SlideShare a Scribd company logo
1 of 11
Download to read offline
RGE: A Repulsive Graph Rectification for Node
Classification via Influence
Jaeyun Song*, Sung-Yub Kim*, Eunho Yang
ICML 2023
Graduate School of AI, KAIST
Introduction
● Graph Neural Networks (GNNs) are susceptible to structural noises in graphs.
● Chen et al. (2022a) proposed an influence function for individual edges to estimate
the counterfactual effects of removing them.
● We first identify the group influence estimation error of Exhaustive Group
Elimination (EGE), that eliminates all opponent edges at once and propose
Repulsive Group Elimination (RGE), that removes distant edges over neighboring
edges to reduce group effect in GNNs.
A single harmful edge (dotted) can negatively affect the
predictions of multiple nodes (colored).
Problem
• Our goal is to find opponent edges 𝐸′ ⊆ 𝐸 that can improve the test performance when
remove the original graph 𝐺 = (𝑉, 𝐸) . Formally, this can be formulated as
• To avoid the combinatorial explosion of selecting an edge set, we consider a simple
strategy, called Exhaustive edge Group Elimination (EGE):
• The key assumption for the optimality of EGE is the additivity of individual influences.
Graph without 𝐸′
Influence of removing 𝐸′
Problem
• Even though the influence additivity cannot be guaranteed in general graphs, we found
the influence additivity can be established between distant edges for the widely used
GNNs, including GCN, SGC, GAT, and GraphSAGE.
• Proposition 3.1 (Influence additivity for distant edges) Let edges 𝑒, 𝑒′
∈ 𝐸 be distant edges
and, for them, assume that the removal of edge 𝑒 does not change the gradient of
unaffected train node 𝒗 :
for 𝑣 ∈ 𝑉𝑇𝑟 and 𝑣 ∉ 𝑉𝑇𝑟(𝑒). Then, the influence additivity holds.
• Detailed proofs can be found in Appendix B!
Method Overview
• The overview of our method
• Compute the influence for all edges
• Remove non-adjacent edges (distant edges) with negative influence
• Retrain GNNs on graphs without those edges
Repeat these processes until there are no more negative edges
labeled nodes unlabeled nodes non-negative edges negative edges
Remove negative
distant edges
& Retrain GNNs
Repeat processes
Rectified graph
Method
• Repulsive selection rule & Multi-step edge elimination (under 1-layer SGC)
labeled nodes unlabeled nodes non-negative edges negative edges
Choose the most
negative edge
Choose the second
most negative
non-adjacent edge
selected edges
1-st Iteration
Remove edges
& Retrain GNNs
Choose the most
negative edge
2-nd Iteration
Remove edges
& Retrain GNNs
Repeat processes
Experiment: Group Influence Estimation Errors
• RGE significantly decreases the group influence estimation errors
EGE RGE
Group Influence Estimation Errors
Experiment: Performance on Homophilous Graphs
• RGE outperforms other baselines
Experiment: Performance under Other Architectures
• Rectified graphs under SGC are also effective on other architectures.
Conclusion
• We demonstrate that removing opponent edges simultaneously can increase the
estimation errors of group influence, which might result in performance drops
• We propose a new approach to rectify graphs via multiple steps while reducing group
influence estimation errors by removing distant edges at each step
• We show that our method reduces group influence estimation errors and exhibits
superior performance compared to baselines
Thank you!

More Related Content

Similar to J. Song, S. Kim, ICML 2023, MLILAB, KAISTAI

Automatic Generation of Persistent Formations Under Range Constraints
Automatic Generation of Persistent Formations Under Range ConstraintsAutomatic Generation of Persistent Formations Under Range Constraints
Automatic Generation of Persistent Formations Under Range Constraints
elliando dias
 
Image segmentation methods for brain mri images
Image segmentation methods for brain mri imagesImage segmentation methods for brain mri images
Image segmentation methods for brain mri images
eSAT Journals
 
zhaowei_LIU_acme_2016
zhaowei_LIU_acme_2016zhaowei_LIU_acme_2016
zhaowei_LIU_acme_2016
Zhaowei Liu
 

Similar to J. Song, S. Kim, ICML 2023, MLILAB, KAISTAI (20)

VJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCNVJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCN
 
