Heterophily-Aware Personalized PageRank for Node Classification

Node classification in heterophilous graphs, where connected nodes often have different characteristics, 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 HAPPYeffectively captures both homophilous and heterophilous relationships. Comprehensive experiments validate our method's state-of-the-art performance across challenging heterophilous benchmarks.