---
title: "Heterophily-Aware Personalized PageRank for Node Classification"
authors:
  - "Giuseppe Pirrò"
doi: "10.24963/ijcai.2025/676"
url: "https://ijcai.org/proceedings/2025/676"
pdf: "https://ijcai.org/proceedings/2025/0676.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "6075-6083"
track: "Main Track"
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"
---

# Heterophily-Aware Personalized PageRank for Node Classification

Giuseppe Pirrò

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 6075-6083. DOI: [10.24963/ijcai.2025/676](https://doi.org/10.24963/ijcai.2025/676)

## 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.