Low Resource Quadratic Forms for Knowledge Graph Embeddings

Zachary Zhou, Jeffery Kline, Devin Conathan, Glenn Fung


Abstract
We address the problem of link prediction between entities and relations of knowledge graphs. State of the art techniques that address this problem, while increasingly accurate, are computationally intensive. In this paper we cast link prediction as a sparse convex program whose solution defines a quadratic form that is used as a ranking function. The structure of our convex program is such that standard support vector machine software packages, which are numerically robust and efficient, can solve it. We show that on benchmark data sets, our model’s performance is competitive with state of the art models, but training times can be reduced by a factor of 40 using only CPU-based (and not GPU-accelerated) computing resources. This approach may be suitable for applications where balancing the demands of graph completion performance against computational efficiency is a desirable trade-off.
Anthology ID:
2021.sustainlp-1.1
Volume:
Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing
Month:
November
Year:
2021
Address:
Virtual
Venue:
sustainlp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–10
Language:
URL:
https://aclanthology.org/2021.sustainlp-1.1
DOI:
10.18653/v1/2021.sustainlp-1.1
Bibkey:
Cite (ACL):
Zachary Zhou, Jeffery Kline, Devin Conathan, and Glenn Fung. 2021. Low Resource Quadratic Forms for Knowledge Graph Embeddings. In Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing, pages 1–10, Virtual. Association for Computational Linguistics.
Cite (Informal):
Low Resource Quadratic Forms for Knowledge Graph Embeddings (Zhou et al., sustainlp 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sustainlp-1.1.pdf
Software:
 2021.sustainlp-1.1.Software.zip
Video:
 https://aclanthology.org/2021.sustainlp-1.1.mp4