Research map / Graph learning / Graph self-supervised learning
Multi-view graph clustering
Cluster using multi-view graphs with anchor and contrastive representations.
70 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Graph self-supervised learning, keyword cluster “classification · semi supervised · representation”
State History Tried Checklist 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.
17 papers in 2023–24 and 36 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 4.9% to 6.2%.
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 · GraB: Visual Saliency via Novel Graph Model and Background Priors (CVPR 2016 · 109 citations)
- 2017 · Zero Shot Learning via Multi-Scale Manifold Regularization (CVPR 2017 · 44 citations)
- 2018 · Constructing Deep Neural Networks by Bayesian Network Structure Learning (NeurIPS 2018 · 14 citations)
- 2019 · Lorentzian Distance Learning for Hyperbolic Representations (ICML 2019 · 43 citations)
- 2020 · Space-Time Correspondence as a Contrastive Random Walk (NeurIPS 2020 · 112 citations)
- 2021 · Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus (AAAI 2021 · 6 citations)
- 2022 · JoinABLe: Learning Bottom-Up Assembly of Parametric CAD Joints (CVPR 2022 · 68 citations)
- 2023 · Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering (AAAI 2023 · 42 citations)
- 2024 · Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering (AAAI 2024 · 36 citations)
- 2025 · Structure-Adaptive Multi-View Graph Clustering for Remote Sensing Data (AAAI 2025 · 24 citations)
- 2026 · Scale-Net: A Hierarchical U-Net Framework for Cross-Scale Generalization in Multi-Task Vehicle Routing (AAAI 2026 · 3 citations)
Earliest papers here
- GraB: Visual Saliency via Novel Graph Model and Background Priors (CVPR 2016 · 109 citations)
- Zero Shot Learning via Multi-Scale Manifold Regularization (CVPR 2017 · 44 citations)
- Graph-based Isometry Invariant Representation Learning (ICML 2017 · 32 citations)
What has been tried
47 papers here report 439 measured changes (a component added, removed or swapped, compared with a baseline): helped 81%, no clear effect 7%, hurt 11%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add local graph convolution and global graph fusion | BDGP · ACC | 0.932 -> 0.979 | Helped | Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering (AAAI 2024 · 36 citations) |
| Add the graph structure learning module | Mfeat · clustering performance | Helped | SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · 28 citations) | |
| add graph spatial correlation adaptive refinement | Trento; MUUFL; Augsburg; MDSA · ACC | 92.89 -> 95.04; 46.58 -> 50.50; 65.11 -> 67.80; 45.58 -> 47.59 | Helped | Structure-Adaptive Multi-View Graph Clustering for Remote Sensing Data (AAAI 2025 · 24 citations) |
| add reconstruction loss | Chameleon · ACC | 41.5 -> 43.2 | Helped | Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering (AAAI 2024 · 21 citations) |
| Add global graph propagation loss | MSRC-V1, missing rate 0.5 · ACC | 87.81 -> 91.14 | Helped | Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (AAAI 2025 · 13 citations) |
| Add GCET to IPS | YFCC100M known, SIFT · mAP5° | +13.97% | Helped | Graph Context Transformation Learning for Progressive Correspondence Pruning (AAAI 2024 · 12 citations) |
| Use mask labels rather than unsorted vector labels for line-segment supervision | SpaceNet · APLS | 57.34 -> 69.68 | Helped | Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · 10 citations) |
| Add Lgl and Lgc to Lpl | Caltech101-20, 50% complete, 50% paired · NMI | 28.76 -> 30.33 | Helped | Incomplete and Unpaired Multi-View Graph Clustering with Cross-View Feature Fusion (AAAI 2025 · 7 citations) |
| Add contrastive learning loss to reconstruction-only training | ALOI-100 · ACC | 70.59 -> 75.79 | Helped | EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering (CVPR 2025 · 7 citations) |
| add hub-aware representation embedding and cross-view pairing losses rather than using conventional autoencoders | 3Sources · ACC | 0.7065 -> 0.9290 | Helped | A Hubness Perspective on Representation Learning for Graph-Based Multi-View Clustering (CVPR 2025 · 4 citations) |
| use dual graph diffusion convolution instead of concatenation for consensus-graph information | Citeseer · ACC (%) | 59.74 ± 1.01 -> 65.34 ± 1.24 | Helped | Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering (CVPR 2025 · 2 citations) |
| add intra-view K-nearest neighbors | Emotions · Micro-F1 | 0.689±0.019 -> 0.692±0.015 | Helped | Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 2025 · 1 citation) |
What reviewers will expect
Datasets and baselines named in the 18 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- HandWritten · 3 of 18 papers
- Caltech101-20 · 3 of 18 papers
- BBCSport · 3 of 18 papers
- MSRC-V1 · 2 of 18 papers
- BDGP · 2 of 18 papers
- Yale · 2 of 18 papers
- MNIST-USPS · 2 of 18 papers
- CORA · 2 of 18 papers
Baselines
- MFLVC · 3 of 18 papers
- GCFAgg · 3 of 18 papers
- SDMVC · 2 of 18 papers
- MCGC · 2 of 18 papers
- DFP-GNN · 2 of 18 papers
- DSMVC · 2 of 18 papers
- SCMVC · 2 of 18 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 53 papers; from OpenAlex and the papers' affiliations).
- University of Electronic Science and Technology of China · 5 papers
- Lehigh University · 4 papers
- Sichuan University · 3 papers
- Harbin Institute of Technology · 2 papers
- Shantou University · 2 papers
- Beijing University of Technology · 2 papers
- Beijing Jiaotong University · 2 papers
- Dalian University of Technology · 2 papers
- National University of Defense Technology · 2 papers
Use it
Download BibTeX of 37 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
- Semi-supervised node representation learning (214 papers)
- Heterophily and imbalance on graphs (178 papers)
- LLMs and graph foundation models (117 papers)
- Brain and biological graph learning (78 papers)
Elsewhere in the topic
- Diffusion-based graph generation (138 papers)
- Graph anomaly detection (101 papers)
- Molecular graph pretraining (101 papers)
- Graph domain adaptation (82 papers)
- Graph contrastive learning analysis (61 papers)
- Graph out-of-distribution generalization (58 papers)
- Contrastive learning with negatives and views (51 papers)
- Augmentation-free graph learning (25 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).