Federated Learning papers, 2023–2026

Key findings

• Federated Learning fell from 137 papers in 2023 to 119 in 2026, so interest is cooling.
• NeurIPS publishes the most Federated Learning work: 157 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Low-Rank Adaptation: papers tagged with both rose from 0 in 2023 to 12 in 2026.
• Among the 5 topics under Federated and Privacy, it ranks #2 by 2026 paper count; the fastest grower in the group, Secure Aggregation, is up 1.8x versus 0.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Federated Learning papers

91 papers, page 2 of 2

51. ICML 2025Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
52. ICML 2025LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation
53. ICML 2025Local Pan-privacy for Federated Analytics
54. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
55. ICML 2025NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
56. ICML 2025One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory
57. ICML 2025Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
58. ICML 2025SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
59. ICML 2025Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models
60. ICML 2025Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
61. NeurIPS 2025A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments
62. NeurIPS 2025A Reinforcement Learning-based Bidding Strategy for Data Consumers in Auction-based Federated Learning
63. NeurIPS 2025Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
64. NeurIPS 2025Adaptive Latent-Space Constraints in Personalized Federated Learning
65. NeurIPS 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learning
66. NeurIPS 2025Competitive Advantage Attacks to Decentralized Federated Learning
67. NeurIPS 2025Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
68. NeurIPS 2025Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
69. NeurIPS 2025Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning
70. NeurIPS 2025FedEL: Federated Elastic Learning for Heterogeneous Devices
71. NeurIPS 2025FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
72. NeurIPS 2025FedIGL: Federated Invariant Graph Learning for Non-IID Graphs
73. NeurIPS 2025FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling
74. NeurIPS 2025FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
75. NeurIPS 2025FORLA: Federated Object-centric Representation Learning with Slot Attention
76. NeurIPS 2025Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
77. NeurIPS 2025Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
78. NeurIPS 2025Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data
79. NeurIPS 2025MARS: A Malignity-Aware Backdoor Defense in Federated Learning
80. NeurIPS 2025Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
81. NeurIPS 2025Personalized Federated Conformal Prediction with Localization
82. NeurIPS 2025Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections
83. NeurIPS 2025Resource-Constrained Federated Continual Learning: What Does Matter?
84. NeurIPS 2025Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity
85. NeurIPS 2025Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
86. NeurIPS 2025Sharp Gaussian approximations for Decentralized Federated Learning
87. NeurIPS 2025Soft-consensual Federated Learning for Data Heterogeneity via Multiple Paths
88. NeurIPS 2025Streaming Federated Learning with Markovian Data
89. NeurIPS 2025Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
90. NeurIPS 2025Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
91. NeurIPS 2025Vertical Federated Feature Screening

FAQ

How many Federated Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

460 in total: 137 in 2023, 113 in 2024, 91 in 2025, 119 in 2026.

How many Federated Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 42 Federated Learning papers, versus 31 the year before.

How many Federated Learning papers are at ICLR 2026?

ICLR 2026 has 19 Federated Learning papers, versus 18 the year before.

How many Federated Learning papers are at ICML 2026?

ICML 2026 has 37 Federated Learning papers, versus 23 the year before.

How many Federated Learning papers are at CVPR 2026?

CVPR 2026 has 21 Federated Learning papers, versus 19 the year before.

Which conference publishes the most Federated Learning papers?

NeurIPS, with 157 papers from 2023 to 2026.