Paper Presentation (Graph)
Paper Presentation (Graph)Paper Presentation (Graph)
Paper Presentation (Graph)
 
An Efficient Algorithm for Edge Detection of Corroded Surface
An Efficient Algorithm for Edge Detection of Corroded SurfaceAn Efficient Algorithm for Edge Detection of Corroded Surface
An Efficient Algorithm for Edge Detection of Corroded Surface
 
An Efficient Algorithm for Edge Detection of Corroded Surface
An Efficient Algorithm for Edge Detection of Corroded SurfaceAn Efficient Algorithm for Edge Detection of Corroded Surface
An Efficient Algorithm for Edge Detection of Corroded Surface
 
Study and Comparison of Various Image Edge Detection Techniques
Study and Comparison of Various Image Edge Detection TechniquesStudy and Comparison of Various Image Edge Detection Techniques
Study and Comparison of Various Image Edge Detection Techniques
 
220206 transformer interpretability beyond attention visualization
220206 transformer interpretability beyond attention visualization220206 transformer interpretability beyond attention visualization
220206 transformer interpretability beyond attention visualization
 
Automatic Generation of Persistent Formations Under Range Constraints
Automatic Generation of Persistent Formations Under Range ConstraintsAutomatic Generation of Persistent Formations Under Range Constraints
Automatic Generation of Persistent Formations Under Range Constraints
 
Real time Canny edge detection
Real time Canny edge detectionReal time Canny edge detection
Real time Canny edge detection
 
NeurIPS22.pptx
NeurIPS22.pptxNeurIPS22.pptx
NeurIPS22.pptx
 
195706916 i journals-paper-template-2013
195706916 i journals-paper-template-2013195706916 i journals-paper-template-2013
195706916 i journals-paper-template-2013
 
Image segmentation methods for brain mri images
Image segmentation methods for brain mri imagesImage segmentation methods for brain mri images
Image segmentation methods for brain mri images
 
04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Distance transforms and correlation maps for advanced 3D analysis of impact d...
Distance transforms and correlation maps for advanced 3D analysis of impact d...Distance transforms and correlation maps for advanced 3D analysis of impact d...
Distance transforms and correlation maps for advanced 3D analysis of impact d...
 
The neural tangent link between CNN denoisers and non-local filters
The neural tangent link between CNN denoisers and non-local filtersThe neural tangent link between CNN denoisers and non-local filters
The neural tangent link between CNN denoisers and non-local filters
 
J. Park, H. Shim, AAAI 2022, MLILAB, KAISTAI
J. Park, H. Shim, AAAI 2022, MLILAB, KAISTAIJ. Park, H. Shim, AAAI 2022, MLILAB, KAISTAI
J. Park, H. Shim, AAAI 2022, MLILAB, KAISTAI
 
Ds33717725
Ds33717725Ds33717725
Ds33717725
 
Ds33717725
Ds33717725Ds33717725
Ds33717725
 
zhaowei_LIU_acme_2016
zhaowei_LIU_acme_2016zhaowei_LIU_acme_2016
zhaowei_LIU_acme_2016
 
Visibility graphs
Visibility graphsVisibility graphs
Visibility graphs
 

More from MLILAB

H. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AIH. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AI
MLILAB
 

More from MLILAB (20)

J. Jeong, AAAI 2024, MLILAB, KAIST AI..
J. Jeong,  AAAI 2024, MLILAB, KAIST AI..J. Jeong,  AAAI 2024, MLILAB, KAIST AI..
J. Jeong, AAAI 2024, MLILAB, KAIST AI..
 
J. Yun, NeurIPS 2023, MLILAB, KAISTAI
J. Yun,  NeurIPS 2023,  MLILAB,  KAISTAIJ. Yun,  NeurIPS 2023,  MLILAB,  KAISTAI
J. Yun, NeurIPS 2023, MLILAB, KAISTAI
 
S. Kim, NeurIPS 2023, MLILAB, KAISTAI
S. Kim,  NeurIPS 2023,  MLILAB,  KAISTAIS. Kim,  NeurIPS 2023,  MLILAB,  KAISTAI
S. Kim, NeurIPS 2023, MLILAB, KAISTAI
 
