Show simple item record

dc.contributor.authorAkujuobi, Uchenna Thankgod
dc.contributor.authorYufei, Han
dc.contributor.authorZhang, Qiannan
dc.contributor.authorZhang, Xiangliang
dc.date.accessioned2019-12-17T13:51:26Z
dc.date.available2019-12-17T13:51:26Z
dc.date.issued2020-01-31
dc.identifier.citationAkujuobi, U., Yufei, H., Zhang, Q., & Zhang, X. (2019). Collaborative Graph Walk for Semi-Supervised Multi-label Node Classification. 2019 IEEE International Conference on Data Mining (ICDM). doi:10.1109/icdm.2019.00010
dc.identifier.doi10.1109/ICDM.2019.00010
dc.identifier.urihttp://hdl.handle.net/10754/660643
dc.description.abstractIn this work, we study semi-supervised multi-label node classification problem in attributed graphs. Classic solutions to multi-label node classification follow two steps, first learn node embedding and then build a node classifier on the learned embedding. To improve the discriminating power of the node embedding, we propose a novel collaborative graph walk, named Multi-Label-Graph-Walk, to finely tune node representations with the available label assignments in attributed graphs via reinforcement learning. The proposed method formulates the multi-label node classification task as simultaneous graph walks conducted by multiple label-specific agents. Furthermore, policies of the label-wise graph walks are learned in a cooperative way to capture first the predictive relation between node labels and structural attributes of graphs; and second, the correlation among the multiple label-specific classification tasks. A comprehensive experimental study demonstrates that the proposed method can achieve significantly better multi-label classification performance than the state-of-the-art approaches and conduct more efficient graph exploration.
dc.description.sponsorshipThis work is supported by the King Abdullah University of Science and Technology (KAUST), Saudi Arabia
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/8970680/
dc.rightsArchived with thanks to IEEE
dc.titleCollaborative graph walk for semi-supervised multi-label node classification
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentKing Abdullah University of Science and Technology (KAUST), Saudi Arabia
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.date2019-11-08 to 2019-11-11
dc.conference.name19th IEEE International Conference on Data Mining, ICDM 2019
dc.conference.locationBeijing, CHN
dc.eprint.versionPre-print
dc.contributor.institutionSymantec, France
dc.identifier.arxivid1910.09706
kaust.personAkujuobi, Uchenna Thankgod
kaust.personYufei, Han
kaust.personZhang, Qiannan
kaust.personZhang, Xiangliang
refterms.dateFOA2019-12-17T13:51:59Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
953.2Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record