Label-aware aggregation on heterophilous graphs for node representation learning

Linruo Liu, Yangtao Wang, Yanzhao Xie, Xin Tan, Lizhuang Ma, Maobin Tang, Meie Fang

Abstract: Highlights•Both similar/dissimilar neighborhoods make a positive impact on feature aggregation.•We propose a label-aware strategy for each similar/dissimilar neighborhood.•We carry out contribution balance between each center node and all its neighborhoods.•Extensive experiments verify our method can achieve the SOTA performance.