One-stop Training of Multiple Capacity Models for Multilingual Machine Translation

Lan Jiang, Haoyang Huang, Dongdong Zhang, Rui Jiang, Furu Wei

Training models with varying capacities can be advantageous for deploying them in different scenarios. While high-capacity models offer better performance, low-capacity models require fewer computing resources for training and inference. In this work, we propose a novel one-stop training framework consisting of two composite model architectures and a joint training algorithm called Two-Stage Joint-Training (TSJT). Unlike knowledge distillation, where multiple capacity models are trained from scratch separately, our approach integrates supervisions from different flexible-capacity models simultaneously, leading to faster and more efficient convergence. Extensive experiments on the WMT10 benchmark show that our method outperforms low-capacity baseline models and achieves comparable or better performance on high-capacity models. Notably, the analysis demonstrates that our method significantly influences the initial training process, leading to more efficient convergence and superior solutions.

Knowledge Graph



Sign up or login to leave a comment