Model Releases
Biquaternionic Space with Complex-valued Attention for Temporal Knowledge Graph Completion
arXiv:2609.14279v1 Announce Type: cross Abstract: Temporal knowledge graph embedding (TKGE) models infer missing facts in knowledge graphs that evolve over time. Many existing models use a single geom
arXiv:2609.14279v1 Announce Type: cross Abstract: Temporal knowledge graph embedding (TKGE) models infer missing facts in knowledge graphs that evolve over time. Many existing models use a single geometric space, which can limit their ability to represent diverse relational patterns, or treat entity representations as static. We propose Biquaternionic Space with Complex-valued Attention (BSCA), a TKGE model that combines circular and hyperbolic rotations within a unified biquaternionic framework. A complex-valued attention mechanism adaptively fuses time-conditioned and relation-conditioned entity representations, allowing them to vary with temporal and relational context. Experiments on five benchmark datasets show competitive performance across datasets, with the largest improvement on GDELT: BSCA achieves an MRR of 52.1%, compared with 38.1% for the strongest baseline in our comparison.
Related
- Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
- TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs
- Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Source: arXiv cs.AI | 2026-09-15