Auxiliary learning is an effective method for enhancing the generalization capabilities of trained models, particularly when dealing with small datasets. However, this approach may present several difficulties: (i) optimizing multiple objectives can be more challenging, and (ii) how to balance the auxiliary tasks to best assist the main task is unclear. In this work, we propose a novel approach, named AuxiNash, for balancing tasks in auxiliary learning by formalizing the problem as a generalized bargaining game with asymmetric task bargaining power. Furthermore, we describe an efficient procedure for learning the bargaining power of tasks based on their contribution to the performance of the main task and derive theoretical guarantees for its convergence. Finally, we evaluate AuxiNash on multiple multi-task benchmarks and find that it consistently outperforms competing methods.
|Number of pages||17|
|Journal||Proceedings of Machine Learning Research|
|State||Published - 2023|
|Event||40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States|
Duration: 23 Jul 2023 → 29 Jul 2023
Bibliographical notePublisher Copyright:
© 2023 Proceedings of Machine Learning Research. All rights reserved.