Talk Structure 1 State-of-the-art methods for graph classification 2 Relationship between 1-WL kernel and Graph Neural Networks 3 Higher-order graph properties 4 Experimental results 3
  • 7. Supervised Graph Classification: The State-of-the-Art Kernel Methods Find predefined substructures and count them somehow: • Shortest-paths or random walks • Motifs • h-neighborhoods around vertices • Spectral Approaches 4
  • 8. Supervised Graph Classification: The State-of-the-Art Kernel Methods Find predefined substructures and count them somehow: • Shortest-paths or random walks • Motifs • h-neighborhoods around vertices • Spectral Approaches Neural Methods Parameterized neighborhood aggregation function f (t) v = 𝜎(W1 f (t−1) v + W2 ∑︁ w∈N(v) f (t−1) w ) and learn parameters W1 and W2 together with the parameters of the classifier 4
  • 9. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
  • 10. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical 𝜑(G1) = ( ) (a) G1 𝜑(G2) = ( ) (b) G2 N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
  • 11. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical 𝜑(G1) = (2, 2, 2, ) (a) G1 𝜑(G2) = (1, 1, 3, ) (b) G2 N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
  • 12. Example: Weisfeiler-Lehman Subtree Kernel Example (Weisfeiler-Lehman Subtree Kernel) Graph kernel based on heuristic for graph isomorphism testing Iteration: Two vertices get identical colors iff their colored neighborhoods are identical 𝜑(G1) = (2, 2, 2, 2, 2, 2, 0, 0) (a) G1 𝜑(G2) = (1, 1, 3, 2, 0, 1, 1, 1) (b) G2 N. Shervashidze, P. Schweitzer, E. J. van Leeuwen, K. Mehlhorn, and K. M. Borgwardt. “Weisfeiler-Lehman Graph Kernels”. In: JMLR 12 (2011), pp. 2539–2561 5
  • 13. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ 6
  • 14. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ 6
  • 15. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ Both methods aggregate colors/features of neighbors 6
  • 16. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ Both methods aggregate colors/features of neighbors Theorem (Informal) GNNs cannot be more expressive than 1-WL in terms of distinguishing non-isomorphic graphs. 6
  • 17. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ 7
  • 18. Relationship between 1-WL and GNN 1-WL coloring c(t) (v) = hash (︁ c(t−1) (v), {{c(t−1) (w) | w ∈ N(v)}} )︁ General form of GNNs h(t) (v) = f W (t) 1 merge (︁ h(t−1) (v), f W (t) 2 aggr (︀ {{h(t−1) (w) | w ∈ N(v)}} )︀)︁ Insight GNNs are as powerful as 1-WL if f W (t) 1 merge and f W (t) 2 aggr are injective Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 7
  • 19. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 8
  • 20. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 1-WL GNN ∇ 8
  • 21. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 1-WL GNN ∇ Take Away GNNs have the same power as 1-WL in distinguishing non-isomorphic graphs. 8
  • 22. Relationship between 1-WL and GNN Theorem (Informal) There exists a GNN architecture and corresponding weights such that it reaches an equivalent coloring as 1-WL. 1-WL GNN ∇ Take Away GNNs have the same power as 1-WL in distinguishing non-isomorphic graphs. Limits of 1-WL are well understood. V. Arvind, J. Köbler, G. Rattan, and O. Verbitsky. “On the Power of Color Refinement”. In: Symposium on Fundamentals of Computation Theory. 2015, pp. 339–350 8
  • 23. Limits of GNNs Observation GNNs cannot distinguish very basic graph properties, e.g., • Cycle-free vs. cyclic graphs • Triangle counts • Regular graphs 9
  • 24. Limits of GNNs Observation GNNs cannot distinguish very basic graph properties, e.g., • Cycle-free vs. cyclic graphs • Triangle counts • Regular graphs Observation Higher-order graph properties play an important role for the characterization of real-world networks. 9
  • 25. Higher-order Graph Properties Challenge Incorporate more higher-order graph properties into Graph Neural Networks. 10
  • 26. Higher-order Graph Properties Challenge Incorporate more higher-order graph properties into Graph Neural Networks. 1-WL GNN k-WL k-GNN ∇ Global Global ∇ 10
  • 27. Higher-order Graph Properties Challenge Incorporate more higher-order graph properties into Graph Neural Networks. 1-WL GNN k-WL k-GNN ∇ Global Global ∇ Idea: k-WL Color subgraphs instead of vertices, and define neighborhoods between them. 10
  • 28. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 11
  • 29. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 11
  • 30. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 Idea of the Algorithm Initially Two tuples get the same color if the induced subgraphs are isomorphic 11
  • 31. k-dimensional Weisfeiler-Lehman k-dimensional Weisfeiler-Lehman • Colors vertex tuples from Vk • Two tuples v, w are i-neighbors if vj = wj for all j ̸= i v1 v2 v3 v4 v5 v6 Idea of the Algorithm Initially Two tuples get the same color if the induced subgraphs are isomorphic Iteration Two tuples get same color iff they have the same colored neighborhood 11
  • 32. k-GNN Idea Derive k-dimensional Graph Neural Network ft S = 𝜎(W1ft−1 S + W2 ∑︁ T∈N(S) ft−1 T ), where S is a subgraph of the input graph of size k. 12
  • 33. k-GNN Idea Derive k-dimensional Graph Neural Network ft S = 𝜎(W1ft−1 S + W2 ∑︁ T∈N(S) ft−1 T ), where S is a subgraph of the input graph of size k. Challenges • Scalability • GPU memory consumption 12
  • 34. Hierarchical k-GNN Idea Learn features for subgraphs in a hierarchical way 13
  • 35. Hierarchical k-GNN Idea Learn features for subgraphs in a hierarchical way 1-GNN . . . 2-GNN . . . 3-GNN . . . MLP Pool Pool Pool Learning higher-order graph properties 13
  • 36. Experimental Results PRO IMDB-M NCI1 PTC-FM MUTAG 0 20 40 60 80 100 Accuracy[%] 1-GNN 1-k-GNN Figure 3: Classification: Improvement on smaller benchmark datasets 14
  • 37. Experimental Results U0 ZPVE H 0.00 0.25 0.50 0.75 1.00 1.25 1.50 1.75 2.00 Errornormalizedto1-GNN(lowerisbetter) 1-k-GNN 1-GNN MPNN DTNN Figure 4: Regression (QM9 data set): Gain over 1-GNN baseline 15
  • 38. Conclusion 1 Relationship between 1-WL kernel and Graph Neural Networks • GNN are a differentiable version of 1-WL • GNNs and 1-WL are equally powerful 2 Higher-order graph embeddings • k-dimensional GNN • Hierarchical Variant 3 Experimental results • Good results for large datasets with continuous node labels 16
  • 39. Conclusion 1 Relationship between 1-WL kernel and Graph Neural Networks • GNN are a differentiable version of 1-WL • GNNs and 1-WL are equally powerful 2 Higher-order graph embeddings • k-dimensional GNN • Hierarchical Variant 3 Experimental results • Good results for large datasets with continuous node labels Collection of graph classification benchmarks graphkernels.cs.tu-dortmund.de 16