SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
Graph Neural Networks (GNNs) Meet Reinforcement
Learning (RL)
05/01/2021
Graph Neural Networks (GNNs)
Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph
convolutional networks." arXiv preprint arXiv:1609.02907 (2016).
● Targeting at real-world problems having underlying graph
structures which are non-Euclidean.
○ Euclidean data is data which is sensibly modelled as
being plotted in n-dimensional linear space, e.g.,
images (where the x and y coordinates refer to the
location of each pixel, and the z coordinate refers to its
colour/intensity).
○ Non-Euclidean data: have information of edges,
values associated with nodes, or the directionality of
edges.
Graph Neural Networks (GNNs)
Tasks
Graph Neural Networks (GNNs)
Neural Networks Forward Propagation
●
● w is weights, H is the last hidden states, b is the bias and
sigma is the nonlinear function.
● When i = 0, then H[i]
= X, where X is the input.
Graph Neural Networks
● Sparse.
● Flexible connection.
Graph Neural Networks (GNNs)
Definitions
● Adjacency matrix (A): a N x N matrix filled
with either 0 or 1, where N is the total number
of nodes.
● Node attributes matrix (X): represents the
features or attributes of each node. If there are
N nodes and the size of node attributes is F,
then the shape of this matrix is N x F.
● Edge attributes matrix (E), can also have its
own attributes.
Adjacency matrix
Node attributes matrix (6 x 6)
Graph Neural Networks (GNNs)
Graph
● G = (V, E), denote a graph.
● node feature vectors Xv for v in V
Graph Neural Networks[1]
● Step1: aggregate information from neighbors.
● Step2: combine encoded neighbor’s info with its
own info.
● Step3: use READOUT function to extract the
representation.
Graph Convolutional Neural Network (GCN)
Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph
convolutional networks." arXiv preprint arXiv:1609.02907 (2016).
Aggregator + Combine:
Representation from the paper
●
GraphSAGE
Hamilton, William L., Rex Ying, and Jure Leskovec. "Inductive representation
learning on large graphs." arXiv preprint arXiv:1706.02216 (2017).
● Aggregator:
● Combine:
Representation from the paper
● Different aggregator
○ Mean, LSTM, Pooling.
GraphSAGE
Hamilton, William L., Rex Ying, and Jure Leskovec. "Inductive
representation learning on large graphs." arXiv preprint arXiv:1706.02216
(2017).
Literature Review
Dong, Jiqian, et al. "A DRL-based Multiagent
Cooperative Control Framework for CAV
Networks: a Graphic Convolution Q Network."
arXiv preprint arXiv:2010.05437 (2020).
● Combining graphic convolution neural
network (GCN) and Deep Q Network (DQN)
to solve the lane changing problem in mixed
traffic with multiple AVs.
● Off-policy Q learning.
Attention (Self-attention)
● Self-attention, also known as intra-attention, is an attention
mechanism relating different positions of a single sequence in
order to compute a representation of the same sequence.
Attention (self-attention, intra-attention)
● Different attention mechanisms.
Attention (self-attention, intra-attention)
● Born for Translation
Attention (self-attention, intra-attention)
●
Attention (self-attention, intra-attention)
●
Attention (self-attention, intra-attention)
●
Attention (self-attention, intra-attention)
●
Attention (self-attention, intra-attention)
●
Attention (self-attention, intra-attention)
● Learnable attention matrix: WQ, WK and WV.
Previous Works
● Iqbal, Shariq, and Fei Sha. "Actor-attention-critic for multi-agent
reinforcement learning." International Conference on Machine Learning.
PMLR, 2019.
Our attention critic is able to
dynamically select which agents to
attend to at each time point during
training, improving performance in
multi-agent domains with complex
interactions.
Graph Convolutional Reinforcement Learning (DGN)
Jiang, Jiechuan, et al. "Graph convolutional
reinforcement learning." arXiv preprint
arXiv:1810.09202 (2018).
● Graph convolution adapts to the dynamics of
the underlying graph of the multi-agent
environment, and relation kernels capture the
interplay between agents by their relation
representations.
● Use self-attention to extract features.
● Off-policy Q learning.
GAT on Autonomous Driving
Wang, Jiawei, et al. "Multi-agent Graph Reinforcement Learning for Connected
Automated Driving", 2020
● On-policy PPO.
● Lane-following.
References
1. Dong, Jiqian, et al. "A DRL-based Multiagent Cooperative Control Framework for CAV Networks: a
Graphic Convolution Q Network." arXiv preprint arXiv:2010.05437 (2020).
2. Gupta, Jayesh K., Maxim Egorov, and Mykel Kochenderfer. "Cooperative multi-agent control using
deep reinforcement learning." International Conference on Autonomous Agents and Multiagent
Systems. Springer, Cham, 2017.
3. Lin, Kaixiang, et al. "Efficient large-scale fleet management via multi-agent deep reinforcement
learning." Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery
& Data Mining. 2018.
4. https://ai.stackexchange.com/questions/11226/what-is-non-euclidean-data#:~:text=Since%20Euclidean
%20spaces%20are%20prototypically,coordinate%20refers%20to%20its%20colour%2F
5. https://towardsdatascience.com/understanding-graph-convolutional-networks-for-node-classification-a
2bfdb7aba7b
6. Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional
networks." arXiv preprint arXiv:1609.02907 (2016).
Thanks!

