Proceedings

Heterophily-Aware Personalized PageRank for Node Classification

Giuseppe Pirrò

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 6075-6083.

https://doi.org/10.24963/ijcai.2025/676

Keywords

  • Machine Learning: ML: Representation learning
  • Machine Learning: ML: Deep learning architectures
  • Multidisciplinary Topics and Applications: MTA: Web and social networks
  • Machine Learning: ML: Geometric learning

Abstract

Node classification in heterophilous graphs, where connected nodes often have different characteristics, which presents a significant challenge. We introduce HAPPY, which combines heterophily-aware random walks with targeted subgraph extraction. Our approach enhances Personalized PageRank by incorporating both label and feature diversity into the random walk process. Through theoretical analysis, we demonstrate that HAPPY effectively captures both homophilous and heterophilous relationships. Comprehensive experiments validate our method’s state-of-the-art performance across challenging heterophilous benchmarks.

Giuseppe Pirrò. 2025. Heterophily-Aware Personalized PageRank for Node Classification. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 6075–6083. https://doi.org/10.24963/ijcai.2025/676
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards