AI Paper Atlas

Research map / Graph learning / GNN architectures

Heterophily-Aware Representation Learning on Heterogeneous Graphs

Jintang Li, Zheng Wei, Yuchang Zhu, Ruofan Wu, Huizhe Zhang, Liang Chen, Zibin Zheng

TPAMI 2025 · Graph learning › GNN architectures · approach: Graph structure learning · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add correlation loss (disentanglement) (ablation)Ours · MAGMicro-F1: 53.10 -> 55.13Improved
add correlation loss (disentanglement) (ablation)Ours · DBLPMicro-F1: 93.94 -> 94.46Improved
add masked metapath reconstruction loss (ablation)Ours · DBLPMicro-F1: 93.09 -> 94.46Improved
add masked metapath reconstruction loss (ablation)Ours · MAGMacro-F1: 31.32 -> 33.28Improved
add both correlation and reconstruction losses (ablation)Ours · MAGMicro-F1: 51.97 -> 55.13Improved
add both correlation and reconstruction losses (ablation)Ours · IMDBMicro-F1: 67.80 -> 69.61Improved
add masked label prediction (ablation)Ours · MAGMicro-F1: 49.04 -> 55.13Improved
add masked label prediction (ablation)Ours · MAGMacro-F1: 28.23 -> 33.28Improved
add masked label prediction (ablation)Ours · IMDBMicro-F1: 68.41 -> 69.61Improved
add masked label prediction (ablation)Ours · ACMMicro-F1: 93.44 -> 93.91Improved
add correlation loss (disentanglement) (ablation)Ours · ACMMicro-F1: 93.38 -> 93.91Improved
add masked metapath reconstruction loss (ablation)Ours · ACMMicro-F1: 93.62 -> 93.91Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy