ChronoR: Rotation Based Temporal Knowledge Graph Embedding

03/18/2021
by   Ali Sadeghian, et al.
0

Despite the importance and abundance of temporal knowledge graphs, most of the current research has been focused on reasoning on static graphs. In this paper, we study the challenging problem of inference over temporal knowledge graphs. In particular, the task of temporal link prediction. In general, this is a difficult task due to data non-stationarity, data heterogeneity, and its complex temporal dependencies. We propose Chronological Rotation embedding (ChronoR), a novel model for learning representations for entities, relations, and time. Learning dense representations is frequently used as an efficient and versatile method to perform reasoning on knowledge graphs. The proposed model learns a k-dimensional rotation transformation parametrized by relation and time, such that after each fact's head entity is transformed using the rotation, it falls near its corresponding tail entity. By using high dimensional rotation as its transformation operator, ChronoR captures rich interaction between the temporal and multi-relational characteristics of a Temporal Knowledge Graph. Experimentally, we show that ChronoR is able to outperform many of the state-of-the-art methods on the benchmark datasets for temporal knowledge graph link prediction.

READ FULL TEXT
research
02/26/2019

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

We study the problem of learning representations of entities and relatio...
research
09/10/2018

Learning Sequence Encoders for Temporal Knowledge Graph Completion

Research on link prediction in knowledge graphs has mainly focused on st...
research
10/16/2015

Holographic Embeddings of Knowledge Graphs

Learning embeddings of entities and relations is an efficient and versat...
research
07/02/2020

Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs

We present a multi-relational temporal Knowledge Graph based on the dail...
research
10/01/2019

TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction

Link prediction is an important and frequently studied task that contrib...
research
05/21/2022

Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction

Few-shot relational learning for static knowledge graphs (KGs) has drawn...
research
02/03/2019

A Relational Tucker Decomposition for Multi-Relational Link Prediction

We propose the Relational Tucker3 (RT) decomposition for multi-relationa...

Please sign up or login with your details

Forgot password? Click here to reset