Weitere ähnliche Inhalte

Ähnlich wie GNNs meet RL.pdf

240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...
240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...
240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...thanhdowork
 
Edge Representation Learning with Hypergraphs
Edge Representation Learning with HypergraphsEdge Representation Learning with Hypergraphs
Edge Representation Learning with HypergraphsMLAI2
 
NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...
NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...
NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...ssuser4b1f48
 
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
Learning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RLLearning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RLlauratoni4
 
Laplacian-regularized Graph Bandits
Laplacian-regularized Graph BanditsLaplacian-regularized Graph Bandits
Laplacian-regularized Graph Banditslauratoni4
 
Bridging knowledge graphs_to_generate_scene_graphs
Bridging knowledge graphs_to_generate_scene_graphsBridging knowledge graphs_to_generate_scene_graphs
Bridging knowledge graphs_to_generate_scene_graphsWoen Yon Lai
 
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...ssuser4b1f48
 
An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...IJDKP
 
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...Preferred Networks
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術CHENHuiMei
 
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...ssuser4b1f48
 
From Signal to Symbols
From Signal to SymbolsFrom Signal to Symbols
From Signal to Symbolsgpano
 
An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...IJDKP
 
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
 
240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...
240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...
240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...thanhdowork
 

Ähnlich wie GNNs meet RL.pdf (20)

240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...
240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...
240311_Thuy_Labseminar[Contrastive Multi-View Representation Learning on Grap...
 
Gnn overview
Gnn overviewGnn overview
Gnn overview
 
Sun_MAPL_GNN.pptx
Sun_MAPL_GNN.pptxSun_MAPL_GNN.pptx
Sun_MAPL_GNN.pptx
 
Line
LineLine
Line
 
Edge Representation Learning with Hypergraphs
Edge Representation Learning with HypergraphsEdge Representation Learning with Hypergraphs
Edge Representation Learning with Hypergraphs
 
NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...
NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...
NS-CUK Seminar: V.T.Hoang, Review on "Exploiting Neighbor Effect: Conv-Agnost...
 
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
Learning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RLLearning Graph Representation for Data-Efficiency RL
Learning Graph Representation for Data-Efficiency RL
 
Laplacian-regularized Graph Bandits
Laplacian-regularized Graph BanditsLaplacian-regularized Graph Bandits
Laplacian-regularized Graph Bandits
 
Bridging knowledge graphs_to_generate_scene_graphs
Bridging knowledge graphs_to_generate_scene_graphsBridging knowledge graphs_to_generate_scene_graphs
Bridging knowledge graphs_to_generate_scene_graphs
 
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
 
An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...
 
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
 
From Signal to Symbols
From Signal to SymbolsFrom Signal to Symbols
From Signal to Symbols
 
An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...An experimental evaluation of similarity-based and embedding-based link predi...
An experimental evaluation of similarity-based and embedding-based link predi...
 
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
 
240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...
240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...
240401_Thanh_LabSeminar[Person Re-identification using Heterogeneous Local Gr...
 

Kürzlich hochgeladen

chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringmulugeta48
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapRishantSharmaFr
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfJiananWang21
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptNANDHAKUMARA10
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueBhangaleSonal
 
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...soginsider
 
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Bookingroncy bisnoi
 
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoorTop Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoordharasingh5698
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
 
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...tanu pandey
 
Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086anil_gaur
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTbhaskargani46
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayEpec Engineered Technologies
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Bookingdharasingh5698
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startQuintin Balsdon
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdfKamal Acharya
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptxJIT KUMAR GUPTA
 

Kürzlich hochgeladen (20)

chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineering
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leap
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.ppt
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
 
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
 
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
 
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoorTop Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
Top Rated Call Girls In chittoor 📱 {7001035870} VIP Escorts chittoor
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
 
Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086Minimum and Maximum Modes of microprocessor 8086
Minimum and Maximum Modes of microprocessor 8086
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
 
