mlsanityData to 7 Oct 2026

BAFFLE: A Baseline of Backpropagation-Free Federated Learning

arXiv 2301.12195 ↗First posted 28 Jan 2023cs.LG cs.AI cs.CRcited by 12

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation is replaced by multiple forward processes to estimate gradients. BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server. Empirically we use BAFFLE to train deep models from scratch or to finetune pretrained models, achieving acceptable results. Code is available in https://github.com/FengHZ/BAFFLE.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 69 of its 102 references that are in the map. First posted on arXiv 28 Jan 2023.

Builds on

69 of 102 references.

References · 69

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  6. 2016Wide Residual Networkscited by 3,057
  7. 2019Advances and Open Problems in Federated Learningcited by 3,021
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2018Group Normalizationcited by 1,514
  12. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
38 more
  1. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  2. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  3. 2018Federated Learning with Non-IID Datacited by 1,099
  4. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  5. 2018LEAF: A Benchmark for Federated Settingscited by 780
  6. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  7. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  8. 2017Federated Multi-Task Learningcited by 669
  9. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  11. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  12. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  13. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  14. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  15. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  16. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  17. 2019Can You Really Backdoor Federated Learning?cited by 250
  18. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  19. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
  20. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  21. 2016What makes ImageNet good for transfer learning?cited by 192
  22. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  23. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 179
  24. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  25. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 178
  26. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
  27. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 162
  28. 2020A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learningcited by 160
  29. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  30. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  31. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  32. 2017Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networkscited by 95
  33. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  34. 2019Reliable Federated Learning for Mobile Networkscited by 92
  35. 2019Natural Compression for Distributed Deep Learningcited by 88
  36. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 71
  37. 2022Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learningcited by 59
  38. 2019On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learningcited by 57

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3; 2025: 6.

12 papers.

  1. 2023Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytescited by 55
  2. 2023FwdLLM: Efficient FedLLM using Forward Gradientcited by 25
  3. 2024Thinking Forward: Memory-Efficient Federated Finetuning of Language Modelscited by 7
  4. 2023FedZeN: Towards superlinear zeroth-order federated learning via incremental Hessian estimationcited by 4
  5. 2025Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimizationcited by 3
  6. 2024When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devicescited by 2
  7. 2024Communication and Energy Efficient Federated Learning using Zero-Order Optimization Techniquecited by 1
  8. 2025Memory Savings at What Cost? A Study of Alternatives to Backpropagationcited by 1
  9. 2025Communication-Efficient Zero-Order and First-Order Federated Learning Methods over Wireless Networkscited by 1
  10. 2025Learning without Global Backpropagation via Synergistic Information Distillationcited by 1
  11. 2025Analytic Personalized Federated Meta-Learningcited by 0
  12. 2025Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devicescited by 0