Compositional Network Embedding

• Main Authors: Lyu, Tianshu, Sun, Fei, Jiang, Peng, Ou, Wenwu, Zhang, Yan
• Format: Journal Article
• Language: English
• Published: 17-04-2019
• Subjects: Computer Science - Learning; Computer Science - Social and Information Networks; Statistics - Machine Learning
• DOI: 10.48550/arxiv.1904.08157

Network embedding has proved extremely useful in a variety of network
analysis tasks such as node classification, link prediction, and network
visualization. Almost all the existing network embedding methods learn to map
the node IDs to their corresponding node embeddings. This design principle,
however, hinders the existing methods from being applied in real cases. Node ID
is not generalizable and, thus, the existing methods have to pay great effort
in cold-start problem. The heterogeneous network usually requires extra work to
encode node types, as node type is not able to be identified by node ID. Node
ID carries rare information, resulting in the criticism that the existing
methods are not robust to noise.
To address this issue, we introduce Compositional Network Embedding, a
general inductive network representation learning framework that generates node
embeddings by combining node features based on the principle of
compositionally. Instead of directly optimizing an embedding lookup based on
arbitrary node IDs, we learn a composition function that infers node embeddings
by combining the corresponding node attribute embeddings through a graph-based
loss. For evaluation, we conduct the experiments on link prediction under four
different settings. The results verified the effectiveness and generalization
ability of compositional network embeddings, especially on unseen nodes.