Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.15328 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908365766000640 |
|---|---|
| author | Wang, Chenguang Pan, Xuanhao Yu, Tianshu |
| author_facet | Wang, Chenguang Pan, Xuanhao Yu, Tianshu |
| contents | Multi-task learning (MTL) aims to leverage shared information among tasks to improve learning efficiency and accuracy. However, MTL often struggles to effectively manage positive and negative transfer between tasks, which can hinder performance improvements. Task grouping addresses this challenge by organizing tasks into meaningful clusters, maximizing beneficial transfer while minimizing detrimental interactions. This paper introduces a principled approach to task grouping in MTL, advancing beyond existing methods by addressing key theoretical and practical limitations. Unlike prior studies, our method offers a theoretically grounded approach that does not depend on restrictive assumptions for constructing transfer gains. We also present a flexible mathematical programming formulation that accommodates a wide range of resource constraints, thereby enhancing its versatility. Experimental results across diverse domains, including computer vision datasets, combinatorial optimization benchmarks, and time series tasks, demonstrate the superiority of our method over extensive baselines, thereby validating its effectiveness and general applicability in MTL without sacrificing efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15328 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Principled Task Grouping for Multi-Task Learning Wang, Chenguang Pan, Xuanhao Yu, Tianshu Machine Learning Multi-task learning (MTL) aims to leverage shared information among tasks to improve learning efficiency and accuracy. However, MTL often struggles to effectively manage positive and negative transfer between tasks, which can hinder performance improvements. Task grouping addresses this challenge by organizing tasks into meaningful clusters, maximizing beneficial transfer while minimizing detrimental interactions. This paper introduces a principled approach to task grouping in MTL, advancing beyond existing methods by addressing key theoretical and practical limitations. Unlike prior studies, our method offers a theoretically grounded approach that does not depend on restrictive assumptions for constructing transfer gains. We also present a flexible mathematical programming formulation that accommodates a wide range of resource constraints, thereby enhancing its versatility. Experimental results across diverse domains, including computer vision datasets, combinatorial optimization benchmarks, and time series tasks, demonstrate the superiority of our method over extensive baselines, thereby validating its effectiveness and general applicability in MTL without sacrificing efficiency. |
| title | Towards Principled Task Grouping for Multi-Task Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.15328 |