Efficient Relational Context Perception for Knowledge Graph Completion

TL;DR

This paper introduces TRP, a novel architecture for knowledge graph completion that models dynamic relational context efficiently, outperforming existing models in accuracy and computational cost.

Contribution

The paper proposes the Triple Receptance Perception (TRP) architecture combined with tensor decomposition for more expressive and efficient knowledge graph completion.

Findings

Outperforms state-of-the-art models on benchmark datasets

Achieves higher accuracy in link prediction and triple classification

Reduces computational complexity compared to transformer-based methods

Abstract

Knowledge Graphs (KGs) provide a structured representation of knowledge but often suffer from challenges of incompleteness. To address this, link prediction or knowledge graph completion (KGC) aims to infer missing new facts based on existing facts in KGs. Previous knowledge graph embedding models are limited in their ability to capture expressive features, especially when compared to deeper, multi-layer models. These approaches also assign a single static embedding to each entity and relation, disregarding the fact that entities and relations can exhibit different behaviors in varying graph contexts. Due to complex context over a fact triple of a KG, existing methods have to leverage complex non-linear context encoder, like transformer, to project entity and relation into low dimensional representations, resulting in high computation cost. To overcome these limitations, we propose Triple Receptance Perception (TRP) architecture to model sequential information, enabling the learning of dynamic context of entities and relations. Then we use tensor decomposition to calculate triple scores, providing robust relational decoding capabilities. This integration allows for more expressive representations. Experiments on benchmark datasets such as YAGO3-10, UMLS, FB15k, and FB13 in link prediction and triple classification tasks demonstrate that our method performs better than several state-of-the-art models, proving the effectiveness of the integration.