Research map / Label-efficient and robust learning / Recognition and long-tail
Incomplete multi-view multi-label learning
Imputes embeddings and shares label-guided representations for incomplete multi-view multi-label data.
35 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Recognition and long-tail, keyword cluster “multi view · views · view clustering”
State History Benchmarks Tried Checklist Preprints Who Export
Where it stands
Few recent reports The tracked benchmarks have at most one report from 2025–26 that could beat the old record, too few to say whether they are still moving.
10 papers in 2023–24 and 19 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 0.8% to 1.4%.
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
- 2018 · Latent Semantic Aware Multi-View Multi-Label Classification (AAAI 2018 · 103 citations)
- 2019 · Multi-View Multi-Instance Multi-Label Learning Based on Collaborative Matrix Factorization (AAAI 2019 · 28 citations)
- 2020 · Multi-View Partial Multi-Label Learning with Graph-Based Disambiguation (AAAI 2020 · 50 citations)
- 2022 · Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning (AAAI 2022 · 35 citations)
- 2023 · DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification (AAAI 2023 · 75 citations)
- 2024 · Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · 38 citations)
- 2025 · Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection (AAAI 2025 · 11 citations)
- 2026 · Hypergraph-Based Multi-View Multi-Label Classification via Adaptive High-Order Semantic Fusion (AAAI 2026 · 2 citations)
Earliest papers here
- Latent Semantic Aware Multi-View Multi-Label Classification (AAAI 2018 · 103 citations)
- Learning With Incomplete Labels (AAAI 2018 · 3 citations)
- Multi-View Multi-Instance Multi-Label Learning Based on Collaborative Matrix Factorization (AAAI 2019 · 28 citations)
Benchmark records
The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.
Corel5k · Average Precision (higher is better)
4 papers, 2018–2025 · one report since 2024, not better
| Year | Best so far | Set by |
|---|---|---|
| 2018 | 0.462 | Latent Semantic Aware Multi-View Multi-Label Classification (AAAI 2018 · 103 citations) |
| 2022 | 0.475 | Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning (AAAI 2022 · 35 citations) |
What has been tried
24 papers here report 235 measured changes (a component added, removed or swapped, compared with a baseline): helped 83%, no clear effect 5%, hurt 9%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add label-missing mask | Corel5k · AP | 0.380 -> 0.400 | Helped | Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · 38 citations) |
| add GNN-based completion | ALOI (PER=60%, LER=10%) · ACC | 55.44 -> 83.74 | Helped | Deep Incomplete Multi-View Learning Network with Insufficient Label Information (AAAI 2024 · 21 citations) |
| add L(k)IB to the LCE backbone | Corel5k · AP | 0.375 -> 0.383 | Helped | A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification (AAAI 2024 · 19 citations) |
| Replace four vanilla transformer encoders with the view-category interactive sharing transformer | Corel5k · AP | 34.9 -> 39.5 | Helped | View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning (CVPR 2024 · 17 citations) |
| add the common-label majority regularization (alpha component) | SCENE, Corel5K, and IAPRTC12 · Average Precision | 0.7852 -> 0.7951; 0.2366 -> 0.2370; 0.1403 -> 0.1421 | Helped | Double-Layer Hybrid-Label Identification Feature Selection for Multi-View Multi-Label Learning (AAAI 2024 · 16 citations) |
| add sample confidence | yeast · AP | 0.6616 -> 0.6725 | Helped | Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection (AAAI 2025 · 11 citations) |
| Add nonlinear RBF kernel preprocessing | Multi-view datasets · clustering ACC and NMI | Helped | Unsupervised Kernel-based Multi-view Feature Selection with Robust Self-representation and Binary Hashing (AAAI 2025 · 7 citations) | |
| Add inter-class association calibration to distribution-sampling imputation | Five multi-view datasets, η = 0.3 · accuracy | Helped | Biased Incomplete Multi-View Learning (AAAI 2025 · 5 citations) | |
| Add reconstruction loss Lrec | Caltech101-all (r=1, p=0.3) · accuracy | 0.656±0.021 -> 0.668±0.011 | Helped | CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · 5 citations) |
| add disentangled specific feature extraction to consistent feature extraction | Corel5k · AP | 0.416 -> 0.431 | Helped | Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · 5 citations) |
| Replace statistical-regularity redundancy identification with DiffSumm identification | Corel5k · AP | 40.7 -> 45.7 | Helped | Incomplete Multi-View Multi-Label Classification via Diffusion-Guided Redundancy Removal (AAAI 2025 · 4 citations) |
| add LRE1, LRE2, and LCE | Corel5k · AP | 0.390 -> 0.432 | Helped | Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025) |
What reviewers will expect
Datasets and baselines named in the 10 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- Corel5k · 4 of 10 papers
- Espgame · 4 of 10 papers
- IAPRTC12 · 4 of 10 papers
- Mirflickr · 4 of 10 papers
- Pascal07 · 3 of 10 papers
- Scene15 · 2 of 10 papers
- MSRCv1 · 2 of 10 papers
- yeast · 2 of 10 papers
Baselines
- iMvWL · 3 of 10 papers
- DICNet · 3 of 10 papers
- ML-BVAE · 2 of 10 papers
- LMVCAT · 2 of 10 papers
- lrMMC · 2 of 10 papers
- NAIML · 2 of 10 papers
- DDINet · 2 of 10 papers
- DM2L · 2 of 10 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 29 papers; from OpenAlex and the papers' affiliations).
- Harbin Institute of Technology · 8 papers
- National University of Defense Technology · 3 papers
- Shenzhen Campus of Sun Yat-sen University · 2 papers
- Peng Cheng Laboratory · 2 papers
- Jilin University · 2 papers
- Portland State University · 2 papers
- Beijing University of Technology · 2 papers
- Beijing University of Posts and Telecommunications · 2 papers
Use it
Download BibTeX of 29 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
- Uncertainty-aware multi-view learning (95 papers)
Elsewhere in the topic
- Multilingual language representation pretraining (507 papers)
- Contrastive representation theory (495 papers)
- Dense features and foundation priors (482 papers)
- Correspondence and causal representation learning (447 papers)
- Data augmentation and generalization bias (409 papers)
- Partial and multi-label learning (345 papers)
- Loss design and classifier theory (273 papers)
- Group-robust classification (251 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).