Graph Embeddings

Large-scale Information Network Embedding

Introduced by Tang et al. in LINE: Large-scale Information Network Embedding

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

Source: Tang et al.

Image source: Tang et al.

Source: LINE: Large-scale Information Network Embedding


Paper Code Results Date Stars


Task Papers Share
Graph Embedding 3 27.27%
Link Prediction 2 18.18%
Node Classification 2 18.18%
Chatbot 1 9.09%
Decision Making 1 9.09%
Recommendation Systems 1 9.09%
Graph Sampling 1 9.09%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign