Explainable Graph Representation Learning via Graph Pattern Analysis

2025-12-04

AI Summary

This work addresses the interpretability of graph representation learning: specifically, what structural and semantic information is encoded in learned graph representations? To this end, we propose PXGL-GNN—the first method to directly interpret graph embeddings at the representation level. Inspired by graph kernels, PXGL-GNN samples diverse subgraph patterns, jointly learns pattern-level representations with node features, and aggregates them via learnable weights to produce human-interpretable, attribution-aware graph embeddings. Theoretical analysis establishes its robustness and generalization guarantees. Extensive experiments on multiple real-world datasets demonstrate that PXGL-GNN significantly outperforms state-of-the-art baselines in both supervised and unsupervised tasks. Crucially, it provides intuitive, verifiable subgraph-pattern attributions—thereby advancing graph neural networks from opaque “black-box” models toward transparent, interpretable modeling.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for 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 query analysis, representation and understanding

Abstract

Explainable artificial intelligence (XAI) is an important area in the AI community, and interpretability is crucial for building robust and trustworthy AI models. While previous work has explored model-level and instance-level explainable graph learning, there has been limited investigation into explainable graph representation learning. In this paper, we focus on representation-level explainable graph learning and ask a fundamental question: What specific information about a graph is captured in graph representations? Our approach is inspired by graph kernels, which evaluate graph similarities by counting substructures within specific graph patterns. Although the pattern counting vector can serve as an explainable representation, it has limitations such as ignoring node features and being high-dimensional. To address these limitations, we introduce a framework (PXGL-GNN) for learning and explaining graph representations through graph pattern analysis. We start by sampling graph substructures of various patterns. Then, we learn the representations of these patterns and combine them using a weighted sum, where the weights indicate the importance of each graph pattern's contribution. We also provide theoretical analyses of our methods, including robustness and generalization. In our experiments, we show how to learn and explain graph representations for real-world data using pattern analysis. Additionally, we compare our method against multiple baselines in both supervised and unsupervised learning tasks to demonstrate its effectiveness.

Problem

• Develops explainable graph representation learning via pattern analysis
• Addresses limitations of pattern counting by incorporating node features
• Provides theoretical robustness and generalization analyses for the method

Innovation

• Learning graph representations via pattern analysis
• Weighted combination of sampled substructure patterns
• Theoretical analysis of robustness and generalization