Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning

No. 1: AAAI-19, IAAI-19, EAAI-20

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 33

Student Abstract Track

In settings with related prediction tasks, integrated multi-task learning models can often improve performance relative to independent single-task models. However, even when the average task performance improves, individual tasks may experience negative transfer in which the multi-task model’s predictions are worse than the single-task model’s. We show the prevalence of negative transfer in a computational chemistry case study with 128 tasks and introduce a framework that provides a foundation for reducing negative transfer in multitask models. Our Loss-Balanced Task Weighting approach dynamically updates task weights during model training to control the influence of individual tasks.

10.1609/aaai.v33i01.33019977