Adaptive Serverless Learning
This work addresses the need for adaptive training in applications like deep factorization machines with sparse and categorical features, offering a novel solution for distributed data scenarios, though it is incremental in extending existing decentralized methods.
The paper tackles the problem of training machine learning models with adaptive algorithms in a serverless, decentralized setting, proposing two approaches that achieve linear speedup with respect to the number of workers, as confirmed by extensive experiments.
With the emergence of distributed data, training machine learning models in the serverless manner has attracted increasing attention in recent years. Numerous training approaches have been proposed in this regime, such as decentralized SGD. However, all existing decentralized algorithms only focus on standard SGD. It might not be suitable for some applications, such as deep factorization machine in which the feature is highly sparse and categorical so that the adaptive training algorithm is needed. In this paper, we propose a novel adaptive decentralized training approach, which can compute the learning rate from data dynamically. To the best of our knowledge, this is the first adaptive decentralized training approach. Our theoretical results reveal that the proposed algorithm can achieve linear speedup with respect to the number of workers. Moreover, to reduce the communication-efficient overhead, we further propose a communication-efficient adaptive decentralized training approach, which can also achieve linear speedup with respect to the number of workers. At last, extensive experiments on different tasks have confirmed the effectiveness of our proposed two approaches.