LGDCDec 2, 2022

Faster Adaptive Federated Learning

arXiv:2212.00974v3102 citationsh-index: 22
Originality Highly original
AI Analysis

This work addresses efficiency and adaptivity issues in federated learning for distributed data applications, representing a strong specific gain rather than a foundational advancement.

The paper tackles the challenge of slow convergence and lack of adaptivity in federated learning by proposing FAFED, an adaptive algorithm that achieves sample complexity of O(ε^{-3}) and communication rounds of O(ε^{-2}) to find an ε-stationary point, with experimental validation on language modeling and image classification tasks.

Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variance-reduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples $O(ε^{-3})$ and $O(ε^{-2})$ communication rounds to find an $ε$-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes