Divergent Paths: Separating Homophilic and Heterophilic Learning for Enhanced Graph-level Representations
Open Access
- 3 August 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1286-1295
Abstract
No abstract availableAll Related Versions
Funding Information
- MOE Academic Research Fund (Tier 1 (RG16/24))
This publication has 13 references indexed in Scilit:
- Rethinking the message passing for graph-level classification tasks in a category-based viewEngineering Applications of Artificial Intelligence, 2025
- Beyond low-pass filtering on large-scale graphs via Adaptive Filtering Graph Neural NetworksNeural Networks, 2023
- Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks2022
- Universal Graph Transformer Self-Attention Networks2022
- GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily2022
- Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs2021
- Graph representation learning: a surveyAPSIPA Transactions on Signal and Information Processing, 2020
- Object categorization by learned universal visual dictionary2005
- The Predictive Toxicology Challenge 2000–2001Bioinformatics, 2001
- Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicityJournal of Medicinal Chemistry, 1991