Publications [#364982] of Lawrence Carin

Papers Published

1. Sundararaman, D; Tsai, H; Lee, KH; Turc, I; Carin, L, Learning Task Sampling Policy for Multitask Learning, Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021 (January, 2021), pp. 4410-4415, ISBN 9781955917100
   (last updated on 2024/12/31)

   Abstract:
   It has been shown that training multi-task models with auxiliary tasks can improve the target tasks quality through cross-task transfer. However, the importance of each auxiliary task to the primary task is likely not known a priori. While the importance weights of auxiliary tasks can be manually tuned, it becomes practically infeasible with the number of tasks scaling up. To address this, we propose a search method that automatically assigns importance weights. We formulate it as a reinforcement learning problem and learn a task sampling schedule based on evaluation accuracy of the multi-task model. Our empirical evaluation on XNLI and GLUE shows that our method outperforms uniform sampling and the corresponding single-task baseline.