Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks

2025-07-22

AI Summary

Existing GNNs suffer from performance degradation on heterogeneous graphs due to the failure of the homophily assumption and the neglect of higher-order structural information. To address this, we propose HPGNN, a novel graph neural network that explicitly models multi-scale topological structures. Its core innovation lies in the first integration of efficient high-order personalized PageRank (PPR) approximation into the GNN framework, enabling explicit incorporation of both long-range dependencies and local neighborhood information. This design mitigates label conflict noise and enhances robust modeling of heterogeneous relational patterns. HPGNN performs hierarchical information aggregation via PPR-guided graph convolution. Extensive experiments demonstrate that HPGNN outperforms five out of seven state-of-the-art methods on multiple heterogeneous graph benchmarks, while maintaining competitive performance on homogeneous graphs—validating its generalizability and effectiveness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph Neural Networks (GNNs) excel in node classification tasks but often assume homophily, where connected nodes share similar labels. This assumption does not hold in many real-world heterophilic graphs. Existing models for heterophilic graphs primarily rely on pairwise relationships, overlooking multi-scale information from higher-order structures. This leads to suboptimal performance, particularly under noise from conflicting class information across nodes. To address these challenges, we propose HPGNN, a novel model integrating Higher-order Personalized PageRank with Graph Neural Networks. HPGNN introduces an efficient high-order approximation of Personalized PageRank (PPR) to capture long-range and multi-scale node interactions. This approach reduces computational complexity and mitigates noise from surrounding information. By embedding higher-order structural information into convolutional networks, HPGNN effectively models key interactions across diverse graph dimensions. Extensive experiments on benchmark datasets demonstrate HPGNN's effectiveness. The model achieves better performance than five out of seven state-of-the-art methods on heterophilic graphs in downstream tasks while maintaining competitive performance on homophilic graphs. HPGNN's ability to balance multi-scale information and robustness to noise makes it a versatile solution for real-world graph learning challenges. Codes are available at https://github.com/streetcorner/HPGNN.

Problem

• Addresses GNN limitations in heterophilic graph classification
• Incorporates higher-order structures for multi-scale node interactions
• Reduces noise impact from conflicting class information

Innovation

• Integrates Higher-order Personalized PageRank with GNNs
• Uses efficient high-order PPR approximation
• Embeds higher-order structures into convolutional networks