C. Kim, INTERSPEECH 2023, MLILAB, KAISTAI
C. Kim, INTERSPEECH 2023, MLILAB, KAISTAIC. Kim, INTERSPEECH 2023, MLILAB, KAISTAI
C. Kim, INTERSPEECH 2023, MLILAB, KAISTAI
 
Y. Jung, ICML 2023, MLILAB, KAISTAI
Y. Jung, ICML 2023, MLILAB, KAISTAIY. Jung, ICML 2023, MLILAB, KAISTAI
Y. Jung, ICML 2023, MLILAB, KAISTAI
 
K. Seo, ICASSP 2023, MLILAB, KAISTAI
K. Seo, ICASSP 2023, MLILAB, KAISTAIK. Seo, ICASSP 2023, MLILAB, KAISTAI
K. Seo, ICASSP 2023, MLILAB, KAISTAI
 
G. Kim, CVPR 2023, MLILAB, KAISTAI
G. Kim, CVPR 2023, MLILAB, KAISTAIG. Kim, CVPR 2023, MLILAB, KAISTAI
G. Kim, CVPR 2023, MLILAB, KAISTAI
 
S. Kim, ICLR 2023, MLILAB, KAISTAI
S. Kim, ICLR 2023, MLILAB, KAISTAIS. Kim, ICLR 2023, MLILAB, KAISTAI
S. Kim, ICLR 2023, MLILAB, KAISTAI
 
Y. Kim, ICLR 2023, MLILAB, KAISTAI
Y. Kim, ICLR 2023, MLILAB, KAISTAIY. Kim, ICLR 2023, MLILAB, KAISTAI
Y. Kim, ICLR 2023, MLILAB, KAISTAI
 
J. Yun, AISTATS 2022, MLILAB, KAISTAI
J. Yun, AISTATS 2022, MLILAB, KAISTAIJ. Yun, AISTATS 2022, MLILAB, KAISTAI
J. Yun, AISTATS 2022, MLILAB, KAISTAI
 
J. Song, J. Park, ICML 2022, MLILAB, KAISTAI
J. Song, J. Park, ICML 2022, MLILAB, KAISTAIJ. Song, J. Park, ICML 2022, MLILAB, KAISTAI
J. Song, J. Park, ICML 2022, MLILAB, KAISTAI
 
J. Park, J. Song, ICLR 2022, MLILAB, KAISTAI
J. Park, J. Song, ICLR 2022, MLILAB, KAISTAIJ. Park, J. Song, ICLR 2022, MLILAB, KAISTAI
J. Park, J. Song, ICLR 2022, MLILAB, KAISTAI
 
J. Park, AAAI 2022, MLILAB, KAIST AI
J. Park, AAAI 2022, MLILAB, KAIST AIJ. Park, AAAI 2022, MLILAB, KAIST AI
J. Park, AAAI 2022, MLILAB, KAIST AI
 
J. Song, et. al., ASRU 2021, MLILAB, KAIST AI
J. Song, et. al., ASRU 2021, MLILAB, KAIST AIJ. Song, et. al., ASRU 2021, MLILAB, KAIST AI
J. Song, et. al., ASRU 2021, MLILAB, KAIST AI
 
J. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AI
J. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AIJ. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AI
J. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AI
 
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AIT. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
 
G. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AI
G. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AIG. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AI
G. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AI
 
I. Chung, AAAI 2020, MLILAB, KAIST AI
I. Chung, AAAI 2020, MLILAB, KAIST AII. Chung, AAAI 2020, MLILAB, KAIST AI
I. Chung, AAAI 2020, MLILAB, KAIST AI
 
H. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AIH. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AI
 
J. Yi, ICLR 2020, MLILAB, KAIST AI
J. Yi, ICLR 2020, MLILAB, KAIST AIJ. Yi, ICLR 2020, MLILAB, KAIST AI
J. Yi, ICLR 2020, MLILAB, KAIST AI
 

Recently uploaded

Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Christo Ananth
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
Tonystark477637
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
dollysharma2066
 
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
dharasingh5698
 

Recently uploaded (20)

BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxBSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdfONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
 
Call for Papers - International Journal of Intelligent Systems and Applicatio...
Call for Papers - International Journal of Intelligent Systems and Applicatio...Call for Papers - International Journal of Intelligent Systems and Applicatio...
Call for Papers - International Journal of Intelligent Systems and Applicatio...
 
