metapath2vec: Scalable Representation Learning for Heterogeneous Networks
Explore this paper's citation graph
Summary
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.
- Type
- article
- Published
- 2017-08-04
- Cited by
- 2,506
- References
- 40
- OpenAlex
- https://openalex.org/W2743104969
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3919301
Keywords
Computer science, Node (physics), Scalability, Embedding, Heterogeneous network
References
- PathSim
- word2vec Parameter Learning Explained
- Efficient Estimation of Word Representations in Vector Space
- LINE: Large-scale Information Network Embedding
- Mining Heterogeneous Information Networks: Principles and Methodologies
- Factorization meets the neighborhood: a multifaceted collaborative filtering model
- Panther: Fast Top-k Similarity Search on Large Networks
- ArnetMiner: extraction and mining of academic social networks
- Relational learning via latent social dimensions
- RolX: structural role extraction & mining in large graphs
- Heterogeneous Network Embedding via Deep Architectures
- Latent Space Approaches to Social Network Analysis
- Integrating meta-path selection with user-guided object clustering in heterogeneous information networks
- CoupledLP: Link Prediction in Coupled Networks
- word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
- Graph Embedding and Extensions: A General Framework for Dimensionality Reduction
- Distributed large-scale natural graph factorization
- Recommender systems with social regularization
- PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
- Ranking-based clustering of heterogeneous information networks with star network schema
Cited by
- Node classification over bipartite graphs through projection
- From homogeneous to heterogeneous network alignment via colored graphlets
- A Framework for Generalizing Graph-based Representation Learning Methods
- RUM: network Representation learning throUgh Multi-level structural information preservation
- Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
- Preserving Local and Global Information for Network Embedding
- GraphGAN: Graph Representation Learning with Generative Adversarial Nets
- Motif-based Convolutional Neural Network on Graphs
- Graph Clustering with Dynamic Embedding
- Biological Systems as Heterogeneous Information Networks: A Mini-review and Perspectives
- TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism
- Learning with Heterogeneous Side Information Fusion for Recommender Systems
- Multi-task network embedding
- mvn2vec: Preservation and Collaboration in Multi-View Network Embedding
- HONE: Higher-Order Network Embeddings
- Learning Role-based Graph Embeddings
- Fast Node Embeddings: Learning Ego-Centric Representations
- Multi-Dimensional Network Embedding with Hierarchical Structure
- Dynamic Network Embedding by Modeling Triadic Closure Process
- On Exploring Semantic Meanings of Links for Embedding Social Networks
Related papers
- Embedding as a modeling problem
- Mobile Small Cells for Further Enhanced 5G Heterogeneous Networks
- Heterogeneous Networks in theory and practice
- On performance of HetNet with coexisting small cell technology
- A reversible and multiple-layer embedding strategy with high capacity
- Scalability Issues of Blockchain Technology
- Node similarity distribution of complex networks and its application in link prediction
- A Localization Algorithm Based on Geographical Similarity of RSSI in Wireless Sensor Networks