SlideShare a Scribd company logo
1 of 13
Van Thuy Hoang
Dept. of Artificial Intelligence,
The Catholic University of Korea
hoangvanthuy90@gmail.com
Haiteng Zhao, et al.; ICLR23
2
 Problems
 Proposed model architecture
 Novel graph transformer model named DeepGraph
 Why more self-attention layers become a
disadvantage
 Experiments
3
CONCLUSION
 ZINC dataset of different graph transformers by varying their depths.
4
RELATED WORK
 Graph transformers
 Some other works introduce structure information into attention
by graph distance, path embedding or feature encoded by GNN
 Pure transformers
 Recent works apply transformers in graph tasks by designing a
variety of structure encoding techniques
 Deep neural networks
 Graph substructure
 Certain substructures can also be the pivotal feature for graph
property prediction
5
TRANSFORMER
 The core module of the transformer is self-attention
6
Overview of the proposed graph encoding framework
 X
7
SUBSTRUCTURE SAMPLING
 The sampled substructures cover every node of the graph as evenly
as possible in order to reduce biases resulting from the uneven
density of substructures
8
SUBSTRUCTURE TOKEN ENCODING
 The formal definition of substructure token encoder is
 A single sample is sufficient during training to allow the model to
learn the substructure stably.
9
LOCAL ATTENTION ON SUBSTRUCTURES
 The substructure and its corresponding nodes receive localized
attention after substructure tokens have been added
 mask M is added in selfattention module
10
EXPERIMENTS
 DATASETS:
 PCQM4M-LSC
 ZINC
 PATTERN
 CLUSTER
 BASELINES
 GT
 SAT
 Graphormer
11
RESULTS
 EFFECT OF DEEPENING
 deepen them by 2 and 4 times compared to the original version.
12
CONCLUSION
 Presents the bottleneck of graph transformers’ performance when
depth increases
 A novel graph transformer model based on substructure-based local
attention with additional substructure tokens
NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Transformers?", International Conference on Learning Representations 2023

More Related Content

Similar to NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Transformers?", International Conference on Learning Representations 2023

Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...
Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...
Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...I MT
 
NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...
NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...
NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...ssuser4b1f48
 
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...Virendra Uppalwar
 
Samtec whitepaper
Samtec whitepaperSamtec whitepaper
Samtec whitepaperjohn_111
 
Stochastic Computing Correlation Utilization in Convolutional Neural Network ...
Stochastic Computing Correlation Utilization in Convolutional Neural Network ...Stochastic Computing Correlation Utilization in Convolutional Neural Network ...
Stochastic Computing Correlation Utilization in Convolutional Neural Network ...TELKOMNIKA JOURNAL
 
REVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNNREVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNNIRJET Journal
 
Design of an Efficient Communication Protocol for 3d Interconnection Network
Design of an Efficient Communication Protocol for 3d Interconnection NetworkDesign of an Efficient Communication Protocol for 3d Interconnection Network
Design of an Efficient Communication Protocol for 3d Interconnection NetworkIJMTST Journal
 
turecko-150426_pse_01
turecko-150426_pse_01turecko-150426_pse_01
turecko-150426_pse_01Peter Fabo
 
[20240422_LabSeminar_Huy]Taming_Effect.pptx
[20240422_LabSeminar_Huy]Taming_Effect.pptx[20240422_LabSeminar_Huy]Taming_Effect.pptx
[20240422_LabSeminar_Huy]Taming_Effect.pptxthanhdowork
 
Simulating the triba noc architecture
Simulating the triba noc architectureSimulating the triba noc architecture
Simulating the triba noc architectureijmnct
 
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...ssuser4b1f48
 
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...ssuser4b1f48
 
Multiple Valued Logic for Synthesis and Simulation of Digital Circuits
Multiple Valued Logic for Synthesis and Simulation of Digital CircuitsMultiple Valued Logic for Synthesis and Simulation of Digital Circuits
Multiple Valued Logic for Synthesis and Simulation of Digital CircuitsIJERA Editor
 
A Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptxA Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptxssuser2624f71
 
Vlsi design process for low power design methodology using reconfigurable fpga
Vlsi design process for low power design methodology using reconfigurable fpgaVlsi design process for low power design methodology using reconfigurable fpga
Vlsi design process for low power design methodology using reconfigurable fpgaeSAT Publishing House
 

Similar to NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Transformers?", International Conference on Learning Representations 2023 (20)

62
6262
62
 
Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...
Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...
Colloque IMT -04/04/2019- L'IA au cœur des mutations industrielles - L'IA pou...
 
NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...
NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...
NS-CUK Seminar: S.T.Nguyen, Review on "Are More Layers Beneficial to Graph Tr...
 
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
 
Samtec whitepaper
Samtec whitepaperSamtec whitepaper
Samtec whitepaper
 
FPGA IMPLEMENTATION OF APPROXIMATE SOFTMAX FUNCTION FOR EFFICIENT CNN INFERENCE
FPGA IMPLEMENTATION OF APPROXIMATE SOFTMAX FUNCTION FOR EFFICIENT CNN INFERENCEFPGA IMPLEMENTATION OF APPROXIMATE SOFTMAX FUNCTION FOR EFFICIENT CNN INFERENCE
FPGA IMPLEMENTATION OF APPROXIMATE SOFTMAX FUNCTION FOR EFFICIENT CNN INFERENCE
 
Jj2416341637
Jj2416341637Jj2416341637
Jj2416341637
 
Stochastic Computing Correlation Utilization in Convolutional Neural Network ...
Stochastic Computing Correlation Utilization in Convolutional Neural Network ...Stochastic Computing Correlation Utilization in Convolutional Neural Network ...
Stochastic Computing Correlation Utilization in Convolutional Neural Network ...
 
REVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNNREVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNN
 
Design of an Efficient Communication Protocol for 3d Interconnection Network
Design of an Efficient Communication Protocol for 3d Interconnection NetworkDesign of an Efficient Communication Protocol for 3d Interconnection Network
Design of an Efficient Communication Protocol for 3d Interconnection Network
 
turecko-150426_pse_01
turecko-150426_pse_01turecko-150426_pse_01
turecko-150426_pse_01
 
[20240422_LabSeminar_Huy]Taming_Effect.pptx
[20240422_LabSeminar_Huy]Taming_Effect.pptx[20240422_LabSeminar_Huy]Taming_Effect.pptx
[20240422_LabSeminar_Huy]Taming_Effect.pptx
 
Simulating the triba noc architecture
Simulating the triba noc architectureSimulating the triba noc architecture
Simulating the triba noc architecture
 
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...
 
Scolari's ICCD17 Talk
Scolari's ICCD17 TalkScolari's ICCD17 Talk
Scolari's ICCD17 Talk
 
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...
 
Multiple Valued Logic for Synthesis and Simulation of Digital Circuits
Multiple Valued Logic for Synthesis and Simulation of Digital CircuitsMultiple Valued Logic for Synthesis and Simulation of Digital Circuits
Multiple Valued Logic for Synthesis and Simulation of Digital Circuits
 
A Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptxA Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptx
 
Circuit Simplifier
Circuit SimplifierCircuit Simplifier
Circuit Simplifier
 
Vlsi design process for low power design methodology using reconfigurable fpga
Vlsi design process for low power design methodology using reconfigurable fpgaVlsi design process for low power design methodology using reconfigurable fpga
Vlsi design process for low power design methodology using reconfigurable fpga
 

More from Network Science Lab, The Catholic University of Korea

More from Network Science Lab, The Catholic University of Korea (20)

230727_HB_JointJournalClub.pptx
230727_HB_JointJournalClub.pptx230727_HB_JointJournalClub.pptx
230727_HB_JointJournalClub.pptx
 
S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"
S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"
S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"
 
230724_Thuy_Labseminar.pptx
230724_Thuy_Labseminar.pptx230724_Thuy_Labseminar.pptx
230724_Thuy_Labseminar.pptx
 
230724-JH-Lab Seminar.pptx
230724-JH-Lab Seminar.pptx230724-JH-Lab Seminar.pptx
230724-JH-Lab Seminar.pptx
 
