A General Framework for Content-enhanced Network Representation Learning
Explore this paper's citation graph
Summary
This paper proposes content-enhanced network embedding (CENE), which is capable of jointly leveraging the network structure and the content information, and shows that its models outperform all existing network embeddedding methods, demonstrating the merits of content information and joint learning.
- Type
- preprint
- Published
- 2016-10-10
- Cited by
- 93
- References
- 44
- Access
- Open access
- OpenAlex
- https://openalex.org/W2530041791
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14679478
Keywords
Computer science, Embedding, Node (physics), Representation (politics), Content (measure theory)
References
- Efficient Estimation of Word Representations in Vector Space
- Comprehend DeepWalk as Matrix Factorization
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
- LINE: Large-scale Information Network Embedding
- Composition in Distributional Models of Semantics
- Personalized entity recommendation: a heterogeneous information network approach
- ArnetMiner: extraction and mining of academic social networks
- Nonlinear dimensionality reduction by locally linear embedding.
- Long Short-Term Memory
- Latent Space Approaches to Social Network Analysis
- Modern Multidimensional Scaling: Theory and Applications
- GraRep: Learning Graph Representations with Global Structural Information
- A Convolutional Neural Network for Modelling Sentences
- Distributed Representations of Sentences and Documents
- Bidirectional recurrent neural networks
- PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
- Multi-Label Classification: An Overview
- Grounded Compositional Semantics for Finding and Describing Images with Sentences
- Distributed Representations of Words and Phrases and their Compositionality
- Collective Classification in Network Data
Cited by
- Deep Gaussian Embedding of Attributed Graphs: Unsupervised Inductive Learning via Ranking
- CANE: Context-Aware Network Embedding for Relation Modeling
- Network Embedding via a Bi-Mode and Deep Neural Network Model
- High-Order Proximity Preserved Embedding for Dynamic Networks
- Ontology Evaluation with Path-based Text-aware Entropy Computation
- Diffusion Maps for Textual Network Embedding
- Incorporating label and attribute information for enhanced network representation learning
- Content to Node: Self-Translation Network Embedding
- A Tutorial on Network Embeddings
- A Brief Review of Network Embedding
- Automatic Non-Taxonomic Relation Extraction from Big Data in Smart City
- Edge Content Enhanced Network Embedding
- TNERec: Topic-Aware Network Embedding for Scientific Collaborator Recommendation
- SHNE: Representation Learning for Semantic-Associated Heterogeneous Networks
- A United Approach to Learning Sparse Attributed Network Embedding
- Tag2Vec: Learning Tag Representations in Tag Networks
- Mobile app recommendations using deep learning and big data
- Network Embedding with Deep Metric Learning
- Multi-Path Relationship Preserved Social Network Embedding
- Multi-View Network Representation Learning Algorithm Research
Related papers
- Embedding as a modeling problem
- Analysis on the co-movement effect between sectoral linkage and economic growth of agriculture in Fujian Province based on input-output model
- FDI Technology Spillovers Effects Based on Backward Linkage in Liaoning Province
- A solution to the reversible embedding problem for finite Markov chains
- Design of Large Deployable Networks Constructed by Myard Linkages
- An Extended Myard Linkage and its Derived 6R Linkage
- A National Linkage Program for Technological Innovation