Published on Mon Sep 10 2018

Learning Sequence Encoders for Temporal Knowledge Graph Completion

Alberto García-Durán, Sebastijan Dumančić, Mathias Niepert

Research on link prediction in knowledge graphs has mainly focused on static data. In this work we consider temporal knowledge graphs. Relations between entities may only hold for a time interval or a specific point in time. We utilize recurrent neural networks to learn time-aware representations of relation types.

0
0
0
Abstract

Research on link prediction in knowledge graphs has mainly focused on static multi-relational data. In this work we consider temporal knowledge graphs where relations between entities may only hold for a time interval or a specific point in time. In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations. To incorporate temporal information, we utilize recurrent neural networks to learn time-aware representations of relation types which can be used in conjunction with existing latent factorization methods. The proposed approach is shown to be robust to common challenges in real-world KGs: the sparsity and heterogeneity of temporal expressions. Experiments show the benefits of our approach on four temporal KGs. The data sets are available under a permissive BSD-3 license 1.

Wed Apr 21 2021
Artificial Intelligence
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
0
0
0
Mon Nov 16 2020
Artificial Intelligence
Tucker decomposition-based Temporal Knowledge Graph Completion
A large amount of valuable knowledge still implicitly exists implicitly in the knowledge graphs. We build a new tensor decomposition model for temporal knowledge graphs completion. We show that our model outperforms baselines with an explicit margin on link prediction.
0
0
0
Wed Oct 07 2020
Artificial Intelligence
TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
Inferring missing facts in temporal knowledge graphs (TKGs) is a fundamental and challenging task. We propose the Temporal Message Passing (TeMP) framework to address these challenges. TeMP uses graph neural networks, temporal dynamics models, data imputation and gating techniques.
0
0
0
Tue Oct 30 2018
Machine Learning
DSKG: A Deep Sequential Model for Knowledge Graph Completion
knowledge graph (KG) completion aims to fill the missing facts in a KG. Current KG completion models compel two-thirds of a triple provided (e.g.,subject and relation) to predict the remaining one. In this paper, we propose a new model, which uses
0
0
0
Fri Apr 10 2020
Machine Learning
Tensor Decompositions for temporal knowledge base completion
Most algorithms for representation learning and link prediction in relational data have been designed for static data. However, the data they are applied to usually evolves with time, such as friend graphs in social networks or user interactions with items in recommender systems. We introduce new regularization schemes and present an extension
0
0
0
Sat Jul 06 2019
Artificial Intelligence
Diachronic Embedding for Temporal Knowledge Graph Completion
knowledge graphs (KGs) typically contain temporal facts indicatingrelationships among entities at different times. Due to their incompleteness, approaches have been proposed to infer new facts for a KG based on the existing ones- a problem known as KG completion.
0
0
0