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 23 篇，第 1 / 1 页

1. ICML 2025Causality Inspired Federated Learning for OOD Generalization
2. ICML 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
3. ICML 2025FedECADO: A Dynamical System Model of Federated Learning
4. ICML 2025Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
5. ICML 2025Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
6. ICML 2025Federated Learning for Feature Generalization with Convex Constraints
7. ICML 2025Federated Node-Level Clustering Network with Cross-Subgraph Link Mending
8. ICML 2025FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence
9. ICML 2025Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
10. ICML 2025FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
11. ICML 2025Gap-Dependent Bounds for Federated $Q$-Learning
12. ICML 2025Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference
13. ICML 2025Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning
14. ICML 2025Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
15. ICML 2025LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation
16. ICML 2025Local Pan-privacy for Federated Analytics
17. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
18. ICML 2025NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
19. ICML 2025One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory
20. ICML 2025Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
21. ICML 2025SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
22. ICML 2025Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models
23. ICML 2025Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg

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。