Show simple item record

dc.contributor.authorXiao, Lin
dc.contributor.authorZhang, Xiangliang
dc.contributor.authorJing, Liping
dc.contributor.authorHuang, Chi
dc.contributor.authorSong, Mingyang
dc.date.accessioned2021-09-20T07:04:58Z
dc.date.available2021-02-04T11:39:08Z
dc.date.available2021-09-20T07:04:58Z
dc.date.issued2021
dc.identifier.issn2374-3468
dc.identifier.issn2159-5399
dc.identifier.urihttp://hdl.handle.net/10754/667224
dc.description.abstractMulti-label text classification (MLTC) aims to annotate documents with the most relevant labels from a number of candidate labels. In real applications, the distribution of label frequency often exhibits a long tail, i.e., a few labels are associated with a large number of documents (a.k.a. head labels), while a large fraction of labels are associated with a small number of documents (a.k.a. tail labels). To address the challenge of insufficient training data on tail label classification, we propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to data-poor tail labels. The meta-knowledge is the mapping from few-shot network parameters to many-shot network parameters, which aims to promote the generalizability of tail classifiers. Extensive experimental results on three benchmark datasets demonstrate that HTTN consistently outperforms the state-of-the-art methods. The code and hyper-parameter settings are released for reproducibility(1).
dc.description.sponsorshipThis work was supported in part by the National Natural Science Foundation of China under Grant 61822601, 61773050, 61632004 and 61828302; The Beijing Natural Science Foundation under Grant Z180006; The National Key Research and Development Program of China under Grant 2020AAA0106800 and 2017YFC1703506; The Fundamental Research Funds for the Central Universities (2019JBZ110); And King Abdullah University of Science & Technology, under award number FCC/1/1976-19-01.en_US
dc.publisherarXiven_US
dc.relation.urlhttps://arxiv.org/pdf/2101.09704en_US
dc.rightsArchived with thanks to arXiv
dc.titleDoes Head Label Help for Long-Tailed Multi-Label Text Classification
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.conference.dateFEB 02-09, 2021
dc.conference.name35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence
dc.conference.locationELECTR NETWORK
dc.identifier.wosutWOS:000681269805088
dc.eprint.versionPost-print
dc.contributor.institutionBeijing Jiaotong Univ, Beijing Key Lab Traff Data Anal & Min, Beijing, Peoples R China.
dc.identifier.volume35
dc.identifier.pages14103-14111
dc.identifier.arxivid2101.09704
kaust.personZhang, Xiangliang
kaust.grant.numberFCC/1/1976-19-01
refterms.dateFOA2021-02-04T11:39:47Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
571.7Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record

VersionItemEditorDateSummary

*Selected version