Research map / Graph learning / Graph algorithms and clustering
Neural Graph Matching Network: Learning Lawler’s Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching
Runzhong Wang, Junchi Yan, Xiaokang Yang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| sample 5000 Gumbel-Sinkhorn solutions instead of deterministic Hungarian (ablation) | NGM · QAPLIB | instances with best solution: 12 -> 72 | Improved |
| reduce Gumbel samples from 5000 to 500 (ablation) | NGM-G5k · QAPLIB | instances with best solution: 72 -> 12 | Hurt |
| reduce Gumbel samples from 500 to 50 (ablation) | NGM-G500 · QAPLIB | instances with best solution: 12 -> 2 | Hurt |
| add Gumbel sampling with only 5 samples (ablation) | NGM · QAPLIB | instances with best solution: 12 -> 1 | Hurt |
| learned NGM-G5k instead of learning-free Sinkhorn-JA | Sinkhorn-JA · QAPLIB | instances with best solution: 46 -> 72 | Improved |
| use NGM-G5k instead of RRWM | RRWM · QAPLIB | instances with best solution: 9 -> 72 | Improved |
| add matching-aware Sinkhorn embedding (ablation) | NGM-V · synthetic point matching | accuracy | Improved |
| add multi-head Sinkhorn embedding (8 channels) (ablation) | NGM · synthetic point matching with random scaling | accuracy | Improved |
| learn joint multi-graph matching instead of spectral fusion on NGM (ablation) | NGM-SF · synthetic multi-graph matching | accuracy | Improved |
| use more graphs in multi-graph matching (ablation) | NMGM · synthetic multi-graph matching | accuracy | Improved |
Closest papers by meaning
- Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach (TPAMI 2020 · similarity 0.92)
- Learning Combinatorial Embedding Networks for Deep Graph Matching (ICCV 2019 · similarity 0.91)
- Deep Learning of Graph Matching (CVPR 2018 · similarity 0.90)
- Learning Combinatorial Solver for Graph Matching (CVPR 2020 · similarity 0.90)
- Ensemble Quadratic Assignment Network for Graph Matching (IJCV 2024 · similarity 0.90)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 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.
