paper-with-me

Papers

Generative Causal Explanations for Graph Neural Networks

2021-04-14 · WanYu Lin, Hao Lan, Baochun Li

This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, Gem explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the graph learning tasks. In addition, Gem, once trained, can be used to explain the target GNN very quickly. Our theoretical analysis shows that several recent explainers fall into a unified framework of additive feature attribution methods. Experimental results on synthetic and real-world datasets show that Gem achieves a relative increase of the explanation accuracy by up to $30\%$ and speeds up the explanation process by up to $110\times$ as compared to its state-of-the-art alternatives.

📄 PDF Abstract BibTeX arXiv:2104.06643

Code (1)

wanyu-lin/ICML2021-Gem pytorch

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

Interpreting Graph Neural Networks via Unrevealed Causal Learning

2021-09-29 · WanYu Lin, Hao Lan, Hao Wang, Baochun Li

This paper proposes a new explanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct gener…

Graph Learning

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

2022-03-29 · CVPR 2022 1 · WanYu Lin, Hao Lan, Hao Wang, Baochun Li

This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct gener…

Graph Learning

CLEAR: Generative Counterfactual Explanations on Graphs

2022-10-16 · Jing Ma, Ruocheng Guo, Saumitra Mishra, Aidong Zhang 외

Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance be…

counterfactualCounterfactual ExplanationExplanation Generation

PAGE: Parametric Generative Explainer for Graph Neural Network

2024-08-26 · Yang Qiu, Wei Liu, Jun Wang, Ruixuan Li

This article introduces PAGE, a parameterized generative interpretive framework. PAGE is capable of providing faithful explanations for any graph neural network without necessitating prior knowledge or internal details. …

DecoderDimensionality ReductionGraph Neural Network

Generative causal explanations of black-box classifiers

2020-06-24 · NeurIPS 2020 12 · Matthew O'Shaughnessy, Gregory Canal, Marissa Connor, Mark Davenport 외

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent …