Multi-Modal Bayesian Embeddings for Learning Social Knowledge Graphs

Abstract

We study the extent to which online social networks can be connected to open knowledge bases. The problem is referred to as learning social knowledge graphs. We propose a multi-modal Bayesian embedding model, GenVector, to learn latent topics that generate word and network embeddings. GenVector leverages large-scale unlabeled data with embeddings and represents data of two modalities---i.e., social network users and knowledge concepts---in a shared latent topic space. Experiments on three datasets show that the proposed method clearly outperforms state-of-the-art methods. We then deploy the method on AMiner, a large-scale online academic search system with a network of 38,049,189 researchers with a knowledge base with 35,415,011 concepts. Our method significantly decreases the error rate in an online A/B test with live users.

References in corpus (1)

• Word Representations via Gaussian Embedding

Cited by in corpus (4)

• Graph Embedding Techniques, Applications, and Performance: A Survey
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• A Tutorial on Network Embeddings
• Network representation learning systematic review: ancestors and current development state