Abstract
Recently, Knowledge Graph Embedding (KGE) has attracted considerable research efforts, since it simplifies the manipulation while preserving the inherent structure of the KG. However to some extent, most existing KGE approaches ignore the historical changes of structural information involved in dynamic knowledge graphs (DKGs). To deal with this problem, this paper presents a Timespan-aware Dynamic knowledge Graph Embedding Evolution (TDG2E) method that considers temporal evolving process of DKGs. The major innovations of our paper are two-fold. Firstly, a Gated Recurrent Units (GRU) based model is utilized in TDG2E to deal with the dependency among sub-KGs that is inevitably involved in the learning process of the dynamic knowledge graph embedding. Furthermore, we incorporate an auxiliary loss to supervise the learning process of the next sub-KG by utilizing previous structural information (i.e., the hidden state of GRU). In contrast with existing approaches in the literature (e.g., HyTE and t-TransE), TDG2E preserves structural information of current sub-KG and the temporal evolving process of the DKG simultaneously. Secondly, to further deal with the time unbalance issue underlying the DKGs, a Timespan Gate is designed in GRU. It makes TDG2E possible to model the temporal evolving process of DKGs more effectively by incorporating the timespan between adjacent sub-KGs. Extensive experiments on two large temporal datasets (i.e., YAGO11k and Wikidata12k) extracted from real-world KGs validate that the proposed TDG2E significantly outperforms traditional KGE methods in terms of Mean Rank and Hit Rate.
Highlights
Recent years have witnessed the rapid growth of Knowledge Graph (KG)
Considering that the effect of timespans, determining the effect of cumulative structural information on successors, is similar to that of the update gate in Gated Recurrent Units (GRU), which helps the model to determine how much of the past information needs to be passed along to the future [25], we propose to add a gate like the update gate to GRU for embodying the effect of timespans
WORK In this paper, we propose a novel model termed as TDG2E, which aims to directly encode temporal information in the learned embeddings of dynamic knowledge graphs
Summary
Recent years have witnessed the rapid growth of Knowledge Graph (KG). A great number of KGs, including Freebase [1], DBpedia [2], YAGO [3] and NELL [4] and so on, have been constructed and applied successfully to many realworld applications, ranging from semantic parsing [5], [6] and named entity disambiguation [7], [8], to information extraction [9], [10] and question answering [11], [12]. Each edge in a KG encodes a factual belief ( called a fact) and is represented as a triple of the form (head entity, relation, tail entity), indicating that the head. Though it is effective to represent inevitably structured data, the underlying symbolic nature of such triples usually makes KGs hard to manipulate [13]. To deal with this issue, a new research direction known as Knowledge Graph Embedding (KGE) has been proposed and quickly gained massive attention [14]–[20]. The main idea of KGE is to embed entities and relations of a KG into low dimensional spaces so as to simplify the manipulation while preserving the inherent structure of the KG [13]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
