Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis

TL;DR

This paper presents a novel, efficient framework for task grouping in multi-task learning that infers task similarities through samplewise landscape analysis, significantly reducing computational costs while maintaining high performance.

Contribution

It introduces a samplewise optimisation landscape analysis method to infer task similarities, enabling faster and effective task grouping without extensive shared model training.

Findings

Five-fold speed improvement over state-of-the-art methods

Consistent task grouping performance across 8 datasets

Effective identification of near-optimal task groups

Abstract

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. Empirical assessments conducted on 8 different datasets highlight the effectiveness of the proposed framework, revealing a five-fold speed enhancement compared to previous state-of-the-art methods. Moreover, the framework consistently demonstrates comparable performance, confirming its remarkable efficiency and effectiveness in task grouping.