Multi-Task Learning (MTL) is a powerful technique that has gained popularity due to its performance improvement over traditional Single-Task Learning (STL). However, MTL is often challenging because there is an exponential number of possible task groupings, which can make it difficult to choose the best one, and some groupings might produce performance degradation due to negative interference between tasks. Furthermore, existing solutions are severely suffering from scalability issues, limiting any practical application. In our paper, we propose a new data-driven method that addresses these challenges and provides a scalable and modular solution for classification task grouping based on hand-crafted features, specifically Data Maps, which capture the training behavior for each classification task during the MTL training. We experiment with the method demonstrating its effectiveness, even on an unprecedented number of tasks (up to 100).

翻译：多任务学习（MTL）是一种强大的技术，因其相比传统单任务学习（STL）在性能上的提升而广受欢迎。然而，MTL常面临挑战：可行的任务分组数量呈指数级增长，使得选择最佳分组变得困难；同时，某些分组可能因任务间的负向干扰而导致性能下降。此外，现有解决方案严重受限于可扩展性问题，限制了其实际应用。本文提出一种新颖的数据驱动方法，旨在解决上述挑战，并基于手工设计的特征（具体为数据图）提供可扩展且模块化的分类任务分组方案，其中数据图可捕获MTL训练过程中各分类任务的训练行为。我们通过实验验证了该方法的有效性，即使面对前所未有的大规模任务（多达100个任务）时依然表现良好。