AI Paper Atlas

Research map / Graph learning / GNN architectures

HL-HGAT: Heterogeneous Graph Attention Network via Hodge-Laplacian Operator

Jinghan Huang, Qiufeng Chen, Pengli Zhu, Yijun Bian, Nanguang Chen, Moo Kwon Chung, Anqi Qiu

TPAMI 2025 · Graph learning › GNN architectures · approach: Graph structure learning · 10 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 multi-simplicial interaction (MSI) on top of HL-filters for node and edge signals (M2 to M3) (ablation)HL-HGAT · CIFAR10, Peptide-func, OASIS-3, ABCDaccuracy / prediction errorImproved
apply HL-filters to edge signals as well as node signals (M1 to M2) (ablation)HL-HGAT · CIFAR10, Peptide-func, OASIS-3, ABCDaccuracy / prediction errorImproved
add simplicial attention pooling (SAP) to the model (M3 to M4) (ablation)HL-HGAT · TSP, ZINCaccuracy / prediction errorNo clear effect
add simplicial attention pooling (SAP) to the model (M3 to M4) (ablation)HL-HGAT · CIFAR10, Peptide-func, OASIS-3, ABCDaccuracy / prediction errorImproved
add SAP pooling to reduce memory and compute on large graphs (ablation)HL-HGAT · ZINC, Peptide-func, CIFAR10, ABCD/OASIS-3memory and computational timeImproved

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