Vivazz, Mieres Social Housing Design Spain
Vivazz, Mieres Social Housing Design SpainVivazz, Mieres Social Housing Design Spain
Vivazz, Mieres Social Housing Design Spain
 
UNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICS
UNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICSUNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICS
UNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICS
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
NFPA 5000 2024 standard .
NFPA 5000 2024 standard                                  .NFPA 5000 2024 standard                                  .
NFPA 5000 2024 standard .
 
Intze Overhead Water Tank Design by Working Stress - IS Method.pdf
Intze Overhead Water Tank  Design by Working Stress - IS Method.pdfIntze Overhead Water Tank  Design by Working Stress - IS Method.pdf
Intze Overhead Water Tank Design by Working Stress - IS Method.pdf
 
(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
 
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
 

J. Song, S. Kim, ICML 2023, MLILAB, KAISTAI

  • 1. RGE: A Repulsive Graph Rectification for Node Classification via Influence Jaeyun Song*, Sung-Yub Kim*, Eunho Yang ICML 2023 Graduate School of AI, KAIST
  • 2. Introduction ● Graph Neural Networks (GNNs) are susceptible to structural noises in graphs. ● Chen et al. (2022a) proposed an influence function for individual edges to estimate the counterfactual effects of removing them. ● We first identify the group influence estimation error of Exhaustive Group Elimination (EGE), that eliminates all opponent edges at once and propose Repulsive Group Elimination (RGE), that removes distant edges over neighboring edges to reduce group effect in GNNs. A single harmful edge (dotted) can negatively affect the predictions of multiple nodes (colored).
  • 3. Problem • Our goal is to find opponent edges 𝐸′ ⊆ 𝐸 that can improve the test performance when remove the original graph 𝐺 = (𝑉, 𝐸) . Formally, this can be formulated as • To avoid the combinatorial explosion of selecting an edge set, we consider a simple strategy, called Exhaustive edge Group Elimination (EGE): • The key assumption for the optimality of EGE is the additivity of individual influences. Graph without 𝐸′ Influence of removing 𝐸′
  • 4. Problem • Even though the influence additivity cannot be guaranteed in general graphs, we found the influence additivity can be established between distant edges for the widely used GNNs, including GCN, SGC, GAT, and GraphSAGE. • Proposition 3.1 (Influence additivity for distant edges) Let edges 𝑒, 𝑒′ ∈ 𝐸 be distant edges and, for them, assume that the removal of edge 𝑒 does not change the gradient of unaffected train node 𝒗 : for 𝑣 ∈ 𝑉𝑇𝑟 and 𝑣 ∉ 𝑉𝑇𝑟(𝑒). Then, the influence additivity holds. • Detailed proofs can be found in Appendix B!
  • 5. Method Overview • The overview of our method • Compute the influence for all edges • Remove non-adjacent edges (distant edges) with negative influence • Retrain GNNs on graphs without those edges Repeat these processes until there are no more negative edges labeled nodes unlabeled nodes non-negative edges negative edges Remove negative distant edges & Retrain GNNs Repeat processes Rectified graph
  • 6. Method • Repulsive selection rule & Multi-step edge elimination (under 1-layer SGC) labeled nodes unlabeled nodes non-negative edges negative edges Choose the most negative edge Choose the second most negative non-adjacent edge selected edges 1-st Iteration Remove edges & Retrain GNNs Choose the most negative edge 2-nd Iteration Remove edges & Retrain GNNs Repeat processes
  • 7. Experiment: Group Influence Estimation Errors • RGE significantly decreases the group influence estimation errors EGE RGE Group Influence Estimation Errors
  • 8. Experiment: Performance on Homophilous Graphs • RGE outperforms other baselines
  • 9. Experiment: Performance under Other Architectures • Rectified graphs under SGC are also effective on other architectures.
  • 10. Conclusion • We demonstrate that removing opponent edges simultaneously can increase the estimation errors of group influence, which might result in performance drops • We propose a new approach to rectify graphs via multiple steps while reducing group influence estimation errors by removing distant edges at each step • We show that our method reduces group influence estimation errors and exhibits superior performance compared to baselines