Logo image
Back
Repurposing Knowledge Graph Embeddings for Triple Representation via Weak Supervision
Conference proceeding   Open access

Repurposing Knowledge Graph Embeddings for Triple Representation via Weak Supervision

Yuan An
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings
01 Jan 2022
DOI: https://doi.org/10.1109/IDSTA55301.2022.9923036
url
https://doi.org/10.1109/IDSTA55301.2022.9923036View
Published, Version of Record (VoR)CC BY-NC-ND V4.0,  Open

Abstract

Clustering Embedding Graphical representations Knowledge representation Semantics
Conference Title: 2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA) Conference Start Date: 2022, Sept. 5 Conference End Date: 2022, Sept. 7 Conference Location: San Antonio, TX, USAThe majority of knowledge graph embedding techniques treat entities and predicates as separate embedding matrices, using aggregation functions to build a representation of the input triple. However, these aggregations are lossy, i.e. they do not capture the semantics of the original triples, such as information contained in the predicates. To combat these shortcomings, current methods learn triple embeddings from scratch without utilizing entity and predicate embeddings from pre-trained models. In this paper, we design a novel fine-tuning approach for learning triple embeddings by creating weak supervision signals from pre-trained knowledge graph embeddings. We develop a method for automatically sampling triples from a knowledge graph and estimating their pairwise similarities from pre-trained embedding models. These pairwise similarity scores are then fed to a Siamese-like neural architecture to fine-tune triple representations. We evaluate the proposed method on two widely studied knowledge graphs and show consistent improvement over other state-of-the-art triple embedding methods on triple classification and triple clustering tasks.

Metrics

21 Record Views
5 citations in Scopus

Details

Logo image