Graph algorithms and clustering: research map
990 papers on Graph algorithms and clustering in Graph learning, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 3 clusters and 9 approaches. The busiest year so far is 2026.
What it is
Classic graph problems solved with learning: matching nodes between two graphs, clustering a graph into communities, and learned heuristics for hard combinatorial problems on graphs such as routing.
Terms you will see on this page:
- Graph matching
- finding the correspondence between the nodes of two graphs.
- Spectral clustering
- clustering using eigenvectors of the graph's Laplacian.
- Combinatorial optimization
- choosing the best of a huge discrete set of options, such as a tour.
Start reading with the most cited papers here:
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (NeurIPS 2016 · 1,699 citations)
- Learning Combinatorial Optimization Algorithms over Graphs (NeurIPS 2017 · 1,066 citations)
Within Graph learning, its share shrank from 15.4% in 2023–24 to 12.8% in 2025–26 (196 → 201 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).
Explore Graph algorithms and clustering in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
What changed recently
Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):
- Graph comparison and random features rising: 16% → 20% of the topic (31 → 41 papers)
- Anchor-based multi-view clustering rising: 4% → 7% of the topic (7 → 14 papers)
- Continuous DAG structure learning rising: 11% → 13% of the topic (21 → 27 papers)
- Graph distance and retrieval falling: 13% → 8% of the topic (25 → 17 papers)
- Deep learning for graph matching falling: 7% → 2% of the topic (13 → 5 papers)
Papers from 2025–2026 that are already cited most:
- Anchor Learning with Potential Cluster Constraints for Multi-view Clustering (AAAI 2025 · 25 citations)
- Dimension Reduction with Locally Adjusted Graphs (AAAI 2025 · 6 citations)
- Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching (CVPR 2025 · 2 citations)
- GeoMM: On Geodesic Perspective for Multi-modal Learning (CVPR 2025 · 2 citations)
Approaches and key papers
Graph combinatorics and structure · 726 papers
Keywords: search, directed, causal
Approaches in this cluster:
- Neural combinatorial optimization on graphs (167 papers)
Guide combinatorial and integer-programming solvers with graph neural networks. - Graph comparison and random features (183 papers)
Compare graphs with optimal transport and efficient graph random features. - Graph embedding and spectral sparsification (165 papers)
Scale graph embeddings via coarsening and spectral sparsification. - Continuous DAG structure learning (115 papers)
Learn DAG structure via continuous optimization and active experimental design. - Graph distance and retrieval (96 papers)
Learn graph edit distance and similarity for graph retrieval and coarsening.
Most cited and most cited since 2024:
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (NeurIPS 2016 · 1,699 citations)
- Learning Combinatorial Optimization Algorithms over Graphs (NeurIPS 2017 · 1,066 citations)
- Generating Diagnostic and Actionable Explanations for Fair Graph Neural Networks (AAAI 2024 · 21 citations)
- Large-Scale Multi-Robot Coverage Path Planning via Local Search (AAAI 2024 · 14 citations)
Graph clustering · 142 papers
Keywords: graph clustering, spectral clustering, clusters
Approaches in this cluster:
- Neural and local graph clustering (103 papers)
Cluster graphs with neural modularity, flow diffusion, and correlation clustering. - Anchor-based multi-view clustering (39 papers)
Scale multi-view clustering with anchor graphs and alignment.
Most cited and most cited since 2024:
- Efficient One-Pass Multi-View Subspace Clustering with Consensus Anchors (AAAI 2022 · 206 citations)
- Linkage Based Face Clustering via Graph Convolution Network (CVPR 2019 · 201 citations)
- Attribute-Missing Graph Clustering Network (AAAI 2024 · 58 citations)
- DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization (AAAI 2024 · 32 citations)
Graph matching · 122 papers
Keywords: graph matching, matching graph, correspondence
Approaches in this cluster:
- Deep learning for graph matching (55 papers)
Learn graph matching with neural networks and combinatorial solvers. - Optimization algorithms for graph matching (67 papers)
Solve graph matching with convex relaxations, dual decomposition, and update algorithms.
Most cited and most cited since 2024:
- Graph Matching Networks for Learning the Similarity of Graph Structured Objects (ICML 2019 · 298 citations)
- Deep Learning of Graph Matching (CVPR 2018 · 237 citations)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · 3 citations)
- Discrete Cycle-Consistency Based Unsupervised Deep Graph Matching (AAAI 2024 · 2 citations)
Related topics in Graph learning
- Knowledge and temporal graphs (1,162)
- GNN architectures (1,634)
- Graph self-supervised learning (1,399)
