mlsanityData to 7 Oct 2026

GAS: Generative Activation-Aided Asynchronous Split Federated Learning

arXiv 2409.01251 ↗First posted 2 Sep 2024cs.LG cs.DCcited by 3

Not on the map. Why?

Abstract (arXiv)

Split Federated Learning (SFL) splits and collaboratively trains a shared model between clients and server, where clients transmit activations and client-side models to server for updates. Recent SFL studies assume synchronous transmission of activations and client-side models from clients to server. However, due to significant variations in computational and communication capabilities among clients, activations and client-side models arrive at server asynchronously. The delay caused by asynchrony significantly degrades the performance of SFL. To address this issue, we consider an asynchronous SFL framework, where an activation buffer and a model buffer are embedded on the server to manage the asynchronously transmitted activations and client-side models, respectively. Furthermore, as asynchronous activation transmissions cause the buffer to frequently receive activations from resource-rich clients, leading to biased updates of the server-side model, we propose Generative activations-aided Asynchronous SFL (GAS). In GAS, the server maintains an activation distribution for each label based on received activations and generates activations from these distributions according to the degree of bias. These generative activations are then used to assist in updating the server-side model, ensuring more accurate updates. We derive a tighter convergence bound, and our experiments demonstrate the effectiveness of the proposed method. The code is available at https://github.com/eejiarong/GAS.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 2 Sep 2024.

Builds on

23 of 37 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2020Long-tail learning via logit adjustmentcited by 605
  6. 2021A Field Guide to Federated Optimizationcited by 312
  7. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  8. 2018Distributed learning of deep neural network over multiple agentscited by 277
  9. 2019Asynchronous Federated Optimizationcited by 264
  10. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  11. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
  12. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
11 more
  1. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 108
  2. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 99
  3. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
  4. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  5. 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
  6. 2021Adaptive Transmission Scheduling in Wireless Networks for Asynchronous Federated Learningcited by 15
  7. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
  8. 2022FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clientscited by 14
  9. 2024Queuing dynamics of asynchronous Federated Learningcited by 6
  10. 2023Have Your Cake and Eat It Too: Toward Efficient and Accurate Split Federated Learningcited by 5
  11. 2024SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustmentscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approachcited by 7
  2. 2026HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregationcited by 1
  3. 2026CoeF-SFL: Preserving Collaborative Server-Client Learning with Enhanced Communication Efficiencycited by 0