Timezone: »

 
Poster
Expanding Holographic Embeddings for Knowledge Completion
Yexiang Xue · Yang Yuan · Zhitian Xu · Ashish Sabharwal

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #100
in Tue Poster Session A »

Neural models operating over structured spaces such as knowledge graphs require a continuous embedding of the discrete elements of this space (such as entities) as well as the relationships between them. Relational embeddings with high expressivity, however, have high model complexity, making them computationally difficult to train. We propose a new family of embeddings for knowledge graphs that interpolate between a method with high model complexity and one, namely Holographic embeddings (HolE), with low dimensionality and high training efficiency. This interpolation, termed HolEx, is achieved by concatenating several linearly perturbed copies of original HolE. We formally characterize the number of perturbed copies needed to provably recover the full entity-entity or entity-relation interaction matrix, leveraging ideas from Haar wavelets and compressed sensing. In practice, using just a handful of Haar-based or random perturbation vectors results in a much stronger knowledge completion system. On the Freebase FB15K dataset, HolEx outperforms originally reported HolE by 14.7\% on the HITS@10 metric, and the current path-based state-of-the-art method, PTransE, by 4\% (absolute).

Keywords: Embedding Approaches · Relational Learning · Matrix and Tensor Factorization

Author Information

Yexiang Xue (Purdue University)
Yang Yuan (Cornell University)
Zhitian Xu (Shanghai Jiaotong University)
Ashish Sabharwal (Allen Institute for AI)

More from the Same Authors