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 137 篇，第 1 / 3 页

1. CVPR 2023Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity
2. CVPR 2023Bias-Eliminating Augmentation Learning for Debiased Federated Learning
3. CVPR 2023Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization
4. CVPR 2023DaFKD: Domain-Aware Federated Knowledge Distillation
5. CVPR 2023Efficient On-Device Training via Gradient Filtering
6. CVPR 2023FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
7. CVPR 2023Federated Domain Generalization With Generalization Adjustment
8. CVPR 2023Federated Incremental Semantic Segmentation
9. CVPR 2023Federated Learning With Data-Agnostic Distribution Fusion
10. CVPR 2023FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation
11. CVPR 2023GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting
12. CVPR 2023How To Prevent the Poor Performance Clients for Personalized Federated Learning?
13. CVPR 2023Learning Federated Visual Prompt in Null Space for MRI Reconstruction
14. CVPR 2023Make Landscape Flatter in Differentially Private Federated Learning
15. CVPR 2023On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data
16. CVPR 2023Re-Thinking Federated Active Learning Based on Inter-Class Diversity
17. CVPR 2023Rethinking Federated Learning With Domain Shift: A Prototype View
18. CVPR 2023ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients
19. CVPR 2023STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
20. CVPR 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
21. ICLR 2023Better Generative Replay for Continual Federated Learning
22. ICLR 2023Bias Propagation in Federated Learning
23. ICLR 2023Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
24. ICLR 2023Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity
25. ICLR 2023Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
26. ICLR 2023DepthFL : Depthwise Federated Learning for Heterogeneous Clients
27. ICLR 2023Effective passive membership inference attacks in federated learning against overparameterized models
28. ICLR 2023Efficient Federated Domain Translation
29. ICLR 2023EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data
30. ICLR 2023FedDAR: Federated Domain-Aware Representation Learning
31. ICLR 2023Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach
32. ICLR 2023Federated Learning from Small Datasets
33. ICLR 2023Federated Nearest Neighbor Machine Translation
34. ICLR 2023Federated Neural Bandits
35. ICLR 2023FedExP: Speeding Up Federated Averaging via Extrapolation
36. ICLR 2023FedFA: Federated Feature Augmentation
37. ICLR 2023FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
38. ICLR 2023Instance-wise Batch Label Restoration via Gradients in Federated Learning
39. ICLR 2023Learning to CROSS exchange to solve min-max vehicle routing problems
40. ICLR 2023Machine Unlearning of Federated Clusters
41. ICLR 2023Meta Knowledge Condensation for Federated Learning
42. ICLR 2023MocoSFL: enabling cross-client collaborative self-supervised learning
43. ICLR 2023Multimodal Federated Learning via Contrastive Representation Ensemble
44. ICLR 2023PerFedMask: Personalized Federated Learning with Optimized Masking Vectors
45. ICLR 2023Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
46. ICLR 2023SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
47. ICLR 2023Test-Time Robust Personalization for Federated Learning
48. ICLR 2023Towards Addressing Label Skews in One-Shot Federated Learning
49. ICLR 2023Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection
50. ICML 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learning

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。