Leveraging Static Models for Link Prediction in Temporal Knowledge Graphs
Authors:
- 1 November 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1034-1041
Abstract
Including temporal scopes of facts in knowledge graph embedding (KGE) presents significant opportunities for improving the resulting embeddings, and consequently for increased performance in downstream applications. Yet, little research effort has focussed on this area and much of the carried out research reports only marginally improved results compared to models trained without temporal scopes (static models). Furthermore, rather than leveraging existing work on static models, they introduce new models specific to temporal knowledge graphs. We propose a novel perspective that takes advantage of the power of existing static embedding models by focussing effort on manipulating the data instead. Our method, SPLIME, draws inspiration from the field of signal processing and early work in graph embedding. We show that SPLIME competes with or outperforms the current state of the art in temporal KGE. Additionally, we uncover issues with the procedure currently used to assess the performance of static models on temporal graphs and introduce two ways to counteract them.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Selective review of offline change point detection methodsSignal Processing, 2020
- Timespan-Aware Dynamic Knowledge Graph Embedding by Incorporating Temporal EvolutionIEEE Access, 2020
- Knowledge Graph Embedding Based Question Answering2019
- Learning Sequence Encoders for Temporal Knowledge Graph Completion2018
- HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding2018
- Deriving Validity Time in Knowledge Graph2018
- A survey of methods for time series change point detectionKnowledge and Information Systems, 2016
- Encoding Temporal Information for Time-Aware Link Prediction2016
- A Review of Relational Machine Learning for Knowledge GraphsProceedings of the IEEE, 2015
- Friends and neighbors on the WebSocial Networks, 2003