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 119 篇，第 2 / 3 页

51. ICML 2026Federated Graph Learning via Structure-Aware Fusion Using a Kalman Framework with Learnable Dynamics
52. ICML 2026Federated Multi-view Clustering for Remote Sensing Data
53. ICML 2026FedFit: Federated Dynamic Sparse Training via Fisher Information scoring
54. ICML 2026FedGain: Toward Negative-Gain-Free Client Collaboration in Federated Learning
55. ICML 2026FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources
56. ICML 2026FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
57. ICML 2026FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC Training
58. ICML 2026FedReLa: Imbalanced Federated Learning via Re-Labeling
59. ICML 2026FedRGL: Robust Federated Graph Learning under Label Noise
60. ICML 2026FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
61. ICML 2026FedScar: Correcting Geometric Bias for Flatness-Consistent Federated Learning
62. ICML 2026FedSDR: Federated Self-Distillation with Rectification
63. ICML 2026FedSSM: State Space Model-based Proactive Inference for Heterogeneous Multimodal Federated Learning
64. ICML 2026FedUSD: Unbiased Synthetic Data for Federated Learning
65. ICML 2026FedVeer: Self-Adaptive Skew Estimation for Robust Federated Learning
66. ICML 2026GeoEvo: Identity-Aware Potential Game with Geometric Evolution for Personalized Multimodal Federated Learning
67. ICML 2026Influence-Disentangled Federated Training: Learning Models That Are Easy to Unlearn
68. ICML 2026Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels
69. ICML 2026Lightweight Federated Incremental Learning via Decoupled Replay
70. ICML 2026One-Shot Weighted Ensemble Estimation for Federated Quantile Regression: Optimal Statistical Guarantees under Heterogeneous Structured Data
71. ICML 2026Prototype-guided Bilateral Alignment Multimodal Federated Learning
72. ICML 2026RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective Calibration
73. ICML 2026SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts
74. ICML 2026ShapCCS: Shapley-Driven Client Coreset Selection in Federated Learning
75. ICML 2026Towards Rule-Based Knowledge Sharing in Federated Learning
76. ICML 2026Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
77. ICML 2026Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
78. NeurIPS 2026A typed tensor language for federated learning
79. NeurIPS 2026Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks
80. NeurIPS 2026Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
81. NeurIPS 2026ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning
82. NeurIPS 2026Bayes-pFCL:Bayesian Personalized Federated Continual Learning
83. NeurIPS 2026Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification
84. NeurIPS 2026Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift
85. NeurIPS 2026Crossing the Validation crisis: Cross-validation reduces benchmarking variance surprisingly well
86. NeurIPS 2026Dynamic Spectral Federated Graph-Level Clustering
87. NeurIPS 2026Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
88. NeurIPS 2026Faster Rates For Federated Variational Inequalities
89. NeurIPS 2026FAUST: Federated Asynchronous Update with Staggered Timescales for Low-Communication Foundation Model Training
90. NeurIPS 2026Fed-AGA: An Anchor Graph Alignment Framework for Federated Unaligned Multi-view Clustering
91. NeurIPS 2026FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
92. NeurIPS 2026FedCF: Fair Federated Conformal Prediction
93. NeurIPS 2026Federated Graph Learning with Local Message Compensation
94. NeurIPS 2026Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
95. NeurIPS 2026Federated Logic Gate Networks via Boolean Feature Selection
96. NeurIPS 2026FedLoVA: Value-Only Aggregation for Federated LoRA Fine-Tuning of Large Language Models
97. NeurIPS 2026FedPeel: Peeling Stabilized Layers for Robust Heterogeneous Federated Learning
98. NeurIPS 2026FedReCall: Recalling Client-Specific Directions in Federated LoRA Fine-tuning
99. NeurIPS 2026FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning
100. NeurIPS 2026FedSOUL: Federated Continual Unlearning via Spectral Orthogonality

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。