Multi-View Dynamic Heterogeneous Information Network Embedding

  title={Multi-View Dynamic Heterogeneous Information Network Embedding},
  author={Zhenghao Zhang and Jianbin Huang and Qinglin Tan},
  journal={Comput. J.},
Most existing heterogeneous information network (HIN) embedding methods focus on static environments while neglecting the evolving characteristic of real-world networks. Although several dynamic embedding methods have been proposed, they are merely designed for homogeneous networks and cannot be directly applied in heterogeneous environments. To tackle above challenges, we propose a novel framework for incorporating temporal information into HIN embedding, named multi-view dynamic HIN… 

Fast Community Detection in Dynamic and Heterogeneous Networks

Under this framework, a fast community detection method called DHNet is developed that can estimate the community label as well as the number of communities, and it is shown that the identified label is consistent under a time-varying heterogeneous stochastic block model with a temporal correlation structure and edge sparsity.

HTGN-BTW: Heterogeneous Temporal Graph Network with Bi-Time-Window Training Strategy for Temporal Link Prediction

This work proposes a generic model, i.e., Heterogeneous Temporal Graph Network (HTGN), to solve such temporal link prediction task with the unfixed time intervals and the diverse link types, which can adapt to the heterogeneity of links and the prediction within an arbitrary given time period.



Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN

A novel dynamic heterogeneous network embedding method, termed as DyHATR, which uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns is proposed.

Heterogeneous Information Network Embedding for Recommendation

A novel heterogeneous network embedding based approach for HIN based recommendation, called HERec is proposed, which shows the capability of the HERec model for the cold-start problem, and reveals that the transformed embedding information from HINs can improve the recommendation performance.

Relationship Prediction in Dynamic Heterogeneous Information Networks

This work proposes a technique that leverages a combination of latent and topological features to predict a target relationship between two nodes in a dynamic heterogeneous information network, and effectively combines meta path-based topology features and inferred latent features that incorporate temporal network changes when making link predictions.

MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding

A new embedding learning algorithm is proposed, namely MetaGraph2Vec, which uses metagraph to guide the generation of random walks and to learn latent embeddings of multi-typed HIN nodes, able to outperform the state-of-the-art baselines in various heterogeneous network mining tasks such as node classification, node clustering, and similarity search.

Attributed Network Embedding for Learning in a Dynamic Environment

DANE first provides an offline method for a consensus embedding and then leverages matrix perturbation theory to maintain the freshness of the end embedding results in an online manner, and performs extensive experiments to corroborate the effectiveness and efficiency of the proposed framework.

Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks

This paper re-examine similarity search in HINs and proposes a novel embedding-based framework, ESim, that accepts user-defined meta-paths as guidance to learn vertex vectors in a user-preferred embedding space to explore network structure-embedded similarity.

HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning

Empirical results show that HIN2Vec soundly outperforms the state-of-the-art representation learning models for network data, including DeepWalk, LINE, node2vec, PTE, HINE and ESim, by 6.6% to 23.8% of $micro$-$f_1$ in multi-label node classification and 5% to 70.8%, in link prediction.

Dynamic Network Embedding by Modeling Triadic Closure Process

This paper presents a novel representation learning approach, DynamicTriad, to preserve both structural information and evolution patterns of a given network, and demonstrates that, compared with several state-of-the-art techniques, this approach achieves substantial gains in several application scenarios.

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects.

LINE: Large-scale Information Network Embedding

A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.