Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

• URL: http://arxiv.org/abs/2209.14107v1
• Date: Wed, 28 Sep 2022 13:55:52 GMT
• Title: Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure
• Authors: Shaohua Fan, Xiao Wang, Yanhu Mo, Chuan Shi, Jian Tang
• Abstract summary: 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.
• Score: 46.86463923605841
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. However, by presenting a graph classification investigation on the training graphs with severe bias, surprisingly, we discover that GNNs always tend to explore the spurious correlations to make decision, even if the causal correlation always exists. This implies that existing GNNs trained on such biased datasets will suffer from poor generalization capability. By analyzing this problem in a causal view, we find that disentangling and decorrelating the causal and bias latent variables from the biased graphs are both crucial for debiasing. Inspiring by this, we propose a general disentangled GNN framework to learn the causal substructure and bias substructure, respectively. Particularly, we design a parameterized edge mask generator to explicitly split the input graph into causal and bias subgraphs. Then two GNN modules supervised by causal/bias-aware loss functions respectively are trained to encode causal and bias subgraphs into their corresponding representations. With the disentangled representations, we synthesize the counterfactual unbiased training samples to further decorrelate causal and bias variables. Moreover, to better benchmark the severe bias problem, we construct three new graph datasets, which have controllable bias degrees and are easier to visualize and explain. Experimental results well demonstrate that our approach achieves superior generalization performance over existing baselines. Furthermore, owing to the learned edge mask, the proposed model has appealing interpretability and transferability. Code and data are available at: https://github.com/googlebaba/DisC.

Related papers

• 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)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Deconfounded Training for Graph Neural Networks [98.06386851685645]
  We present a new paradigm of decon training (DTP) that better mitigates the confounding effect and latches on the critical information. Specifically, we adopt the attention modules to disentangle the critical subgraph and trivial subgraph. It allows GNNs to capture a more reliable subgraph whose relation with the label is robust across different distributions.
  arXiv  Detail & Related papers  (2021-12-30T15:22:35Z)
• 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)
• Graph Classification by Mixture of Diverse Experts [67.33716357951235]
  We present GraphDIVE, a framework leveraging mixture of diverse experts for imbalanced graph classification. With a divide-and-conquer principle, GraphDIVE employs a gating network to partition an imbalanced graph dataset into several subsets. Experiments on real-world imbalanced graph datasets demonstrate the effectiveness of GraphDIVE.
  arXiv  Detail & Related papers  (2021-03-29T14:03:03Z)

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.