Federated Edge Inference papers, 2023–2026

Key findings

• Federated Edge Inference went from 43 papers in 2023 to 45 in 2026, roughly 1.0x in three years.
• ICML publishes the most Federated Edge Inference work: 60 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Edge Inference: papers tagged with both rose from 3 in 2023 to 15 in 2026.
• Among the 5 topics under Edge and IoT, it ranks #2 by 2026 paper count; the fastest grower in the group, Sensor Fusion, is up 3.8x versus 1.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
• ICML 2026Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
• ICLR 2026Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
• CVPR 2026E2-SCI Elastic Edge-Cloud Speculative Decoding via Credit Inertia
• NeurIPS 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learning
• ICML 2025Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
• ICLR 2025Connecting Federated ADMM to Bayes
• CVPR 2025Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning
• NeurIPS 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
• ICML 2024Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning
• ICLR 2024FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning
• CVPR 2024FedAS: Bridging Inconsistency in Personalized Federated Learning
• NeurIPS 2023Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices
• ICML 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learning
• ICLR 2023Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
• CVPR 2023How To Prevent the Poor Performance Clients for Personalized Federated Learning?
• NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
• ICML 2026Influence-Disentangled Federated Training: Learning Models That Are Easy to Unlearn
• ICLR 2026DeepAFL: Deep Analytic Federated Learning
• CVPR 2026Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation

All Federated Edge Inference papers

180 papers, page 1 of 4

1. CVPR 2026E2-SCI Elastic Edge-Cloud Speculative Decoding via Credit Inertia
2. CVPR 2026Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation
3. CVPR 2026From Selection to Scheduling Federated Geometry-Aware Correction Makes Exemplar Replay
4. CVPR 2026Single-Round Scalable Analytic Federated Learning
5. CVPR 2026Submodel Extraction for Efficient and Personalized Federated Learning via Optimal
6. ICLR 2026Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
7. ICLR 2026DeepAFL: Deep Analytic Federated Learning
8. ICLR 2026Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
9. ICLR 2026Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language Learning
10. ICLR 2026Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus
11. ICLR 2026Near Optimal Robust Federated Learning Against Data Poisoning Attack
12. ICLR 2026Robust Federated Inference
13. ICML 2026Benchmarking at the Edge of Comprehension
14. ICML 2026Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
15. ICML 2026Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
16. ICML 2026Credibility-Aware Weighting Federated Causal Discovery for Time Series
17. ICML 2026Edge-colored Clustering in Hypergraphs: A MaxECC Approximation
18. ICML 2026FedEMoE: Improving Personalization on Heterogeneous Federated Learning via Elastic Mixture of Experts Architecture
19. ICML 2026FedFit: Federated Dynamic Sparse Training via Fisher Information scoring
20. ICML 2026FedGain: Toward Negative-Gain-Free Client Collaboration in Federated Learning
21. ICML 2026FedReLa: Imbalanced Federated Learning via Re-Labeling
22. ICML 2026Influence-Disentangled Federated Training: Learning Models That Are Easy to Unlearn
23. ICML 2026Lightweight Federated Incremental Learning via Decoupled Replay
24. ICML 2026Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
25. ICML 2026No Retraining at Edge: Efficient Resource-Aware Mixed-Precision Quantization via Federated Supernet Learning
26. ICML 2026Non-Euclidean Gradient Descent Operates at the Edge of Stability
27. ICML 2026PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
28. ICML 2026RADE: Random Add-Drop Edge as a Regularizer
29. ICML 2026ShapCCS: Shapley-Driven Client Coreset Selection in Federated Learning
30. ICML 2026Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
31. NeurIPS 2026A typed tensor language for federated learning
32. NeurIPS 2026ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning
33. NeurIPS 2026Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
34. NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
35. NeurIPS 2026Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
36. NeurIPS 2026FedSEM: Mitigating Cross-Client Evidence Drift in Federated Multiple Instance Learning
37. NeurIPS 2026FedSOUL: Federated Continual Unlearning via Spectral Orthogonality
38. NeurIPS 2026Generalization at the Edge of Stability
39. NeurIPS 2026Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality
40. NeurIPS 2026Geometry-Regularized Collapse Resistance via Consensus Enhancement for Federated Learning
41. NeurIPS 2026MainFL: Intertemporal Data Valuation for Robust Auction-based Federated Learning
42. NeurIPS 2026Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning
43. NeurIPS 2026SGD at the Edge of Stability: The Stochastic Sharpness Gap
44. NeurIPS 2026ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
45. NeurIPS 2026Stability-Enhanced Federated Learning with Accelerated Gradient
46. CVPR 2025AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
47. CVPR 2025Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning
48. CVPR 2025FedCS: Coreset Selection for Federated Learning
49. CVPR 2025NoT: Federated Unlearning via Weight Negation
50. CVPR 2025Population Normalization for Federated Learning

FAQ

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

180 in total: 43 in 2023, 47 in 2024, 45 in 2025, 45 in 2026.

How many Federated Edge Inference papers are at NeurIPS 2026?

NeurIPS 2026 has 15 Federated Edge Inference papers, versus 20 the year before.

How many Federated Edge Inference papers are at ICLR 2026?

ICLR 2026 has 7 Federated Edge Inference papers, versus 10 the year before.

How many Federated Edge Inference papers are at ICML 2026?

ICML 2026 has 18 Federated Edge Inference papers, versus 10 the year before.

How many Federated Edge Inference papers are at CVPR 2026?

CVPR 2026 has 5 Federated Edge Inference papers, versus 5 the year before.

Which conference publishes the most Federated Edge Inference papers?

ICML, with 60 papers from 2023 to 2026.