Research map / Graph learning / GNN architectures
A Collective Learning Framework to Boost GNN Expressiveness for Node Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| add collective learning (CL) to GNNs (GCN, GS, TK, GRAND) | GCN, GraphSAGE, TK, GRAND · Cora, Pubmed, Friendster, Facebook, Protein (connected split) | accuracy: up to +12.41 points | Helped |
| add collective learning to GCN with 50% test labels available | GCN · Cora connect | accuracy: +12.41 (1.96) | Helped |
| add collective learning to GCN in unlabeled test setting | GCN · Cora connect, 0% test labels | accuracy: +3.72 (0.40) | Helped |
| add collective learning to GRAND in unlabeled test setting | GRAND · Friendster, 0% test labels | balanced accuracy: +6.38 (2.29) | Helped |
| add collective learning to GNN on Friendster (sparse graph) with no test labels | GCN · Friendster, 0% test labels | balanced accuracy: +0.75 (0.33) | Helped |
| add collective learning to GCN vs TK: simpler GNNs gain more | GCN vs TK · Cora connect, 50% test labels | accuracy: GCN +12.41 vs TK +7.92 | Mixed |
Closest papers by meaning
- Deep Collective Inference (AAAI 2017 · similarity 0.91)
- Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning (ICLR 2025 · similarity 0.88)
- Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification (NeurIPS 2024 · similarity 0.88)
- Integrating Co-Training with Edge Discrimination to Enhance Graph Neural Networks Under Heterophily (AAAI 2025 · similarity 0.87)
- TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation (ICML 2025 · similarity 0.87)
- Label-free Node Classification on Graphs with Large Language Models (LLMs) (ICLR 2024 · similarity 0.87)
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.