Discovering Invariant Rationales for Graph Neural NetworksDownload PDF

29 Sept 2021, 00:31 (edited 30 Jan 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: Interpretability, Graph Neural Networks, Causal Discovery, Invariant Learning
  • Abstract: Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features --- rationale --- which guides the model prediction. Unfortunately, the leading rationalization models often rely on data biases, especially shortcut features, to compose rationales and make predictions without probing the critical and causal patterns. Moreover, such data biases easily change outside the training distribution. As a result, these models suffer from a huge drop in interpretability and predictive performance on out-of-distribution data. In this work, we propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs. It conducts interventions on the training distribution to create multiple interventional distributions. Then it approaches the causal rationales that are invariant across different distributions while filtering out the spurious patterns that are unstable. Experiments on both synthetic and real-world datasets validate the superiority of our DIR in terms of interpretability and generalization ability on graph classification over the leading baselines. Code and datasets are available at https://github.com/Wuyxin/DIR-GNN.
  • One-sentence Summary: We propose a novel invariant learning algorithm, Discovering Invariant Rationale (DIR), for intrinsically interpretable models.
16 Replies

Loading