{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T20:38:23Z","timestamp":1758400703913},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Task Relation Discovery (TRD), i.e., reveal the relation of tasks, has notable value: it is the key concept underlying Multi-task Learning (MTL) and provides a principled way for identifying redundancies across tasks. However, task relation is usually specifically determined by data scientist resulting in the additional human effort for TRD, while transfer based on brute-force methods or mere training samples may cause negative effects which degrade the learning performance. To avoid negative transfer in an automatic manner, our idea is to leverage commonly available context attributes in nowadays systems, i.e., the metadata. In this paper, we, for the first time, introduce metadata into TRD for MTL and propose a novel Metadata Clustering method, which jointly uses historical samples and additional metadata to automatically exploit the true relatedness. It also avoids the negative transfer by identifying reusable samples between related tasks. Experimental results on five real-world datasets demonstrate that the proposed method is effective for MTL with TRD, and particularly useful in complicated systems with diverse metadata but insufficient data samples. In general, this study helps in automatic relation discovery among partially related tasks and sheds new light on the development of TRD in MTL through the use of metadata as apriori information.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/615","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"4426-4432","source":"Crossref","is-referenced-by-count":15,"title":["Metadata-driven Task Relation Discovery for Multi-task Learning"],"prefix":"10.24963","author":[{"given":"Zimu","family":"Zheng","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"},{"name":"Huawei Technologies Co.Ltd."}]},{"given":"Yuqi","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"},{"name":"Fujian Nebula Big Data Application Service Co., Ltd."}]},{"given":"Quanyu","family":"Dai","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}]},{"given":"Huadi","family":"Zheng","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}]},{"given":"Dan","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2019","name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","start":{"date-parts":[[2019,8,10]]},"theme":"Artificial Intelligence","location":"Macao, China","end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:50:29Z","timestamp":1564300229000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/615"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/615","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}