SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments
This addresses label distribution skew in federated learning for distributed clients, but it appears incremental as it builds on existing SFL frameworks with specific adjustments.
The paper tackles performance degradation in Split Federated Learning due to data heterogeneity and partial client participation by proposing SCALA, which uses concatenated activations and logit adjustments to centrally adjust label distributions, achieving verified superiority on public datasets.
Split Federated Learning (SFL) is a distributed machine learning framework which strategically divides the learning process between a server and clients and collaboratively trains a shared model by aggregating local models updated based on data from distributed clients. However, data heterogeneity and partial client participation result in label distribution skew, which severely degrades the learning performance. To address this issue, we propose SFL with Concatenated Activations and Logit Adjustments (SCALA). Specifically, the activations from the client-side models are concatenated as the input of the server-side model so as to centrally adjust label distribution across different clients, and logit adjustments of loss functions on both server-side and client-side models are performed to deal with the label distribution variation across different subsets of participating clients. Theoretical analysis and experimental results verify the superiority of the proposed SCALA on public datasets.