AISurfingShort, clear updates with the original source one click away
← Back to brief
Research→Official→Preprint→arXiv AI/ML

GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention

Jul 14, 2026

Researchers propose GRATE, a temporal encoding method for knowledge graph foundation models that uses gated rotary attention to encode time without adding learnable parameters. GRATE enables inductive transfer to temporal knowledge graphs with disjoint vocabularies and outperforms static baselines on new benchmarks, GDELTIndT and WIKIIndT.

Why it matters: This work extends the transferability of knowledge graph foundation models to temporal data, enabling generalization to unseen entities, relations, and timestamps across datasets.

Full story at: arXiv AI/ML ↗

Related coverage

Optimal Self-Distillation for Rectified Flow via Linear ProbingHybrid Synthetic Data Framework Improves Causal Inference Fidelity Over Fully Generative ModelsReOPD: Efficient Multi-Turn On-Policy Distillation for LLM Agents