---
title: "Multi-Modal Bayesian Embeddings for Learning Social Knowledge Graphs"
authors:
  - "Zhilin Yang"
  - "Jie Tang"
  - "William W. Cohen"
doi: ""
url: "https://ijcai.org/proceedings/2016/326"
pdf: "https://ijcai.org/proceedings/2016/0326.pdf"
venue: "Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence"
year: 2016
pages: "2287-2292"
track: ""
keywords:
---

# Multi-Modal Bayesian Embeddings for Learning Social Knowledge Graphs

Zhilin Yang, Jie Tang, William W. Cohen

*Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence*, pages 2287-2292.

## 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.