Papers with Code 아카이브
Network Embedding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Network Embedding, also known as "Network Representation Learning", is a collective term for techniques for mapping graph nodes to vectors of real numbers in a multidimensional space. To be useful, a good embedding should preserve the structure of the graph. The vectors can then be used as input to various network and graph analysis tasks, such as link prediction
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation
Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling
PathRank: A Multi-Task Learning Framework to Rank Paths in Spatial Networks
Network Embedding: on Compression and Learning
Graph Representation Learning via Hard and Channel-Wise Attention Networks
Signed Graph Attention Networks
NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization
Dynamic Network Embeddings for Network Evolution Analysis
ANAE: Learning Node Context Representation for Attributed Network Embedding
DISCO: Influence Maximization Meets Network Embedding and Deep Learning
Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
Network Representation of Large-Scale Heterogeneous RNA Sequences with Integration of Diverse Multi-omics, Interactions, and Annotations Data
Embedding Biomedical Ontologies by Jointly Encoding Network Structure and Textual Node Descriptors
Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling
Improving Textual Network Embedding with Global Attention via Optimal Transport
Task-Guided Pair Embedding in Heterogeneous Network
DANE: Domain Adaptive Network Embedding
Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
Relation Structure-Aware Heterogeneous Information Network Embedding
ActiveHNE: Active Heterogeneous Network Embedding
Representation Learning for Attributed Multiplex Heterogeneous Network
ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions
Tag2Vec: Learning Tag Representations in Tag Networks
Compositional Network Embedding
Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks
Multimodal Deep Network Embedding with Integrated Structure and Attribute Information
Subgraph Networks with Application to Structural Feature Space Expansion
Efficient Inner Product Approximation in Hybrid Spaces
Multi-Hot Compact Network Embedding
GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
Global Vectors for Node Representations
Representation Learning for Recommender Systems with Application to the Scientific Literature
Deep Adversarial Network Alignment
Unsupervised Network Embedding for Graph Visualization, Clustering and Classification
Deep Node Ranking for Neuro-symbolic Structural Node Embedding and Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.