SGKGE: Semantically Guided Knowledge Graph Embeddings via Complementary Latent Representations
- 23 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10114-10127
Abstract
Knowledge graph (KG) completion is a challenging yet essential task that has attracted increasing attention in recent years. While entities in KGs typically present complex semantics (a phenomenon known as polysemy), previous works primarily focus on holistic but often inaccurate representations of entities, neglecting the diversity of their semantics. This limitation results in suboptimal representations for entities within KGs. To address this issue, we propose a new method termed semantically guided KG embeddings (SGKGE), which captures the precise semantics of entities in KGs from a semantics-guided perspective. Specifically, SGKGE first guides the learning of holistic semantics of entities through a hyperbolic manifold with learnable shared curvature and a geometric attention-fusion module, facilitating efficient reasoning. Subsequently, SGKGE captures fine-grained semantics through a set of Cartesian product Riemannian manifolds with distinct curvatures, coupled with a semantic interactions module. This approach enables SGKGE to produce more accurate entity semantics and enhance downstream applications. Experimental results demonstrate that our model achieves state-of-the-art performance on six well-established KG completion benchmarks. The release code is available at https://github.com/RuizhouLiu/SGKGE.Keywords
Funding Information
- National Natural Science Foundation of China (62236008, 62441232, 62472238, U21B2038)
This publication has 41 references indexed in Scilit:
- Multimodal Knowledge Graph Embeddings via Lorentz-based Contrastive Learning2024
- TracKGE: Transformer with Relation-pattern Adaptive Contrastive Learning for Knowledge Graph EmbeddingKnowledge-Based Systems, 2024
- Graph attention network with dynamic representation of relations for knowledge graph completionExpert Systems with Applications, 2023
- Knowledge graph embedding by relational rotation and complex convolution for link predictionExpert Systems with Applications, 2022
- Knowledge graph embedding by projection and rotation on hyperplanes for link predictionApplied Intelligence, 2022
- AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System2022
- AutoSF: Searching Scoring Functions for Knowledge Graph Embedding2020
- Modeling Relational Data with Graph Convolutional Networks2018
- The Expression of a Tensor or a Polyadic as a Sum of ProductsJournal of Mathematics and Physics, 1927
- Teoria fondamentale degli spazii di curvatura costanteAnnali di Matematica Pura ed Applicata (1923 -), 1868