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
 

GNNs meet RL.pdf

  • 1. Graph Neural Networks (GNNs) Meet Reinforcement Learning (RL) 05/01/2021
  • 2. Graph Neural Networks (GNNs) Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016). ● Targeting at real-world problems having underlying graph structures which are non-Euclidean. ○ Euclidean data is data which is sensibly modelled as being plotted in n-dimensional linear space, e.g., images (where the x and y coordinates refer to the location of each pixel, and the z coordinate refers to its colour/intensity). ○ Non-Euclidean data: have information of edges, values associated with nodes, or the directionality of edges.
  • 3. Graph Neural Networks (GNNs) Tasks
  • 4. Graph Neural Networks (GNNs) Neural Networks Forward Propagation ● ● w is weights, H is the last hidden states, b is the bias and sigma is the nonlinear function. ● When i = 0, then H[i] = X, where X is the input. Graph Neural Networks ● Sparse. ● Flexible connection.
  • 5. Graph Neural Networks (GNNs) Definitions ● Adjacency matrix (A): a N x N matrix filled with either 0 or 1, where N is the total number of nodes. ● Node attributes matrix (X): represents the features or attributes of each node. If there are N nodes and the size of node attributes is F, then the shape of this matrix is N x F. ● Edge attributes matrix (E), can also have its own attributes. Adjacency matrix Node attributes matrix (6 x 6)
  • 6. Graph Neural Networks (GNNs) Graph ● G = (V, E), denote a graph. ● node feature vectors Xv for v in V Graph Neural Networks[1] ● Step1: aggregate information from neighbors. ● Step2: combine encoded neighbor’s info with its own info. ● Step3: use READOUT function to extract the representation.
  • 7. Graph Convolutional Neural Network (GCN) Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016). Aggregator + Combine: Representation from the paper ●
  • 8. GraphSAGE Hamilton, William L., Rex Ying, and Jure Leskovec. "Inductive representation learning on large graphs." arXiv preprint arXiv:1706.02216 (2017). ● Aggregator: ● Combine: Representation from the paper ● Different aggregator ○ Mean, LSTM, Pooling.
  • 9. GraphSAGE Hamilton, William L., Rex Ying, and Jure Leskovec. "Inductive representation learning on large graphs." arXiv preprint arXiv:1706.02216 (2017).
  • 10. Literature Review Dong, Jiqian, et al. "A DRL-based Multiagent Cooperative Control Framework for CAV Networks: a Graphic Convolution Q Network." arXiv preprint arXiv:2010.05437 (2020). ● Combining graphic convolution neural network (GCN) and Deep Q Network (DQN) to solve the lane changing problem in mixed traffic with multiple AVs. ● Off-policy Q learning.
  • 11. Attention (Self-attention) ● Self-attention, also known as intra-attention, is an attention mechanism relating different positions of a single sequence in order to compute a representation of the same sequence.
  • 12. Attention (self-attention, intra-attention) ● Different attention mechanisms.
  • 19. Attention (self-attention, intra-attention) ● Learnable attention matrix: WQ, WK and WV.
  • 20. Previous Works ● Iqbal, Shariq, and Fei Sha. "Actor-attention-critic for multi-agent reinforcement learning." International Conference on Machine Learning. PMLR, 2019. Our attention critic is able to dynamically select which agents to attend to at each time point during training, improving performance in multi-agent domains with complex interactions.
  • 21. Graph Convolutional Reinforcement Learning (DGN) Jiang, Jiechuan, et al. "Graph convolutional reinforcement learning." arXiv preprint arXiv:1810.09202 (2018). ● Graph convolution adapts to the dynamics of the underlying graph of the multi-agent environment, and relation kernels capture the interplay between agents by their relation representations. ● Use self-attention to extract features. ● Off-policy Q learning.
  • 22. GAT on Autonomous Driving Wang, Jiawei, et al. "Multi-agent Graph Reinforcement Learning for Connected Automated Driving", 2020 ● On-policy PPO. ● Lane-following.
  • 23. References 1. Dong, Jiqian, et al. "A DRL-based Multiagent Cooperative Control Framework for CAV Networks: a Graphic Convolution Q Network." arXiv preprint arXiv:2010.05437 (2020). 2. Gupta, Jayesh K., Maxim Egorov, and Mykel Kochenderfer. "Cooperative multi-agent control using deep reinforcement learning." International Conference on Autonomous Agents and Multiagent Systems. Springer, Cham, 2017. 3. Lin, Kaixiang, et al. "Efficient large-scale fleet management via multi-agent deep reinforcement learning." Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018. 4. https://ai.stackexchange.com/questions/11226/what-is-non-euclidean-data#:~:text=Since%20Euclidean %20spaces%20are%20prototypically,coordinate%20refers%20to%20its%20colour%2F 5. https://towardsdatascience.com/understanding-graph-convolutional-networks-for-node-classification-a 2bfdb7aba7b 6. Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016).