mlsanityData to 7 Oct 2026

Single-Round Scalable Analytic Federated Learning

arXiv 2512.03336 ↗First posted 3 Dec 2025cs.LG cs.AI stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-round, data distribution invariant solution, but is limited to linear models. Subsequent non-linear approaches, like DeepAFL, regain accuracy but sacrifice the single-round benefit. In this work, we break this trade-off. We propose SAFLe, a framework that achieves scalable non-linear expressivity by introducing a structured head of bucketed features and sparse, grouped embeddings. We prove this non-linear architecture is mathematically equivalent to a high-dimensional linear regression. This key equivalence allows SAFLe to be solved with AFL's single-shot, invariant aggregation law. Empirically, SAFLe establishes a new state-of-the-art for analytic FL, significantly outperforming both linear AFL and multi-round DeepAFL in accuracy across all benchmarks, demonstrating a highly efficient and scalable solution for federated vision.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 38 references that are in the map. First posted on arXiv 3 Dec 2025.

Builds on

25 of 38 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  7. 2021Model-Contrastive Federated Learningcited by 762
  8. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  10. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  11. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  12. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 224
13 more
  1. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
  2. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  3. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 66
  4. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  5. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  6. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  7. 2024Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boostingcited by 27
  8. 2024Revisiting Ensembling in One-Shot Federated Learningcited by 13
  9. 2024One-shot Federated Learning via Synthetic Distiller-Distillate Communicationcited by 12
  10. 2024AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Modelscited by 11
  11. 2023Handling Data Heterogeneity via Architectural Design for Federated Visual Recognitioncited by 8
  12. 2025Capture Global Feature Statistics for One-Shot Federated Learningcited by 6
  13. 2025TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Modelscited by 1

Built on by

Not cited yet.