5강 - 멀티모달 및 모듈화.pptx
5강 - 멀티모달 및 모듈화.pptx5강 - 멀티모달 및 모듈화.pptx
5강 - 멀티모달 및 모듈화.pptx
 
3강 - CNN 및 이미지 모델.pptx
3강 - CNN 및 이미지 모델.pptx3강 - CNN 및 이미지 모델.pptx
3강 - CNN 및 이미지 모델.pptx
 
4강 - RNN 및 시계열 모델.pptx
4강 - RNN 및 시계열 모델.pptx4강 - RNN 및 시계열 모델.pptx
4강 - RNN 및 시계열 모델.pptx
 
2강 - 실험 흐름과 멀티모달 개요.pptx
2강 - 실험 흐름과 멀티모달 개요.pptx2강 - 실험 흐름과 멀티모달 개요.pptx
2강 - 실험 흐름과 멀티모달 개요.pptx
 
1강 - pytorch와 tensor.pptx
1강 - pytorch와 tensor.pptx1강 - pytorch와 tensor.pptx
1강 - pytorch와 tensor.pptx
 
Technical Report on "Lecture Quality Prediction using Graph Neural Networks"
Technical Report on "Lecture Quality Prediction using Graph Neural Networks"Technical Report on "Lecture Quality Prediction using Graph Neural Networks"
Technical Report on "Lecture Quality Prediction using Graph Neural Networks"
 
Presentation for "Lecture Quality Prediction using Graph Neural Networks"
Presentation for "Lecture Quality Prediction using Graph Neural Networks"Presentation for "Lecture Quality Prediction using Graph Neural Networks"
Presentation for "Lecture Quality Prediction using Graph Neural Networks"
 
NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...
NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...
NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...
 
NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...
NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...
NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...
 
Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...
Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...
Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...
 
Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...
Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...
Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...
 
NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural net...
NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural net...NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural net...
NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural net...
 
Sang_Graphormer.pdf
Sang_Graphormer.pdfSang_Graphormer.pdf
Sang_Graphormer.pdf
 
NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...
NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...
NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...
 
NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...
NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...
NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...
 
NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...
NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...
NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...
 

Recently uploaded

How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 

Recently uploaded (20)

How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 

NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Transformers?", International Conference on Learning Representations 2023

  • 1. Van Thuy Hoang Dept. of Artificial Intelligence, The Catholic University of Korea hoangvanthuy90@gmail.com Haiteng Zhao, et al.; ICLR23
  • 2. 2  Problems  Proposed model architecture  Novel graph transformer model named DeepGraph  Why more self-attention layers become a disadvantage  Experiments
  • 3. 3 CONCLUSION  ZINC dataset of different graph transformers by varying their depths.
  • 4. 4 RELATED WORK  Graph transformers  Some other works introduce structure information into attention by graph distance, path embedding or feature encoded by GNN  Pure transformers  Recent works apply transformers in graph tasks by designing a variety of structure encoding techniques  Deep neural networks  Graph substructure  Certain substructures can also be the pivotal feature for graph property prediction
  • 5. 5 TRANSFORMER  The core module of the transformer is self-attention
  • 6. 6 Overview of the proposed graph encoding framework  X
  • 7. 7 SUBSTRUCTURE SAMPLING  The sampled substructures cover every node of the graph as evenly as possible in order to reduce biases resulting from the uneven density of substructures
  • 8. 8 SUBSTRUCTURE TOKEN ENCODING  The formal definition of substructure token encoder is  A single sample is sufficient during training to allow the model to learn the substructure stably.
  • 9. 9 LOCAL ATTENTION ON SUBSTRUCTURES  The substructure and its corresponding nodes receive localized attention after substructure tokens have been added  mask M is added in selfattention module
  • 10. 10 EXPERIMENTS  DATASETS:  PCQM4M-LSC  ZINC  PATTERN  CLUSTER  BASELINES  GT  SAT  Graphormer
  • 11. 11 RESULTS  EFFECT OF DEEPENING  deepen them by 2 and 4 times compared to the original version.
  • 12. 12 CONCLUSION  Presents the bottleneck of graph transformers’ performance when depth increases  A novel graph transformer model based on substructure-based local attention with additional substructure tokens