Convergence Analysis of Split Learning on Non-IID Data

Split Learning (SL) is one promising variant of Federated Learning (FL), where the AI model is split and trained at the clients and the server collaboratively. By offloading the computation-intensive portions to the server, SL enables efficient model training on resource-constrained clients. Despite its booming applications, SL still lacks rigorous convergence analysis on non-IID data, which is critical for hyperparameter selection. In this paper, we first prove that SL exhibits an $\mathcal{O}(1/\sqrt{R})$ convergence rate for non-convex objectives on non-IID data, where $R$ is the number of total training rounds. The derived convergence results can facilitate understanding the effect of some crucial factors in SL (e.g., data heterogeneity and synchronization interval). Furthermore, comparing with the convergence result of FL, we show that the guarantee of SL is worse than FL in terms of training rounds on non-IID data. The experimental results verify our theory. More findings on the comparison between FL and SL in cross-device settings are also reported.