Causal invariant geographic network representations with feature and structural distribution shifts

Abstract

The existing methods learn geographic network representations through deep graph neural networks (GNNs) based on the i.i.d. assumption. However, the spatial heterogeneity and temporal dynamics of geographic data make the out-of-distribution (OOD) generalisation problem particularly salient. The latter are particularly sensitive to distribution shifts (feature and structural shifts) between testing and training data and are the main causes of the OOD generalisation problem. Spurious correlations are present between invariant and background representations due to selection biases and environmental effects, resulting in the model extremes being more likely to learn background representations. The existing approaches focus on background representation changes that are determined by shifts in the feature distributions of nodes in the training and test data while ignoring changes in the proportional distributions of heterogeneous and homogeneous neighbour nodes, which we refer to as structural distribution shifts. We propose a feature-structure mixed invariant representation learning (FSM-IRL) model that accounts for both feature distribution shifts and structural distribution shifts. To address structural distribution shifts, we introduce a sampling method based on causal attention, encouraging the model to identify nodes possessing strong causal relationships with labels or nodes that are more similar to the target node. Inspired by the Hilbert-Schmidt independence criterion, we implement a reweighting strategy to maximise the orthogonality of the node representations, thereby mitigating the spurious correlations among the node representations and suppressing the learning of background representations. Our experiments demonstrate that FSM-IRL exhibits strong learning capabilities on both geographic and social network datasets in OOD scenarios.

15 pages, 3 figures, 8 tables

References in corpus (23)

• A Comprehensive Survey on Graph Neural Networks
• Spatial Networks
• OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networks
• Domain Generalization: A Survey
• Deep Learning for Short-Term Traffic Flow Prediction
• Graph Contrastive Learning with Augmentations
• COVID-19 lockdown induces disease-mitigating structural changes in mobility networks
• Multiscale Dynamic Human Mobility Flow Dataset in the U.S. during the COVID-19 Epidemic
• Towards Out-Of-Distribution Generalization: A Survey
• Causal Attention for Interpretable and Generalizable Graph Classification
• Alleviating Structural Distribution Shift in Graph Anomaly Detection
• Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
• GOOD: A Graph Out-of-Distribution Benchmark
• Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
• Out-Of-Distribution Generalization on Graphs: A Survey
• Towards Fair Graph Neural Networks via Graph Counterfactual
• Region2Vec: Community Detection on Spatial Networks Using Graph Embedding with Node Attributes and Spatial Interactions
• SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks
• Neural Embeddings of Urban Big Data Reveal Emergent Structures in Cities
• Deconfounding to Explanation Evaluation in Graph Neural Networks
• OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs
• Learning Invariant Representations of Graph Neural Networks via Cluster Generalization
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks