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 460 篇，第 1 / 10 页

1. CVPR 2026Batman Benign Knowledge Alignment Through Malicious Null Space in Federated
2. CVPR 2026Controllable Federated Prompt Learning at Test Time
3. CVPR 2026Domain Sensitive Federated Learning with Fisher-Informed Pruning
4. CVPR 2026DP-FedAdamW An Efficient Optimizer for Differentially Private Federated Large Models
5. CVPR 2026FedAlign Differentially Private Distribution Alignment for Non-IID Federated Learning
6. CVPR 2026FedBPrompt Federated Domain Generalization Person Re-Identification via Body Distribution Aware
7. CVPR 2026FedCART Tackling Long-Tailed Distributions in Federated Adversarial Training via Classifier
8. CVPR 2026FedDAP Domain-Aware Prototype Learning for Federated Learning under Domain Shift
9. CVPR 2026FedHarmony Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
10. CVPR 2026FedRAC Rolling Submodel Allocation for Collaborative Fairness in Federated Learning
11. CVPR 2026FedRE A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
12. CVPR 2026FedRG Unleashing the Representation Geometry for Federated Learning with Noisy
13. CVPR 2026FedSST Rethinking Fair Federated Graph Learning under Structural Shift
14. CVPR 2026Few-for-Many Personalized Federated Learning
15. CVPR 2026From Selection to Scheduling Federated Geometry-Aware Correction Makes Exemplar Replay
16. CVPR 2026GDFA Geometry-Driven Federated Unlearning with Directional Task Vector Alignment
17. CVPR 2026HiLoRA Hierarchical Low-Rank Adaptation for Personalized Federated Learning
18. CVPR 2026Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification
19. CVPR 2026ProxyFL A Proxy-Guided Framework for Federated Semi-Supervised Learning
20. CVPR 2026RHO Robust Holistic OSM-Based Metric Cross-View Geo-Localization
21. CVPR 2026Single-Round Scalable Analytic Federated Learning
22. ICLR 2026A Near-Optimal Best-of-Both-Worlds Algorithm for Federated Bandits
23. ICLR 2026A Unified Federated Framework for Trajectory Data Preparation via LLMs
24. ICLR 2026Bayesian Evidence-Driven Prototype Evolution for Federated Domain Adaptation
25. ICLR 2026Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
26. ICLR 2026DeepAFL: Deep Analytic Federated Learning
27. ICLR 2026Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
28. ICLR 2026Enhancing Communication Compression via Discrepancy-aware Calibration for Federated Learning
29. ICLR 2026FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments
30. ICLR 2026Federated ADMM from Bayesian Duality
31. ICLR 2026FedMC: Federated Manifold Calibration
32. ICLR 2026Incentives in Federated Learning with Heterogeneous Agents
33. ICLR 2026Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus
34. ICLR 2026Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
35. ICLR 2026Near Optimal Robust Federated Learning Against Data Poisoning Attack
36. ICLR 2026Riemannian Federated Learning via Averaging Gradient Streams
37. ICLR 2026Robust Federated Inference
38. ICLR 2026Traceable Black-Box Watermarks For Federated Learning
39. ICLR 2026Unified Analyses for Hierarchical Federated Learning: Topology Selection under Data Heterogeneity
40. ICLR 2026Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression
41. ICML 2026Accurate, Private, Secure, Federated U-statistics with Higher Degree
42. ICML 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
43. ICML 2026Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
44. ICML 2026CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings
45. ICML 2026Controlled Collaboration Geometry for Personalized Federated Learning
46. ICML 2026Cross-task Calibration for Asynchronous Federated Continual Learning
47. ICML 2026Cross-View Lewis Weight Fusion Empowering Exemplar Replay for Federated Class-Incremental Learning
48. ICML 2026Explainable Federated Learning via Global–Local Attribution Alignment
49. ICML 2026FedEMoE: Improving Personalization on Heterogeneous Federated Learning via Elastic Mixture of Experts Architecture
50. ICML 2026Federated Bilevel Performative Prediction

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。