Timezone: »
Explaining machine learning models is an important and increasingly popular area of research interest. The Shapley value from game theory has been proposed as a prime approach to compute feature importance towards model predictions on images, text, tabular data, and recently graph neural networks (GNNs) on graphs. In this work, we revisit the appropriateness of the Shapley value for GNN explanation, where the task is to identify the most important subgraph and constituent nodes for GNN predictions. We claim that the Shapley value is a non-ideal choice for graph data because it is by definition not structure-aware. We propose a Graph Structure-aware eXplanation (GStarX) method to leverage the critical graph structure information to improve the explanation. Specifically, we define a scoring function based on a new structure-aware value from the cooperative game theory proposed by Hamiache and Navarro (HN). When used to score node importance, the HN value utilizes graph structures to attribute cooperation surplus between neighbor nodes, resembling message passing in GNNs, so that node importance scores reflect not only the node feature importance, but also the node structural roles. We demonstrate that GStarX produces qualitatively more intuitive explanations, and quantitatively improves explanation fidelity over strong baselines on chemical graph property prediction and text graph sentiment classification. Code: https://github.com/ShichangZh/GStarX
Author Information
Shichang Zhang (University of California, Los Angeles)
Yozen Liu (Snap Inc.)
Neil Shah (Snap Research)
Yizhou Sun (UCLA)
More from the Same Authors
-
2022 : Group Excess Risk Bound of Overparameterized Linear Regression with Constant-Stepsize SGD »
Arjun Subramonian · Levent Sagun · Kai-Wei Chang · Yizhou Sun -
2022 : Unit Selection: Learning Benefit Function from Finite Population Data »
Ang Li · Song Jiang · Yizhou Sun · Judea Pearl -
2022 : Dissimilar Nodes Improve Graph Active Learning »
Zhicheng Ren · Yifu Yuan · Yuxin Wu · Xiaxuan Gao · Yewen Wang · Yizhou Sun -
2022 : Empowering Language Models with Knowledge Graph Reasoning for Question Answering »
Ziniu Hu · Yichong Xu · Wenhao Yu · Shuohang Wang · Ziyi Yang · Chenguang Zhu · Kai-Wei Chang · Yizhou Sun -
2023 Poster: GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Node Patching »
Mingxuan Ju · Tong Zhao · Wenhao Yu · Neil Shah · Yanfang Ye -
2023 Poster: Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? »
Haitao Mao · Zhikai Chen · Wei Jin · Haoyu Han · Yao Ma · Tong Zhao · Neil Shah · Jiliang Tang -
2023 Poster: CARE: Modeling Interacting Dynamics Under Temporal Distribution Shift »
Xiao Luo · Haixin Wang · Zijie Huang · Huiyu Jiang · Abhijeet Gangan · Song Jiang · Yizhou Sun -
2023 Poster: AVIS: Autonomous Visual Information Seeking with Large Language Models »
Ziniu Hu · Ahmet Iscen · Chen Sun · Kai-Wei Chang · Yizhou Sun · Cordelia Schmid · David Ross · Alireza Fathi -
2023 Poster: Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation »
Wei Jin · Haitao Mao · Zheng Li · Haoming Jiang · Chen Luo · Hongzhi Wen · Haoyu Han · Hanqing Lu · Zhengyang Wang · Ruirui Li · Zhen Li · Monica Cheng · Rahul Goutam · Haiyang Zhang · Karthik Subbian · Suhang Wang · Yizhou Sun · Jiliang Tang · Bing Yin · Xianfeng Tang -
2023 Poster: Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking »
Juanhui Li · Harry Shomer · Haitao Mao · Shenglai Zeng · Yao Ma · Neil Shah · Jiliang Tang · Dawei Yin -
2023 Poster: Towards a Comprehensive Benchmark for FPGA Targeted High-Level Synthesis »
Yunsheng Bai · Atefeh Sohrabizadeh · Zongyue Qin · Ziniu Hu · Yizhou Sun · Jason Cong -
2022 Spotlight: Improving Multi-Task Generalization via Regularizing Spurious Correlation »
Ziniu Hu · Zhe Zhao · Xinyang Yi · Tiansheng Yao · Lichan Hong · Yizhou Sun · Ed Chi -
2022 Workshop: New Frontiers in Graph Learning »
Jiaxuan You · Marinka Zitnik · Rex Ying · Yizhou Sun · Hanjun Dai · Stefanie Jegelka -
2022 Poster: Improving Multi-Task Generalization via Regularizing Spurious Correlation »
Ziniu Hu · Zhe Zhao · Xinyang Yi · Tiansheng Yao · Lichan Hong · Yizhou Sun · Ed Chi -
2022 Poster: On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs »
Arjun Subramonian · Kai-Wei Chang · Yizhou Sun -
2022 Poster: A Practical, Progressively-Expressive GNN »
Lingxiao Zhao · Neil Shah · Leman Akoglu -
2020 Poster: Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations »
Zijie Huang · Yizhou Sun · Wei Wang -
2019 Workshop: Graph Representation Learning »
Will Hamilton · Rianne van den Berg · Michael Bronstein · Stefanie Jegelka · Thomas Kipf · Jure Leskovec · Renjie Liao · Yizhou Sun · Petar Veličković -
2019 Poster: Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks »
Difan Zou · Ziniu Hu · Yewen Wang · Song Jiang · Yizhou Sun · Quanquan Gu