Generalized Graph Embedding Models

Qiao Liu, Xiaohui Yang, Rui Wan, Shouzhong Tu, Zufeng Wu

Abstract: Many types of relations in physical, biological, social and information systems can be modeled as homogeneous or heterogeneous concept graphs. Hence, learning from and with graph embeddings has drawn a great deal of research interest recently, but only ad hoc solutions have been obtained this far. In this paper, we conjecture that the one-shot supervised learning mechanism is a bottleneck in improving the performance of the graph embedding learning algorithms, and propose to extend this by introducing a multi-shot unsupervised learning framework. Empirical results on several real-world data set show that the proposed model consistently and significantly outperforms existing state-of-the-art approaches on knowledge base completion and graph based multi-label classification tasks.

TL;DR: Generalized Graph Embedding Models

Keywords: representation learning, knowledge graphs, relational inference, link prediction, multi-label classification, knowledge base completion

Data: [FB15k](https://paperswithcode.com/dataset/fb15k), [FB15k-237](https://paperswithcode.com/dataset/fb15k-237), [WN18](https://paperswithcode.com/dataset/wn18), [WN18RR](https://paperswithcode.com/dataset/wn18rr)