Research map / Federated learning and privacy / Personalized and heterogeneous FL
Vertical federated learning
Train across parties holding different features with privacy and communication efficiency.
38 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2020–2026) · an approach in Personalized and heterogeneous FL, keyword cluster “domain · label · multi”
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.
18 papers in 2023–24 and 10 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 7.2% to 2.6%.
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
- 2020 · Practical Federated Gradient Boosting Decision Trees (AAAI 2020 · 197 citations)
- 2021 · Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating (AAAI 2021 · 58 citations)
- 2022 · Seizing Critical Learning Periods in Federated Learning (AAAI 2022 · 45 citations)
- 2023 · FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models (ICML 2023 · 5 citations)
- 2024 · Fair and Efficient Contribution Valuation for Vertical Federated Learning (ICLR 2024 · 14 citations)
- 2025 · HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning (AAAI 2025 · 1 citation)
- 2026 · Equilibrium-Driven Vertical Federated Learning with Selective Privacy Protection (AAAI 2026 · 0 citations)
Earliest papers here
- Practical Federated Gradient Boosting Decision Trees (AAAI 2020 · 197 citations)
- Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating (AAAI 2021 · 58 citations)
- Federated Learning of User Verification Models Without Sharing Embeddings (ICML 2021 · 2 citations)
What has been tried
31 papers here report 305 measured changes (a component added, removed or swapped, compared with a baseline): helped 64%, no clear effect 13%, 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 |
|---|---|---|---|---|
| Add p2a distillation loss | Criteo · AUC (L-Util, %) | 72.1 -> 72.5 | Helped | Complementary Knowledge Distillation for Robust and Privacy-Preserving Model Serving in Vertical Federated Learning (AAAI 2024 · 7 citations) |
| replace direct FedAvg aggregation with server-level CMA-ES aggregation | language understanding datasets · accuracy | Helped | FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models (ICML 2024 · 7 citations) | |
| add dynamic masking | MNIST (50 parties) · accuracy | 72.89% ± 1.43% -> 85.47% ± 0.13% | Helped | Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data (NeurIPS 2024 · 3 citations) |
| increase the number of hash functions | SU · test accuracy | Helped | HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning (AAAI 2025 · 1 citation) | |
| Add GCE to FedGVI with α-Rényi divergence | MNIST, 10% contamination, 10 clients · accuracy | 96.36± 0.09 -> 97.50± 0.07 | Helped | Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework (ICML 2025 · 0 citations) |
| Use Gumbel-Softmax BDPL instead of BDPL | GLUE Avg. (GPT-3.5 Turbo) · score | 61.67 -> 64.28 | Helped | FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning (ICML 2025) |
| Add the waiting deadline mechanism | Synthetic · AUC | 92.86 -> 94.17 | Helped | PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture (NeurIPS 2025) |
What reviewers will expect
Datasets and baselines named in the 8 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- Covertype · 2 of 8 papers
- YearPredictionMSD · 2 of 8 papers
- MNIST · 2 of 8 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 28 papers; from OpenAlex and the papers' affiliations).
- National University of Singapore · 3 papers
- Western University · 3 papers
- Mohamed bin Zayed University of Artificial Intelligence · 3 papers
- Hong Kong University of Science and Technology · 2 papers
- Ant Group · 2 papers
- Wuhan University · 2 papers
- Baidu · 2 papers
- Tsinghua University · 2 papers
- University of Western Ontario · 2 papers
- Jilin University · 2 papers
Use it
Download BibTeX of 33 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
- Non-IID federated learning (198 papers)
- Federated learning with pretrained models (164 papers)
- Federated semi-supervised and graph learning (84 papers)
- Federated prompt and LoRA tuning (91 papers)
- Federated medical and multimodal learning (44 papers)
Elsewhere in the topic
- Personalization with global-local trade-off (48 papers)
- Sparse and collaboration-graph personalization (36 papers)
- Bayesian personalized FL (35 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).