AI Paper Atlas

Research map / Graph learning / GNN architectures

HC2-GNN: Hierarchical Graph Representation Learning for Efficient Text Classification

jiejie fan, Xiaojuan Ban, Zhiyan Zhang, Xi Sun

AAAI 2026 · Graph learning › GNN architectures · approach: Graph structure learning

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 C2GC clustering and coarsening (ablation)HC2-GNN · 20NGaccuracy (%): 86.5 -> 89.6Improved
add text-order-aware clustering instead of topology-only conductance (ablation)HC2-GNN · 20NG-Laccuracy (%): 90.7 -> 94.3Improved
add text-order-aware clustering instead of topology-only conductance (ablation)HC2-GNN · 20NGaccuracy (%): 87.9 -> 89.6Improved
add virtue cluster extension (ablation)HC2-GNN · 20NGaccuracy (%): 88.4 -> 89.6Improved
add virtue cluster extension (ablation)HC2-GNN · 20NG-Laccuracy (%): 92.6 -> 94.3Improved
add global graph branch (GCN) to local subgraph model (ablation)HC2-GNN · 20NG-Laccuracy (%): 90.7 -> 94.3Improved
use GRU-GGNN instead of GCN in subgraphs (ablation)HC2-local · 20NGaccuracy (%): 85.7 -> 86.8Improved
use C2GC instead of rigid conductance partitioning (ablation)HC2-GNN · 20NGaccuracy (%): 86.2 -> 89.6Improved
rigid conductance partitioning instead of GCN-only partitioning (ablation)HC2-Simp · 20NGaccuracy (%): 85.7 -> 86.2No clear effect
apply HC2-GNN on short-text datasetHC2-GNN vs TextING · MRaccuracy (%): 79.82 -> 80.22No clear effect
HC2-GNN vs TextING on long textsHC2-GNN · 20NGaccuracy (%): 85.47 -> 89.66Improved
HC2-GNN-GT vs MSABertGCNHC2-GNN-GT · R52 (transformer-enhanced)accuracy (%): 96.68 -> 96.40No clear effect

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