联邦学习论文趋势 2023–2026

主要结论

• 联邦学习论文从 2023 年的 137 篇降到 2026 年的 119 篇，热度在回落。
• NeurIPS 是发联邦学习论文最多的会议，2023–2026 年共 157 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是低秩适配：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 12 篇。
• 在「联邦与隐私」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的安全聚合是 1.8 倍，联邦学习是 0.9 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A typed tensor language for federated learning
• ICML 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
• ICLR 2026Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
• CVPR 2026FedRG Unleashing the Representation Geometry for Federated Learning with Noisy
• NeurIPS 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learning
• ICML 2025Causality Inspired Federated Learning for OOD Generalization
• ICLR 2025Adaptive Gradient Clipping for Robust Federated Learning
• CVPR 2025FedCS: Coreset Selection for Federated Learning
• NeurIPS 2024Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
• ICML 2024Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning
• ICLR 2024FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning
• CVPR 2024Decentralized Directed Collaboration for Personalized Federated Learning
• NeurIPS 2023DELTA: Diverse Client Sampling for Fasting Federated Learning
• ICML 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learning
• ICLR 2023Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
• CVPR 2023Federated Domain Generalization With Generalization Adjustment
• NeurIPS 2026Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift
• ICML 2026Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
• ICLR 2026DeepAFL: Deep Analytic Federated Learning
• CVPR 2026FedSST Rethinking Fair Federated Graph Learning under Structural Shift

全部联邦学习论文

共 42 篇，第 1 / 1 页

1. NeurIPS 2026A typed tensor language for federated learning
2. NeurIPS 2026Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks
3. NeurIPS 2026Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
4. NeurIPS 2026ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning
5. NeurIPS 2026Bayes-pFCL:Bayesian Personalized Federated Continual Learning
6. NeurIPS 2026Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification
7. NeurIPS 2026Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift
8. NeurIPS 2026Crossing the Validation crisis: Cross-validation reduces benchmarking variance surprisingly well
9. NeurIPS 2026Dynamic Spectral Federated Graph-Level Clustering
10. NeurIPS 2026Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
11. NeurIPS 2026Faster Rates For Federated Variational Inequalities
12. NeurIPS 2026FAUST: Federated Asynchronous Update with Staggered Timescales for Low-Communication Foundation Model Training
13. NeurIPS 2026Fed-AGA: An Anchor Graph Alignment Framework for Federated Unaligned Multi-view Clustering
14. NeurIPS 2026FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
15. NeurIPS 2026FedCF: Fair Federated Conformal Prediction
16. NeurIPS 2026Federated Graph Learning with Local Message Compensation
17. NeurIPS 2026Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
18. NeurIPS 2026Federated Logic Gate Networks via Boolean Feature Selection
19. NeurIPS 2026FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models
20. NeurIPS 2026FedPeel: Peeling Stabilized Layers for Robust Heterogeneous Federated Learning
21. NeurIPS 2026FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning
22. NeurIPS 2026FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning
23. NeurIPS 2026FedSOUL: Federated Continual Unlearning via Spectral Orthogonality
24. NeurIPS 2026FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning
25. NeurIPS 2026FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine
26. NeurIPS 2026FLoRA-Chef: Making A Good LoRA Recipe in Federated Generalization
27. NeurIPS 2026Focus on Where You Aggregate: Restricted SAM for Non-IID Federated Learning
28. NeurIPS 2026Geometry-Regularized Collapse Resistance via Consensus Enhancement for Federated Learning
29. NeurIPS 2026HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
30. NeurIPS 2026Heterogeneity-aware Distillation for Federated Continual Learning
31. NeurIPS 2026LEAN: Library-Based Adaptation for Asynchronous, Federated Fine-Tuning
32. NeurIPS 2026MainFL: Intertemporal Data Valuation for Robust Auction-based Federated Learning
33. NeurIPS 2026Principled Federated Random Forests for Heterogeneous Data
34. NeurIPS 2026Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning
35. NeurIPS 2026Reliable Federated Multi-View Learning via Conflict-Aware Evidence Calibration
36. NeurIPS 2026Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
37. NeurIPS 2026Semantic-Statistical Prior Banks for Federated Low-Shot Learning under Non-IID Clients
38. NeurIPS 2026ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
39. NeurIPS 2026Stability-Enhanced Federated Learning with Accelerated Gradient
40. NeurIPS 2026SynTeX-FL: Cross-Modal Text Transfer in Federated Learning for Medical Visual Question Answering
41. NeurIPS 2026Synthetic Anchor-Assisted Prototype Alignment for Heterogeneous Federated Learning
42. NeurIPS 2026Utility-Driven Clustered Federated Learning via Class-wise Interaction Attribution

常见问题

2023–2026 年四大会议一共有多少篇联邦学习论文？

共 460 篇，按年份分别是 2023 年 137 篇、2024 年 113 篇、2025 年 91 篇、2026 年 119 篇。

NeurIPS 2026 有多少篇联邦学习论文？

NeurIPS 2026 有 42 篇联邦学习论文，上一届是 31 篇。

ICLR 2026 有多少篇联邦学习论文？

ICLR 2026 有 19 篇联邦学习论文，上一届是 18 篇。

ICML 2026 有多少篇联邦学习论文？

ICML 2026 有 37 篇联邦学习论文，上一届是 23 篇。

CVPR 2026 有多少篇联邦学习论文？

CVPR 2026 有 21 篇联邦学习论文，上一届是 19 篇。

哪个会议的联邦学习论文最多？

NeurIPS，2023–2026 年共 157 篇。