Convolutional Hypercomplex Embeddings for Link Prediction

C. Demir, D. Moussallem, S. Heindorf, A.-C. Ngonga Ngomo, in: The 13th Asian Conference on Machine Learning, ACML 2021, 2021.

Conference Paper | English
Abstract
Knowledge graph embedding research has mainly focused on the two smallest normed division algebras, $\mathbb{R}$ and $\mathbb{C}$. 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.
Publishing Year
Proceedings Title
The 13th Asian Conference on Machine Learning, ACML 2021
LibreCat-ID

Cite this

Demir C, Moussallem D, Heindorf S, Ngonga Ngomo A-C. Convolutional Hypercomplex Embeddings for Link Prediction. In: The 13th Asian Conference on Machine Learning, ACML 2021. ; 2021.
Demir, C., Moussallem, D., Heindorf, S., & Ngonga Ngomo, A.-C. (2021). Convolutional Hypercomplex Embeddings for Link Prediction. The 13th Asian Conference on Machine Learning, ACML 2021.
@inproceedings{Demir_Moussallem_Heindorf_Ngonga Ngomo_2021, title={Convolutional Hypercomplex Embeddings for Link Prediction}, booktitle={The 13th Asian Conference on Machine Learning, ACML 2021}, author={Demir, Caglar and Moussallem, Diego and Heindorf, Stefan and Ngonga Ngomo, Axel-Cyrille}, year={2021} }
Demir, Caglar, Diego Moussallem, Stefan Heindorf, and Axel-Cyrille Ngonga Ngomo. “Convolutional Hypercomplex Embeddings for Link Prediction.” In The 13th Asian Conference on Machine Learning, ACML 2021, 2021.
C. Demir, D. Moussallem, S. Heindorf, and A.-C. Ngonga Ngomo, “Convolutional Hypercomplex Embeddings for Link Prediction,” 2021.
Demir, Caglar, et al. “Convolutional Hypercomplex Embeddings for Link Prediction.” The 13th Asian Conference on Machine Learning, ACML 2021, 2021.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Sources

arXiv 2106.15230

Search this title in

Google Scholar