Discovering Invariant Rationales for Graph Neural Networks
- URL: http://arxiv.org/abs/2201.12872v1
- Date: Sun, 30 Jan 2022 16:43:40 GMT
- Title: Discovering Invariant Rationales for Graph Neural Networks
- Authors: Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, Tat-Seng Chua
- Abstract summary: Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features.
We propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs.
- Score: 104.61908788639052
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Generalization of Graph Neural Networks is Robust to Model Mismatch [84.01980526069075]
Graph neural networks (GNNs) have demonstrated their effectiveness in various tasks supported by their generalization capabilities.
In this paper, we examine GNNs that operate on geometric graphs generated from manifold models.
Our analysis reveals the robustness of the GNN generalization in the presence of such model mismatch.
arXiv Detail & Related papers (2024-08-25T16:00:44Z) - Graph Out-of-Distribution Generalization via Causal Intervention [69.70137479660113]
We introduce a conceptually simple yet principled approach for training robust graph neural networks (GNNs) under node-level distribution shifts.
Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor.
Our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks.
arXiv Detail & Related papers (2024-02-18T07:49:22Z) - Interpreting Unfairness in Graph Neural Networks via Training Node
Attribution [46.384034587689136]
We study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes.
Specifically, we propose a novel strategy named Probabilistic Distribution Disparity (PDD) to measure the bias exhibited in GNNs.
We verify the validity of PDD and the effectiveness of influence estimation through experiments on real-world datasets.
arXiv Detail & Related papers (2022-11-25T21:52:30Z) - Debiasing Graph Neural Networks via Learning Disentangled Causal
Substructure [46.86463923605841]
We present a graph classification investigation on the training graphs with severe bias.
We discover that GNNs always tend to explore the spurious correlations to make decision.
We propose a general disentangled GNN framework to learn the causal substructure and bias substructure.
arXiv Detail & Related papers (2022-09-28T13:55:52Z) - OOD-GNN: Out-of-Distribution Generalized Graph Neural Network [73.67049248445277]
Graph neural networks (GNNs) have achieved impressive performance when testing and training graph data come from identical distribution.
Existing GNNs lack out-of-distribution generalization abilities so that their performance substantially degrades when there exist distribution shifts between testing and training graph data.
We propose an out-of-distribution generalized graph neural network (OOD-GNN) for achieving satisfactory performance on unseen testing graphs that have different distributions with training graphs.
arXiv Detail & Related papers (2021-12-07T16:29:10Z) - Generalizing Graph Neural Networks on Out-Of-Distribution Graphs [51.33152272781324]
Graph Neural Networks (GNNs) are proposed without considering the distribution shifts between training and testing graphs.
In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation.
We propose a general causal representation framework, called StableGNN, to eliminate the impact of spurious correlations.
arXiv Detail & Related papers (2021-11-20T18:57:18Z) - Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications.
To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently.
Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes.
Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements.
A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
arXiv Detail & Related papers (2021-10-20T14:23:54Z)
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.