Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates
This work addresses scalability issues in decentralized learning for large-scale ML training, offering an incremental improvement over existing methods.
The paper tackles the problem of stragglers in decentralized machine learning by proposing DSGD-AAU, an algorithm with adaptive asynchronous updates that reduces synchronization delays, achieving a linear speedup in convergence as demonstrated in experiments.
With the increasing demand for large-scale training of machine learning models, fully decentralized optimization methods have recently been advocated as alternatives to the popular parameter server framework. In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset. However, the synchronization phase is sensitive to stragglers. An efficient way to mitigate this effect is to consider asynchronous updates, where each worker computes stochastic gradients and communicates with other workers at its own pace. Unfortunately, fully asynchronous updates suffer from staleness of stragglers' parameters. To address these limitations, we propose a fully decentralized algorithm DSGD-AAU with adaptive asynchronous updates via adaptively determining the number of neighbor workers for each worker to communicate with. We show that DSGD-AAU achieves a linear speedup for convergence and demonstrate its effectiveness via extensive experiments.