Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tasks, although these tasks are usually of a similar nature. In this work, we attempt to expand this range even further, by including heterogeneous tasks in a single learning procedure. To do so, we firstly formally define a multi-network model, identifying the necessary components and characteristics to allow different adaptations of said model depending on the tasks it is required to fulfill. Secondly, employing the formal definition as a starting point, we develop an illustrative model example consisting of three different tasks (classification, regression, and data sampling). The performance of this illustrative model is then analyzed, showing its capabilities. Motivated by the results of the analysis, we enumerate a set of open challenges and future research lines over which the full potential of the proposed model definition can be exploited.

中文翻译：

---

面向异构多任务学习的多网络模型的自动构建

正如现在所理解的，多任务学习包括使用一个模型来执行几个类似的任务。从对不同字母的手写字符进行分类到使用强化学习弄清楚如何玩多个 Atari 游戏，多任务模型已经能够扩大它们在不同任务中的性能范围，尽管这些任务通常具有相似的性质。在这项工作中，我们试图通过在单个学习过程中包含异构任务来进一步扩大这一范围。为此，我们首先正式定义一个多网络模型，确定必要的组件和特征，以允许根据需要完成的任务对所述模型进行不同的调整。其次，以正式定义为起点，我们开发了一个包含三个不同任务（分类、回归和数据采样）的说明性模型示例。然后分析此说明性模型的性能，显示其功能。受分析结果的启发，我们列举了一组开放的挑战和未来的研究路线，在这些挑战和未来的研究路线上，可以利用所提出的模型定义的全部潜力。