TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation

Abstract

In the last few years, there has been a surge of interest in learning representations of entities and relations in knowledge graph (KG). However, the recent availability of temporal knowledge graphs (TKGs) that contain time information for each fact created the need for reasoning over time in such TKGs. In this regard, we present a new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding as a rotation from the initial time to the current time in the complex vector space. Specially, for facts involving time intervals, each relation is represented as a pair of dual complex embeddings to handle the beginning and the end of the relation, respectively. We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models and has the ability of learning and inferring various relation patterns over time. Experimental results on four different TKGs show that TeRo significantly outperforms existing state-of-the-art models for link prediction. In addition, we analyze the effect of time granularity on link prediction over TKGs, which as far as we know has not been investigated in previous literature.

TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

“…However, recent researches in TKGs focus on temporal link prediction, which is simply single-hop. The methods include tensor decomposition methods [8][9][10] timestamp transformation methods [11][12][13][14], etc. A complex logical query involving multiple facts for multi-hop reasoning is not fully explored yet.…”

“…Transformation-based methods use timestamps in temporal facts to transform embeddings of entity/relation in the facts and then use a score function to evaluate the validity of the facts. Existing approaches include relation transformation [11] and entity-relation transformation [12][13][14]. However, transformation-based methods are only confined to the one-hop link prediction task and cannot answer a multi-hop query that involves multiple entities and relations in the knowledge graph.…”

Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings

“…RotatE adds a margin parameter into the binary logistic loss function without the regularization term. This margin-based logistic loss function has been proven to be helpful to enhance the performance of distance-based models [11,12,13]. In this work, we utilize the binary logistic loss function to train TransE, RotatE, DistMult and ComplEx.…”

Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures

“…An advantage of ATISE is its ability to represent time uncertainty as the covariance of the Gaussian distributions. TERO (Xu et al, 2020b) combines ideas from TRANSE and ROTATE. It defines relations as translations and timestamps as rotations.…”

“…The final models for evaluation were selected upon the MRR metric on the validation set. We re-train ATISE and TERO using the same parameters as mentionned in Xu et al (2019) and Xu et al (2020b) but varying dimensions. 5…”