Order Matters in the Presence of Dataset Imbalance for Multilingual Learning
This addresses optimization challenges in multi-task learning for researchers and practitioners dealing with imbalanced datasets, though it is incremental as it builds on existing pre-training and fine-tuning approaches.
The paper tackles the problem of dataset imbalance in multilingual learning by proposing a method of pre-training on high-resource tasks followed by fine-tuning on a mixture of tasks, showing consistent improvements over standard static weighting in neural machine translation and multilingual language modeling.
In this paper, we empirically study the optimization dynamics of multi-task learning, particularly focusing on those that govern a collection of tasks with significant data imbalance. We present a simple yet effective method of pre-training on high-resource tasks, followed by fine-tuning on a mixture of high/low-resource tasks. We provide a thorough empirical study and analysis of this method's benefits showing that it achieves consistent improvements relative to the performance trade-off profile of standard static weighting. We analyze under what data regimes this method is applicable and show its improvements empirically in neural machine translation (NMT) and multi-lingual language modeling.