PISA: Prioritized Invariant Subgraph Aggregation

2025-11-27

AI Summary

To address performance degradation in out-of-distribution (OOD) generalization of graph data—caused by structural complexity and diverse distribution shifts—this paper proposes a Dynamic Multi-Invariant Subgraph Aggregation (DMISA) framework. Unlike existing methods relying on a single invariant subgraph, DMISA jointly models multiple causally consistent subgraph patterns via a learnable, dynamic MLP-based prioritized aggregation mechanism. It integrates causal modeling, an information-theoretic objective, diversity-aware subgraph sampling, and regularization to achieve robust nonlinear fusion. Extensive experiments across 15 standard graph OOD benchmarks—including DrugOOD—demonstrate that DMISA improves average classification accuracy by up to 5% over state-of-the-art baselines, significantly enhancing model adaptability and generalization under heterogeneous distribution shifts.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and diverse distribution shifts in node attributes and topology. To handle these, Chen et al. proposed CIGA (Chen et al., 2022b), which uses causal modeling and an information-theoretic objective to extract a single invariant subgraph capturing causal features. However, this single-subgraph focus can miss multiple causal patterns. Liu et al. (2025) addressed this with SuGAr, which learns and aggregates diverse invariant subgraphs via a sampler and diversity regularizer, improving robustness but still relying on simple uniform or greedy aggregation. To overcome this, the proposed PISA framework introduces a dynamic MLP-based aggregation that prioritizes and combines subgraph representations more effectively. Experiments on 15 datasets, including DrugOOD (Ji et al., 2023), show that PISA achieves up to 5% higher classification accuracy than prior methods.

Problem

• Extracts multiple invariant subgraphs for graph OOD generalization
• Prioritizes subgraph aggregation with dynamic MLP for robustness
• Improves classification accuracy on diverse distribution shifts

Innovation

• Dynamic MLP-based aggregation prioritizes subgraph representations
• Overcomes single-subgraph limitation by combining multiple causal patterns
• Improves robustness in graph OOD generalization via effective aggregation