Publication:
Relation prediction via graph neural network in heterogeneous information networks with missing type information

dc.contributor.advisor Cao, Xin en_US
dc.contributor.advisor Wang, Wei en_US
dc.contributor.author Zhang, Han en_US
dc.date.accessioned 2022-03-15T08:50:34Z
dc.date.available 2022-03-15T08:50:34Z
dc.date.issued 2021 en_US
dc.description.abstract Relation prediction is a fundamental task in network analysis which aims to predict the relationship between two nodes. Thus, this differes from the traditional link prediction problem predicting whether a link exists between a pair of nodes, which can be viewed as a binary classification task. However, in the heterogeneous information network (HIN) which contains multiple types of nodes and multiple relations between nodes, the relation prediction task is more challenging. In addition, the HIN might have missing relation types on some edges and missing node types on some nodes, which makes the problem even harder. In this work, we propose RPGNN, a novel relation prediction model based on the graph neural network (GNN) and multi-task learning to solve this problem. Existing GNN models for HIN representation learning usually focus on the node classification/clustering task. They require the type information of all edges and nodes and always learn a weight matrix for each type, thus requiring a large number of learning parameters on HINs with rich schema. In contrast, our model directly encodes and learns relations in HINs and avoids the requirement of type information during message passing in GNN. Hence, our model is more robust to the missing types for the relation prediction task on HINs. The experiments on real HINs show that our model can consistently achieve better performance than several state-of-the-art HIN representation learning methods. en_US
dc.identifier.uri http://hdl.handle.net/1959.4/71105
dc.language English
dc.language.iso EN en_US
dc.publisher UNSW, Sydney en_US
dc.rights CC BY-NC-ND 3.0 en_US
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/3.0/au/ en_US
dc.subject.other Graph neural network en_US
dc.subject.other Relation prediction en_US
dc.subject.other Heterogeneous information network en_US
dc.subject.other Graph representation learning en_US
dc.title Relation prediction via graph neural network in heterogeneous information networks with missing type information en_US
dc.type Thesis en_US
dcterms.accessRights open access
dcterms.rightsHolder Zhang, Han
dspace.entity.type Publication en_US
unsw.accessRights.uri https://purl.org/coar/access_right/c_abf2
unsw.date.embargo 2023-09-28 en_US
unsw.description.embargoNote Embargoed until 2023-09-28
unsw.identifier.doi https://doi.org/10.26190/unsworks/2352
unsw.relation.faculty Engineering
unsw.relation.originalPublicationAffiliation Zhang, Han, School of Computer Science and Engineering, Engineering, UNSW en_US
unsw.relation.originalPublicationAffiliation Cao, Xin, School of Computer Science and Engineering, Engineering, UNSW en_US
unsw.relation.originalPublicationAffiliation Wang, Wei, School of Computer Science and Engineering, Engineering, UNSW en_US
unsw.relation.school School of Computer Science and Engineering *
unsw.thesis.degreetype Masters Thesis en_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
public version.pdf
Size:
848.57 KB
Format:
application/pdf
Description:
Resource type