Can I read Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis on EtoBox?

Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis by Thakur, Anshul; Huang, Yichen; Molaei, Soheila; Wang, Yujiang; Clifton, David A. is a scholarly article available to read on EtoBox.

What is Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis about?

Shared training approaches, such as multi-task learning (MTL) and gradient-based meta-learning, are widely used in various machine learning applications, but they often suffer from negative transfer, leading to performance degradation in specific tasks. While several optimisation techniques have been developed to mitigate this issue for pre-selected task cohorts, identifying optimal task combinations for joint learning - known as task grouping - remains underexplored and computationally challenging due to the exponential growth in task combinations and the need for extensive training and evaluation cycles. This paper introduces an efficient task grouping framework designed to reduce these overwhelming computational demands of the existing methods. The proposed framework infers pairwise task similarities through a sample-wise optimisation landscape analysis, eliminating the need for the shared model training required to infer task similarities in existing methods. With task similarities acquired, a graph-based clustering algorithm is employed to pinpoint near-optimal task groups, providing an approximate yet efficient and effective solution to the originally NP-hard problem. Empiric

Author

Thakur, Anshul; Huang, Yichen; Molaei, Soheila; Wang, Yujiang; Clifton, David A.

Published

2024

Language

EN