Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis
Dec 15, 2023
Speakers
Junfeng Fang
Speaker · 0 followers
About
This work studies the evaluation of explaining graph neural networks (GNNs), which is crucial to the credibility of post-hoc explainability in practical usage. Conventional evaluation metrics, and even explanation methods -- which mainly follow the paradigm of feeding the explanatory subgraph and measuring output difference -- always suffer from the notorious out-of-distribution (OOD) issue. In this work, we endeavor to confront the issue by introducing a novel evaluation metric, termed **O**OD-resistant **A**dversarial **R**obustness (OAR). Specifically, we draw inspiration from the notion of adversarial robustness and evaluate post-hoc explanation subgraphs by calculating their robustness under attack. On top of that, an elaborate OOD reweighting block is inserted into the pipeline to confine the evaluation process to the original data distribution. For applications involving large datasets, we further devise a **Sim**plified version of **OAR** (SimOAR), which achieves a significant improvement in computational efficiency at the cost of a small amount of performance. Extensive empirical studies validate the effectiveness of our OAR and SimOAR.This work studies the evaluation of explaining graph neural networks (GNNs), which is crucial to the credibility of post-hoc explainability in practical usage. Conventional evaluation metrics, and even explanation methods -- which mainly follow the paradigm of feeding the explanatory subgraph and measuring output difference -- always suffer from the notorious out-of-distribution (OOD) issue. In this work, we endeavor to confront the issue by introducing a novel evaluation metric, termed **O**OD-…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning and Processing the Ordinal information of Temporal Sequences in Recurrent Neural Circuits
Watch later
Xiaolong Zou, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
Watch later
Jiaqi Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Curriculum Learning with Infant Egocentric Videos
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Explaining Self-Driving Cars for Accountable Autonomy.
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%