Research map / Graph learning / Knowledge and temporal graphs
Query Embedding on Hyper-Relational Knowledge Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use qualifiers instead of removing them (ablation) | StarQE · WD50K-QE 2p | Hits@10 (%): 12.76 -> 51.20 | Helped |
| Use qualifiers instead of removing them (ablation) | StarQE · WD50K-QE 1p | Hits@10 (%): 45.04 -> 51.72 | Mixed |
| Use qualifiers instead of removing them (ablation) | StarQE · WD50K-QE 2i-1p | Hits@10 (%): 16.77 -> 61.81 | Helped |
| Use qualifiers instead of removing them (ablation) | StarQE · WD50K-QE 1p-2i | Hits@10 (%): 40.67 -> 81.60 | Helped |
| Use qualifiers instead of removing them (ablation) | StarQE · WD50K-QE 3p | Hits@10 (%): 24.66 -> 65.50 | Helped |
| Remove message-passing layers (ablation) | StarQE · WD50K-QE 2p | Hits@10 (%): 51.20 -> 29.94 | Hurt |
| Remove message-passing layers (ablation) | StarQE · WD50K-QE 1p-2i | Hits@10 (%): 81.60 -> 47.85 | Hurt |
| Reify hyper-relational query graphs as triples (ablation) | StarQE · WD50K-QE across patterns | Hits@10 (%) | Mixed |
| Train/evaluate on reified rather than native query patterns (ablation) | MPQE-like setup · WD50K-QE unseen patterns | MRR (%): MPQE-like 39.81; MPQE-like + Reif 29.25 | Hurt |
| Set message-passing steps to query diameter, with an extra-step variant (ablation) | StarQE · WD50K-QE | QA performance | No clear effect |
| Include relation embeddings in the aggregation (ablation) | StarQE · WD50K-QE | QA performance | No clear effect |
| Train only on 1p query patterns (ablation) | MPQE-like StarQE · WD50K-QE unseen patterns | MRR (%): 55.20 -> 9.62 | Hurt |
Closest papers by meaning
- NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge Graphs (AAAI 2023 · similarity 0.92)
- Inductive Logical Query Answering in Knowledge Graphs (NeurIPS 2022 · similarity 0.91)
- ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs (NeurIPS 2021 · similarity 0.91)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.89)
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations (ICLR 2025 · similarity 0.88)
- Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.