Show simple item record

dc.contributor.authorChen, Xia
dc.contributor.authorYu, Guoxian
dc.contributor.authorWang, Jun
dc.contributor.authorDomeniconi, Carlotta
dc.contributor.authorLi, Zhao
dc.contributor.authorZhang, Xiangliang
dc.date.accessioned2019-12-17T13:41:35Z
dc.date.available2019-12-17T13:41:35Z
dc.date.issued2019-07-28
dc.identifier.citationChen, X., Yu, G., Wang, J., Domeniconi, C., Li, Z., & Zhang, X. (2019). ActiveHNE: Active Heterogeneous Network Embedding. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. doi:10.24963/ijcai.2019/294
dc.identifier.doi10.24963/ijcai.2019/294
dc.identifier.urihttp://hdl.handle.net/10754/660642
dc.description.abstractHeterogeneous network embedding (HNE) is a challenging task due to the diverse node types and/or diverse relationships between nodes. Existing HNE methods are typically unsupervised. To maximize the profit of utilizing the rare and valuable supervised information in HNEs, we develop a novel Active Heterogeneous Network Embedding (ActiveHNE) framework, which includes two components: Discriminative Heterogeneous Network Embedding (DHNE) and Active Query in Heterogeneous Networks (AQHN). In DHNE, we introduce a novel semi-supervised heterogeneous network embedding method based on graph convolutional neural networks. In AQHN, we first introduce three active selection strategies based on uncertainty and representativeness, and then derive a batch selection method that assembles these strategies using a multi-armed bandit mechanism. ActiveHNE aims at improving the performance of HNE by feeding the most valuable supervision obtained by AQHN into DHNE. Experiments on public datasets demonstrate the effectiveness of ActiveHNE and its advantage on reducing the query cost.
dc.description.sponsorshipThis work is supported by NSFC (61872300 and 61873214), Fundamental Research Funds for the Central Universities (XDJK2019B024), NSF of CQ CSTC (cstc2018jcyjAX0228 and cstc2016jcyjA0351), King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
dc.publisherInternational Joint Conferences on Artificial Intelligence Organization
dc.relation.urlhttps://www.ijcai.org/proceedings/2019/294
dc.rightsArchived with thanks to International Joint Conferences on Artificial Intelligence Organization
dc.titleActivehne: Active heterogeneous network embedding
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentMachine Intelligence & kNowledge Engineering Lab
dc.conference.date2019-08-10 to 2019-08-16
dc.conference.name28th International Joint Conference on Artificial Intelligence, IJCAI 2019
dc.conference.locationMacao, CHN
dc.eprint.versionPre-print
dc.contributor.institutionCollege of Computer and Information Sciences, Southwest University, Chongqing, China
dc.contributor.institutionDepartment of Computer Science, George Mason University, VA, USA
dc.contributor.institutionAlibaba Group, Hangzhou, China
dc.identifier.arxivid1905.05659
kaust.personYu, Guoxian
kaust.personZhang, Xiangliang
refterms.dateFOA2019-12-17T13:42:20Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
480.4Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record