RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
read the original abstract
We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the relations. In this paper, we present a new approach for knowledge graph embedding called RotatE, which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition. Specifically, the RotatE model defines each relation as a rotation from the source entity to the target entity in the complex vector space. In addition, we propose a novel self-adversarial negative sampling technique for efficiently and effectively training the RotatE model. Experimental results on multiple benchmark knowledge graphs show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
Relation operators in knowledge graphs are Kraus channels obeying three axioms, enabling KrausKGE which outperforms baselines on N-to-N relations and supplies a rank-based complexity measure.
-
Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models
Graphlets mined as structural tokens improve zero-shot inductive and transductive link prediction in knowledge graph foundation models across 51 diverse graphs.
-
AlertStar: Path-Aware Alert Prediction on Hyper-Relational Knowledge Graphs
AlertStar achieves superior performance on hyper-relational alert prediction by fusing qualifier context and structural paths in embedding space, outperforming global propagation methods on Warden and UNSW-NB15 benchmarks.
-
ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning
ChronoMedKG builds a temporal biomedical KG with 460k evidence-linked triples across 13k diseases using LLM consensus and introduces the ChronoTQA benchmark showing RAG gains on time-sensitive questions.
-
Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning
Polaris learns hierarchical concepts via coupled orbital polar embeddings on hyperspheres that separate meaning from structure using tangent projections, exponential maps, and asymmetric objectives, yielding up to 19-...
-
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming ...
-
When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs
MRCKG combines a multimodal-structural curriculum, cross-modal preservation, and contrastive replay to let multimodal knowledge graphs learn new entities and relations over time without catastrophic forgetting.
-
FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding
FactNet is a billion-scale multilingual knowledge graph that links 1.7B Wikidata assertions to 3.01B byte-precise evidence spans from 316 Wikipedia editions, accompanied by a leakage-controlled benchmark suite.
-
A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
A2QTGN combines adaptive quantum amplitude encoding with a temporal graph network to improve dynamic link prediction, showing strong results on five benchmark datasets.
-
Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies
Attribute inference attacks succeed on KGE outputs and randomization-based sanitization offers partial mitigation at the cost of recommendation utility.
-
Multi-Faceted Continual Knowledge Graph Embedding for Semantic-Aware Link Prediction
MF-CKGE separates temporal old and new knowledge into distinct embedding spaces with semantic decoupling and adaptive importance scoring to improve continual link prediction.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.