HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding

@article{He2019HeteSpaceyWalkAH,
  title={HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding},
  author={Yu He and Yangqiu Song and Jianxin Li and Cheng Ji and Jian Peng and Hao Peng},
  journal={Proceedings of the 28th ACM International Conference on Information and Knowledge Management},
  year={2019}
}
  • Yu He, Yangqiu Song, Hao Peng
  • Published 7 September 2019
  • Computer Science
  • Proceedings of the 28th ACM International Conference on Information and Knowledge Management
Heterogeneous information network (HIN) embedding has gained increasing interests recently. However, the current way of random-walk based HIN embedding methods have paid few attention to the higher-order Markov chain nature of meta-path guided random walks, especially to the stationarity issue. In this paper, we systematically formalize the meta-path guided random walk as a higher-order Markov chain process,and present a heterogeneous personalized spacey random walk to efficiently and… 

Figures and Tables from this paper

SchemaWalk: Schema Aware Random Walks for Heterogeneous Graph Embedding

TLDR
This work utilizes network schema as a unique blueprint of HIN, and proposes SchemaWalk, a random walk to uniformly sample all edge types within the network schema, and identifies the starvation phenomenon which induces random walkers on HINs to under- or over-sample certain edge types.

Heterogeneous Network Embedding Based on Random Walks of Type and Inner Constraint

TLDR
A novel model HNE-RWTIC (Heterogeneous Network Embedding Based on Random Walks of Type and Inner Constraint), which can realize the random walks based on meta-paths, the flexibility of the walks, and can sample the node types and nodes uniformly in proportion is proposed.

RWNE: A Scalable Random-Walk based Network Embedding Framework with Personalized Higher-order Proximity Preserved

TLDR
This paper presents a general scalable random-walk based network embedding framework, in which random walk is explicitly incorporated into a sound objective designed theoretically to preserve arbitrary higher-order proximity, and introduces the random walk with restart process into the framework to naturally and effectively achieve personalized-weighted preservation of proximities of different orders.

Het-node2vec: second order random walk sampling for heterogeneous multigraphs embedding

TLDR
A set of algorithms ( Het-node2vec ) are introduced that extend the original node2vec node-neighborhood sampling method to heterogeneous multigraphs, i.e. networks characterized by multiple types of nodes and edges, to boost unsupervised and supervised learning on heterogeneous graphs.

Recommendation Model Based on a Heterogeneous Personalized Spacey Embedding Method

TLDR
A meta-path-based heterogeneous personalized spacey random walk for recommendation, which is used to generate a meaningful sequence of nodes for network representation learning, and the learned embedded vectors are transformed by a nonlinear fusion function and integrated into a matrix decomposition model for rating prediction.

CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling

TLDR
This work addresses a limitation of the random-walk-based HIN embedding that has not been emphasized before, and confirms that CoarSAS catches richer information of the network compared with that through other methods.

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources

TLDR
This survey presents several widely deployed systems that have demonstrated the success of HG embedding techniques in resolving real-world application problems with broader impacts and summarizes the open-source code, existing graph learning platforms and benchmark datasets.

FallbackWalk: A Random Walk Based Fallback for Heterogeneous Information Network

TLDR
A graph embedding model based on fallback strategy (FallbackWalk) is proposed, which takes into account the differences of nodes in the information network, and make more use of neighborhood nodes by random walk strategy based onfallback, and the Skip-gram model is used to train and get the vector representation of nodes.

Collaborative Knowledge Distillation for Heterogeneous Information Network Embedding

TLDR
This work makes the first attempt to explicitly model the correlation among meta-paths by proposing Collaborative Knowledge Distillation for Heterogeneous Information Network Embedding (CKD), and model the knowledge in each meta- path with two different granularities: regional knowledge and global knowledge.

Neural PathSim for Inductive Similarity Search in Heterogeneous Information Networks

TLDR
This paper designs an encoder-decoder based framework, NeuPath, where the algorithmic structure of PathSim is considered, and demonstrates that Neu path performs better than state-of-the-art baselines in the PathSim approximation task and similarity search task.

References

SHOWING 1-10 OF 43 REFERENCES

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

TLDR
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.

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

TLDR
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.

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

TLDR
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.

MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding

TLDR
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.

Heterogeneous Information Network Embedding for Recommendation

TLDR
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.

Integrating meta-path selection with user-guided object clustering in heterogeneous information networks

TLDR
This work proposes to integrate meta-path selection with user-guided clustering to cluster objects in networks, where a user first provides a small set of object seeds for each cluster as guidance, and an effective and efficient iterative algorithm, PathSelClus, is proposed to learn the model.

CARL: Content-Aware Representation Learning for Heterogeneous Networks

TLDR
Extensive experiments demonstrate that CARL outperforms state-of-the-art baselines in various heterogeneous network mining tasks, such as link prediction, document retrieval, node recommendation and relevance search, and the effectiveness of the CARL's online update module through a category visualization study.

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

TLDR
This work proposesMEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively, which uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta-paths between nodes simultaneously, and then leverages tensor decomposition method to perform node embedding.

LINE: Large-scale Information Network Embedding

TLDR
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.

MultiAspectForensics: mining large heterogeneous networks using tensor

TLDR
This work introduces MultiAspectForensics, a novel tool to automatically detect and visualise bursts of specific sub-graph patterns within a local community of nodes as anomalies in a heterogeneous network, leveraging scalable tensor analysis methods.