Computer Science / Machine Learning

BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework

Reading time: 2 minute
...

📝 Original Info

  • Title: BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework
  • ArXiv ID: 2512.24708
  • Date: 2025-12-31
  • Authors: András Millinghoffer, András Formanek, András Antos, Péter Antal

📝 Abstract

The challenge of effectively transferring knowledge across multiple tasks is of critical importance and is also present in downstream tasks with foundation models. However, the nature of transfer, its transitive-intransitive nature, is still an open problem, and negative transfer remains a significant obstacle. Selection of beneficial auxiliary task sets in multi-task learning is frequently hindered by the high computational cost of their evaluation, the high number of plausible candidate auxiliary sets, and the varying complexity of selection across target tasks. To address these constraints, we introduce BandiK, a novel threestage multi-task auxiliary task subset selection method using multibandits, where each arm pull evaluates candidate auxiliary sets by training and testing a multiple output neural network on a single random train-test dataset split. Firstly, BandiK estimates the pairwise transfers between tasks, which helps in identifying which tasks are likely to benefit from joint learning. In the second stage, it constructs a linear number of candidate sets of auxiliary tasks (in the number of all tasks) for each target task based on the initial estimations, significantly reducing the exponential number of...

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)

Start searching

Enter keywords to search articles

↑↓
↵
ESC
⌘K Shortcut