Research map / Graph learning / GNN architectures
Supervised Community Detection with Line Graph Neural Networks
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 oriented non-backtracking edge propagation instead of using a symmetric line graph (ablation) | LGNN · 5-class disassortative SBM | overlap: 0.18 -> 0.21 | Helped |
| add nonlinear activation functions (ablation) | LGNN · 5-class disassortative SBM | overlap: 0.18 -> 0.21 | Helped |
| add oriented non-backtracking edge propagation instead of using a symmetric line graph (ablation) | LGNN · Amazon | accuracy: 0.97 -> 0.96 | No clear effect |
| add oriented non-backtracking edge propagation instead of using a symmetric line graph (ablation) | LGNN · DBLP | accuracy: 0.89 -> 0.90 | Helped |
| add oriented non-backtracking edge propagation instead of using a symmetric line graph (ablation) | LGNN · Youtube | accuracy: 0.91 -> 0.92 | Helped |
Closest papers by meaning
- LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL (ICLR 2022 · similarity 0.92)
- Learning on Large Graphs using Intersecting Communities (NeurIPS 2024 · similarity 0.88)
- The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks (NeurIPS 2024 · similarity 0.88)
- Community Detection Guarantees using Embeddings Learned by Node2Vec (NeurIPS 2024 · similarity 0.88)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.88)
- Integrating Co-Training with Edge Discrimination to Enhance Graph Neural Networks Under Heterophily (AAAI 2025 · 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.