Skip navigation

MixSp: a framework for embedding heterogeneous information networks with arbitrary number of node and edge types

MixSp: a framework for embedding heterogeneous information networks with arbitrary number of node and edge types

Xu, Linchuan, Wang, Jing, He, Lifang, Cao, Jiannong, Wei, Xiaokai, Yu, Phillip S. and Yamanishi, Kenji (2019) MixSp: a framework for embedding heterogeneous information networks with arbitrary number of node and edge types. IEEE Transactions on Knowledge and Data Engineering, 33 (6). pp. 2627-2639. ISSN 1041-4347 (Print), 1558-2191 (Online) (doi:https://doi.org/10.1109/TKDE.2019.2955945)

Full text not available from this repository. (Request a copy)

Abstract

Heterogeneous information network (HIN) embedding is to encode network structure into node representations with the heterogeneous semantics of different node and edge types considered. However, since each HIN may have a unique nature, e.g., a unique set of node and edge types, a model designed for one type of networks may not be applicable to or effective on another type. In this paper, we thus attempt to propose a framework for HINs with arbitrary number of node and edge types. The proposed framework constructs a novel mixture-split representation of an HIN, and hence is named as MixSp. The mixture sub-representation and the split sub-representation serve as two different views of the network. Compared with existing models which only learn from the original view, MixSp thus may exploit more comprehensive information. Node representations in each view are learned by embedding the respective network structure. Moreover, the node representations are further refined through cross-view co-regularization. The framework is instantiated in three models which differ from each other in the co-regularization. Extensive experiments on three real-world datasets show MixSp outperforms several recent models in both node classification and link prediction tasks even though MixSp is not designed for a particular type of HINs.

Item Type: Article
Uncontrolled Keywords: network embedding, heterogeneous information networks, multi-label classification, link prediction
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / Department / Research Group: Faculty of Liberal Arts & Sciences
Faculty of Liberal Arts & Sciences > School of Computing & Mathematical Sciences (CAM)
Last Modified: 31 Aug 2021 14:42
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
Selected for GREAT 2019: None
Selected for REF2021: None
URI: http://gala.gre.ac.uk/id/eprint/30484

Actions (login required)

View Item View Item