SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.13501 · ICML · 2023

Auxiliary Learning as an Asymmetric Bargaining Game

Gal Chechik, Aviv Navon, Ethan Fetaya, Kenji Kawaguchi, Aviv Shamsian, Neta Glazer

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
AvivSham/auxinash canonical 0 of 3
FunctionStatusWhere it lives
AuxiNash Not yet run AvivSham/auxinash/methods/weight_methods.py
code served (permissive licence) · get_code("41ef7af6d65becf5")
NashMTL Not yet run AvivSham/auxinash/methods/weight_methods.py
code served (permissive licence) · get_code("6f9014a85f531ffe")
WeightMethod Not yet run AvivSham/auxinash/methods/weight_methods.py
code served (permissive licence) · get_code("d7b21de5b7ce2610")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.13501")
get_code_for_paper("2301.13501")
have("2301.13501")

Connect an agent — have() is free.