Auxiliary Learning as an Asymmetric Bargaining Game

2023/01/31 by Aviv Shamsian, Shamsian, Aviv, Aviv Navon +9 · 3 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2301.13501

openalex publication_date 2023/01/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 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.

Cited by

• Model Merging via Multi-Teacher Knowledge Distillation
• Generating Auxiliary Tasks with Reinforcement Learning
• Expert Merging in Sparse Mixture of Experts with Nash Bargaining

Related

• Multi-Task Learning as a Bargaining Game
• A Contextual Combinatorial Bandit Approach to Negotiation
• Automated Configuration and Usage of Strategy Portfolios for Bargaining
• LLM Agents for Bargaining with Utility-based Feedback
• Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning