• Login
    View Item 
    •   Home
    • Research
    • Preprints
    • View Item
    •   Home
    • Research
    • Preprints
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    Does Head Label Help for Long-Tailed Multi-Label Text Classification

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Preprintfile1.pdf
    Size:
    571.7Kb
    Format:
    PDF
    Description:
    Pre-print
    Download
    Type
    Preprint
    Authors
    Xiao, Lin
    Zhang, Xiangliang cc
    Jing, Liping
    Huang, Chi
    Song, Mingyang
    KAUST Department
    Computer Science Program
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    KAUST Grant Number
    FCC/1/1976-19-01
    Date
    2021-01-24
    Permanent link to this record
    http://hdl.handle.net/10754/667224
    
    Metadata
    Show full item record
    Abstract
    Multi-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
    Sponsors
    This 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.
    Publisher
    arXiv
    arXiv
    2101.09704
    Additional Links
    https://arxiv.org/pdf/2101.09704
    Collections
    Preprints; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2021  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.