Multi-view Dynamic Heterogeneous Information Network Embedding
نویسندگان
چکیده
Abstract Most existing heterogeneous information network (HIN) embedding methods focus on static environments while neglecting the evolving characteristic of real-world networks. Although several dynamic have been proposed, they are merely designed for homogeneous networks and cannot be directly applied in environments. To tackle above challenges, we propose a novel framework incorporating temporal into HIN embedding, named multi-view (MDHNE), which can efficiently preserve evolution patterns implicit relationships from different views updating node vectors over time. We first transform to series corresponding views. Then our proposed MDHNE applies recurrent neural (RNN) incorporate pattern complex structure semantic between nodes latent spaces, thus multiple learned updated when evolves Moreover, come up with an attention-based fusion mechanism, automatically infer weights by minimizing objective function specific mining tasks. Extensive experiments clearly demonstrate that model outperforms state-of-the-art baselines three datasets
منابع مشابه
HINE: Heterogeneous Information Network Embedding
Network embedding has shown its effectiveness in embedding homogeneous networks. Compared with homogeneous networks, heterogeneous information networks (HINs) contain semantic information from multi-typed entities and relations, and are shown to be a more effective model for real world data. The existing network embedding methods fail to explicitly capture the semantics in HINs. In this paper, ...
متن کاملHeterogeneous Information Network Embedding for Recommendation
Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in recommender systems, called HIN based recommendation. It is challenging to develop effective methods for HIN based recommendation in both extraction and exploitation of the information from HINs. Most of HIN based recommenda...
متن کاملGraph Embedding with Rich Information through Bipartite Heterogeneous Network
Graph embedding has attracted increasing attention due to its critical application in social network analysis. Most existing algorithms for graph embedding only rely on the typology information and fail to use the copious information in nodes as well as edges. As a result, their performance for many tasks may not be satisfactory. In this paper, we proposed a novel and general framework of repre...
متن کاملHeterogeneous Information Network Embedding for Meta Path based Proximity
A network embedding is a representation of a large graph in a lowdimensional space, where vertices are modeled as vectors. The objective of a good embedding is to preserve the proximity (i.e., similarity) between vertices in the original graph. This way, typical search and mining methods (e.g., similarity search, kNN retrieval, classification, clustering) can be applied in the embedded space wi...
متن کاملMulti-View Clustering for Mining Heterogeneous Social Network Data∗
Uncovering community structure is a core challenge in social network analysis. This is a significant challenge for large networks where there is a single type of relation in the network (e.g. friend or knows). In practice there may be other types of relation, for instance demographic or geographic information, that also reveal network structure. Uncovering structure in such multi-relational net...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Computer Journal
سال: 2021
ISSN: ['0010-4620', '1460-2067']
DOI: https://doi.org/10.1093/comjnl/bxab041