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.

翻译：共享训练方法，如多任务学习（MTL）和基于梯度的元学习，在各类机器学习应用中得到了广泛使用，但它们常常受到负迁移的影响，导致特定任务的性能下降。尽管已有多种优化技术被开发出来，用于缓解预选任务组合中的这一问题，但为联合学习识别最优任务组合——即任务分组——仍然研究不足且计算上具有挑战性，这源于任务组合数量的指数级增长以及需要进行大量训练和评估循环。本文提出了一种高效的任务分组框架，旨在降低现有方法中这些过高的计算需求。该框架通过样本级的优化景观分析来推断任务间的两两相似性，从而无需像现有方法那样通过共享模型训练来推断任务相似性。在获得任务相似性后，采用一种基于图的聚类算法来识别接近最优的任务分组，为这个原本是NP难的问题提供了一个近似但高效且有效的解决方案。在8个不同数据集上进行的实证评估突显了所提框架的有效性，与先前最先进的方法相比，其速度提升了五倍。此外，该框架始终展现出可比的性能，证实了其在任务分组方面卓越的效率和有效性。