GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations

• URL: http://arxiv.org/abs/2309.16223v2
• Date: Sun, 5 Nov 2023 16:34:36 GMT
• Title: GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations
• Authors: Kenza Amara and Mennatallah El-Assady and Rex Ying
• Abstract summary: Diverse explainability methods of graph neural networks (GNN) have been developed to highlight the edges and nodes in the graph that contribute the most to the model predictions. It is not clear yet how to evaluate the correctness of those explanations, whether it is from a human or a model perspective. We propose GInX-Eval, an evaluation procedure of graph explanations that overcomes the pitfalls of faithfulness.
• Score: 21.997015999698732
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Diverse explainability methods of graph neural networks (GNN) have recently been developed to highlight the edges and nodes in the graph that contribute the most to the model predictions. However, it is not clear yet how to evaluate the correctness of those explanations, whether it is from a human or a model perspective. One unaddressed bottleneck in the current evaluation procedure is the problem of out-of-distribution explanations, whose distribution differs from those of the training data. This important issue affects existing evaluation metrics such as the popular faithfulness or fidelity score. In this paper, we show the limitations of faithfulness metrics. We propose GInX-Eval (Graph In-distribution eXplanation Evaluation), an evaluation procedure of graph explanations that overcomes the pitfalls of faithfulness and offers new insights on explainability methods. Using a fine-tuning strategy, the GInX score measures how informative removed edges are for the model and the EdgeRank score evaluates if explanatory edges are correctly ordered by their importance. GInX-Eval verifies if ground-truth explanations are instructive to the GNN model. In addition, it shows that many popular methods, including gradient-based methods, produce explanations that are not better than a random designation of edges as important subgraphs, challenging the findings of current works in the area. Results with GInX-Eval are consistent across multiple datasets and align with human evaluation.

Related papers

• On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions [49.8110352174327]
  We assess attribution methods from a perspective not previously explored in the graph domain: retraining. The core idea is to retrain the network on important (or not important) relationships as identified by the attributions. We run our analysis on four state-of-the-art GNN attribution methods and five synthetic and real-world graph classification datasets.
  arXiv  Detail & Related papers  (2024-01-01T02:03:35Z)
• Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks [32.345435955298825]
  Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. A main challenge in studying GNN explainability is to provide fidelity measures that evaluate the performance of these explanation functions. This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics.
  arXiv  Detail & Related papers  (2023-10-03T06:25:14Z)
• Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching [68.35685422301613]
  We propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs. It couples the target graph with other counterpart instances and identifies the most crucial joint substructure by minimizing the node corresponding-based distance. Experiments on synthetic and real-world datasets show the effectiveness of our MatchExplainer by outperforming all state-of-the-art parametric baselines with significant margins.
  arXiv  Detail & Related papers  (2023-01-07T05:14:45Z)
• Reinforced Causal Explainer for Graph Neural Networks [112.57265240212001]
  Explainability is crucial for probing graph neural networks (GNNs) We propose a reinforcement learning agent, Reinforced Causal Explainer (RC-Explainer) RC-Explainer generates faithful and concise explanations, and has a better power to unseen graphs.
  arXiv  Detail & Related papers  (2022-04-23T09:13:25Z)
• Deconfounding to Explanation Evaluation in Graph Neural Networks [136.73451468551656]
  We argue that a distribution shift exists between the full graph and the subgraph, causing the out-of-distribution problem. We propose Deconfounded Subgraph Evaluation (DSE) which assesses the causal effect of an explanatory subgraph on the model prediction.
  arXiv  Detail & Related papers  (2022-01-21T18:05:00Z)
• GraphSVX: Shapley Value Explanations for Graph Neural Networks [81.83769974301995]
  Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data. In this paper, we propose a unified framework satisfied by most existing GNN explainers. We introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs.
  arXiv  Detail & Related papers  (2021-04-18T10:40:37Z)
• Explainability in Graph Neural Networks: A Taxonomic Survey [42.95574260417341]
  Graph neural networks (GNNs) and their explainability are experiencing rapid developments. There is neither a unified treatment of GNN explainability methods, nor a standard benchmark and testbed for evaluations. This work provides a unified methodological treatment of GNN explainability and a standardized testbed for evaluations.
  arXiv  Detail & Related papers  (2020-12-31T04:34:27Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.