Taming Update Drift in Asynchronous Federated Learning via Orthogonal Calibration
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 6464-6475
Abstract
No abstract availableFunding Information
- NSF (National Science Foundation) (2239440)
- NSF (National Science Foundation) (2333790)
- ACE SRC JUMP 2.0 (2023-JU-3134)
This publication has 24 references indexed in Scilit:
- FediOS: decoupling orthogonal subspaces for personalization in feature-skew federated learningMachine Learning, 2025
- FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning2024
- Towards Efficient Asynchronous Federated Learning in Heterogeneous Edge Environments2024
- Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning2024
- How Asynchronous can Federated Learning Be?2022
- Robust Federated Learning with Noisy and Heterogeneous Clients2022
- FedMask2021
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]IEEE Signal Processing Magazine, 2012
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998