Training Mixed-Domain Translation Models via Federated Learning

TL;DR

This paper explores using federated learning to train mixed-domain neural machine translation models, enabling domain adaptation and reducing data sharing costs while maintaining competitive performance.

Contribution

It introduces a federated learning approach for NMT, with modifications for domain fusion, and proposes a dynamic bandwidth control technique for efficient communication.

Findings

FL-based NMT models perform on par with centralized baselines.

The approach effectively adapts to multiple domains with minimal modifications.

A novel bandwidth control method reduces communication overhead during FL updates.

Abstract

Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation demonstrates that with slight modifications in the training process, neural machine translation (NMT) engines can be easily adapted when an FL-based aggregation is applied to fuse different domains. Experimental results also show that engines built via FL are able to perform on par with state-of-the-art baselines that rely on centralized training techniques. We evaluate our hypothesis in the presence of five datasets with different sizes, from different domains, to translate from German into English and discuss how FL and NMT can mutually benefit from each other. In addition to providing benchmarking results on the union of FL and NMT, we also propose a novel technique to dynamically control the communication bandwidth by selecting impactful parameters during FL updates. This is a significant achievement considering the large size of NMT engines that need to be exchanged between FL parties.