Label-aware aggregation on heterophilous graphs for node representation learning

• Published in: Displays 2024-09, Vol.84, p.102817, Article 102817
• Main Authors: Liu, Linruo, Wang, Yangtao, Xie, Yanzhao, Tan, Xin, Ma, Lizhuang, Tang, Maobin, Fang, Meie
• Format: Article
• Language: English
• Subjects: Heterophilous graphs; Label-aware aggregation; Node representation learning
• ISSN: 0141-9382
• DOI: 10.1016/j.displa.2024.102817

Learning node representation on heterophilous graphs has been challenging due to nodes with diverse labels/attributes being connected. The main idea is to balance contributions between the center node and neighborhoods. However, existing methods failed to make full use of personalized contributions of different neighborhoods based on whether they own the same label as the center node, making it necessary to explore the distinctive contributions of similar/dissimilar neighborhoods. We reveal that both similar/dissimilar neighborhoods have positive impacts on feature aggregation under different homophily ratios. Especially, dissimilar neighborhoods play a significant role under low homophily ratios. Based on this, we propose LAAH, a label-aware aggregation approach for node representation learning on heterophilous graphs. LAAH separates each center node from its neighborhoods and generates their own node representations. Additionally, for each neighborhood, LAAH records its label information based on whether it belongs to the same class as the center node and then aggregates its effective feature in a weighted manner. Finally, a learnable parameter is used to balance the contributions of each center node and all its neighborhoods, leading to updated representations. Extensive experiments on 8 real-world heterophilous datasets and a synthetic dataset verify that LAAH can achieve competitive or superior accuracy in node classification with lower parameter scale and computational complexity compared with the SOTA methods. The code is released at GitHub: https://github.com/laah123graph/LAAH. •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.