Details

Autor(en) / Beteiligte

• Pranavan, Theivendiram
• Sim, Terence
• Li, Jianshu

Titel

Virtual Tasks but Real Gains: Improving Multi-Task Learning

Ist Teil von

• 2022 26th International Conference on Pattern Recognition (ICPR), 2022, p.4829-4836

Ort / Verlag

IEEE

Erscheinungsjahr

2022

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• In supervised multi-task learning, the choice of auxiliary tasks is usually decided manually. This immediately raises the issue of how to choose suitable tasks, which in turn requires the need to measure the similarity between tasks. In this paper, we propose a task-similarity metric that depends solely on the task labels, not on the machine learning models. We show that auxiliary tasks may be synthetically generated from the main tasks with any desired similarity. Labels for these virtual tasks are also generated. Finally, we show that learning these virtual tasks along with the main task leads to real performance gains.