Convolutional Hypercomplex Embeddings for Link Prediction

by   Caglar Demir, et al.

Knowledge graph embedding research has mainly focused on the two smallest normed division algebras, ℝ and ℂ. Recent results suggest that trilinear products of quaternion-valued embeddings can be a more effective means to tackle link prediction. In addition, models based on convolutions on real-valued embeddings often yield state-of-the-art results for link prediction. In this paper, we investigate a composition of convolution operations with hypercomplex multiplications. We propose the four approaches QMult, OMult, ConvQ and ConvO to tackle the link prediction problem. QMult and OMult can be considered as quaternion and octonion extensions of previous state-of-the-art approaches, including DistMult and ComplEx. ConvQ and ConvO build upon QMult and OMult by including convolution operations in a way inspired by the residual learning framework. We evaluated our approaches on seven link prediction datasets including WN18RR, FB15K-237 and YAGO3-10. Experimental results suggest that the benefits of learning hypercomplex-valued vector representations become more apparent as the size and complexity of the knowledge graph grows. ConvO outperforms state-of-the-art approaches on FB15K-237 in MRR, Hit@1 and Hit@3, while QMult, OMult, ConvQ and ConvO outperform state-of-the-approaches on YAGO3-10 in all metrics. Results also suggest that link prediction performances can be further improved via prediction averaging. To foster reproducible research, we provide an open-source implementation of approaches, including training and evaluation scripts as well as pretrained models.


page 1

page 2

page 3

page 4


Convolutional Complex Knowledge Graph Embeddings

In this paper, we study the problem of learning continuous vector repres...

Out-of-Vocabulary Entities in Link Prediction

Knowledge graph embedding techniques are key to making knowledge graphs ...

Complex Embeddings for Simple Link Prediction

In statistical relational learning, the link prediction problem is key t...

Conditional Link Prediction of Category-Implicit Keypoint Detection

Keypoints of objects reflect their concise abstractions, while the corre...

InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions

Most existing knowledge graphs suffer from incompleteness, which can be ...

Link Prediction with Social Vector Clocks

State-of-the-art link prediction utilizes combinations of complex featur...

Runtime Performances Benchmark for Knowledge Graph Embedding Methods

This paper wants to focus on providing a characterization of the runtime...

Please sign up or login with your details

Forgot password? Click here to reset