Weighted Training for Cross-Task Learning
arXiv:2105.14095
Abstract
In this paper, we introduce Target-Aware Weighted Training (TAWT), a weighted training algorithm for cross-task learning based on minimizing a representation-based task distance between the source and target tasks. We show that TAWT is easy to implement, is computationally efficient, requires little hyperparameter tuning, and enjoys non-asymptotic learning-theoretic guarantees. The effectiveness of TAWT is corroborated through extensive experiments with BERT on four sequence tagging tasks in natural language processing (NLP), including part-of-speech (PoS) tagging, chunking, predicate detection, and named entity recognition (NER). As a byproduct, the proposed representation-based task distance allows one to reason in a theoretically principled way about several critical aspects of cross-task learning, such as the choice of the source data and the impact of fine-tuning.
Published as a conference paper at ICLR 2022
References in corpus (6)
- Distilling the Knowledge in a Neural Network
- On the Theory of Transfer Learning: The Importance of Task Diversity
- Provable Meta-Learning of Linear Representations
- On the Value of Target Data in Transfer Learning
- How Fine-Tuning Allows for Effective Meta-Learning
- Meta-learning Transferable Representations with a Single Target Domain