Research map / Graph learning / Graph algorithms and clustering
Optimization algorithms for graph matching
Solve graph matching with convex relaxations, dual decomposition, and update algorithms.
42 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Graph algorithms and clustering, keyword cluster “graph matching · matching graph · correspondence”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
10 papers in 2023–24 and 7 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 5.1% to 3.5%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Tensor Power Iteration for Multi-Graph Matching (CVPR 2016 · 30 citations)
- 2017 · Alternating Direction Graph Matching (CVPR 2017 · 57 citations)
- 2018 · Generalizing Graph Matching beyond Quadratic Assignment Model (NeurIPS 2018 · 28 citations)
- 2019 · (Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs (NeurIPS 2019 · 40 citations)
- 2020 · Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory (ICML 2020 · 22 citations)
- 2021 · Efficient Initial Pose-Graph Generation for Global SfM (CVPR 2021 · 29 citations)
- 2022 · Generalized Stochastic Matching (AAAI 2022 · 2 citations)
- 2023 · Progressive Neighbor Consistency Mining for Correspondence Pruning (CVPR 2023 · 35 citations)
- 2024 · Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · 3 citations)
- 2025 · Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching (CVPR 2025 · 2 citations)
- 2026 · Neural Minimum Weight Perfect Matching for Quantum Error Codes (ICML 2026 · 0 citations)
Earliest papers here
- Tensor Power Iteration for Multi-Graph Matching (CVPR 2016 · 30 citations)
- Kinematic Structure Correspondences via Hypergraph Matching (CVPR 2016 · 11 citations)
- Path Following with Adaptive Path Estimation for Graph Matching (AAAI 2016 · 8 citations)
What has been tried
33 papers here report 275 measured changes (a component added, removed or swapped, compared with a baseline): helped 71%, no clear effect 6%, hurt 19%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| use parallel GM local search instead of sequential GM local search | worms-10 · convergence speed | Helped | Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging (CVPR 2025 · 1 citation) | |
| add IMG correspondence supervision rather than fine-tuning alone | ICE benchmark · FVD | 358.31 -> 225.06 | Helped | EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation (NeurIPS 2025 · 1 citation) |
| add node merging preprocessing | CodeSearchNet graphs and evaluated ReGaPs · number of SAT clauses | 25.7% less clauses | Helped | SAT-Based Algorithms for Regular Graph Pattern Matching (AAAI 2024 · 1 citation) |
| Set β=6 and β⁻=5 rather than β=6 and β⁻=4 | Bipartite maximum matching · approximation ratio | 0.5 -> 0.6774 | Helped | Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS (ICML 2024 · 0 citations) |
| increase trust-region radius; moderate increases initially improve Hits@1, while too-large radii reduce it | SNS, PPI, DBLP · Hits@1 | Mixed | Effective Federated Graph Matching (ICML 2024) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 17 papers; from OpenAlex and the papers' affiliations).
- Shanghai Jiao Tong University · 2 papers
Use it
Download BibTeX of 34 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Deep learning for graph matching (42 papers)
Elsewhere in the topic
- Neural combinatorial optimization on graphs (159 papers)
- Graph comparison and random features (155 papers)
- Graph embedding and spectral sparsification (126 papers)
- Continuous DAG structure learning (102 papers)
- Neural and local graph clustering (81 papers)
- Graph distance and retrieval (79 papers)
- Anchor-based multi-view clustering (31 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).