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 89 篇，第 1 / 2 页

1. ICLR 2026A Near-Optimal Best-of-Both-Worlds Algorithm for Federated Bandits
2. ICLR 2026A Unified Federated Framework for Trajectory Data Preparation via LLMs
3. ICLR 2026Bayesian Evidence-Driven Prototype Evolution for Federated Domain Adaptation
4. ICLR 2026Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
5. ICLR 2026DeepAFL: Deep Analytic Federated Learning
6. ICLR 2026Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
7. ICLR 2026Enhancing Communication Compression via Discrepancy-aware Calibration for Federated Learning
8. ICLR 2026FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments
9. ICLR 2026Federated ADMM from Bayesian Duality
10. ICLR 2026FedMC: Federated Manifold Calibration
11. ICLR 2026Incentives in Federated Learning with Heterogeneous Agents
12. ICLR 2026Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus
13. ICLR 2026Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
14. ICLR 2026Near Optimal Robust Federated Learning Against Data Poisoning Attack
15. ICLR 2026Riemannian Federated Learning via Averaging Gradient Streams
16. ICLR 2026Robust Federated Inference
17. ICLR 2026Traceable Black-Box Watermarks For Federated Learning
18. ICLR 2026Unified Analyses for Hierarchical Federated Learning: Topology Selection under Data Heterogeneity
19. ICLR 2026Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression
20. ICLR 2025Adaptive Gradient Clipping for Robust Federated Learning
21. ICLR 2025Can Textual Gradient Work in Federated Learning?
22. ICLR 2025Connecting Federated ADMM to Bayes
23. ICLR 2025Debiasing Federated Learning with Correlated Client Participation
24. ICLR 2025Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees
25. ICLR 2025Decoupled Subgraph Federated Learning
26. ICLR 2025Event-Driven Online Vertical Federated Learning
27. ICLR 2025Federated Domain Generalization with Data-free On-server Matching Gradient
28. ICLR 2025Federated Few-Shot Class-Incremental Learning
29. ICLR 2025Federated Residual Low-Rank Adaptation of Large Language Models
30. ICLR 2025FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking
31. ICLR 2025FedTMOS: Efficient One-Shot Federated Learning with Tsetlin Machine
32. ICLR 2025On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
33. ICLR 2025Problem-Parameter-Free Federated Learning
34. ICLR 2025SparsyFed: Sparse Adaptive Federated Learning
35. ICLR 2025Subgraph Federated Learning for Local Generalization
36. ICLR 2025Towards Federated RLHF with Aggregated Client Preference for LLMs
37. ICLR 2025Unlocking the Potential of Model Calibration in Federated Learning
38. ICLR 2024A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging
39. ICLR 2024Accurate Forgetting for Heterogeneous Federated Continual Learning
40. ICLR 2024Adaptive Federated Learning with Auto-Tuned Clients
41. ICLR 2024Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
42. ICLR 2024Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
43. ICLR 2024FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation
44. ICLR 2024FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler
45. ICLR 2024Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
46. ICLR 2024Federated Recommendation with Additive Personalization
47. ICLR 2024Federated Wasserstein Distance
48. ICLR 2024FedInverse: Evaluating Privacy Leakage in Federated Learning
49. ICLR 2024FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning
50. ICLR 2024FedWon: Triumphing Multi-domain Federated Learning Without Normalization

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。