Research map / Graph learning / Knowledge and temporal graphs
NQE: N-ary Query Embedding for Complex Query Answering over 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 NQE instead of StarQE | CQA over hyper-relational knowledge graphs · WD50K-QE | AVG_p MRR (%): 64.47 -> 75.84 | Helped |
| Train NQE using only one-hop queries rather than all query types | NQE · WD50K-QE | AVG_p MRR (%): 75.84 -> 72.94 | Hurt |
| Train NQE using only one-hop queries rather than all query types | NQE · WD50K-NFOL | AVG_p MRR (%): 36.87 -> 32.80 | Hurt |
| Add edge heterogeneity to the Transformer (ablation) | NQE · WD50K-NFOL | AVG_p MRR (%): 31.32 -> 36.87 | Helped |
| Add node heterogeneity to the Transformer (ablation) | NQE · WD50K-NFOL | AVG_p MRR (%): 29.05 -> 36.87 | Helped |
| Use fuzzy logic operators instead of averaging (ablation) | NQE · WD50K-NFOL | AVG_p MRR (%): 32.92 -> 36.87 | Helped |
| Use fuzzy logic operators instead of averaging (ablation) | NQE · WD50K-NFOL | AVG_n MRR (%): 7.75 -> 14.06 | Helped |
| Use parallel processing rather than non-parallel processing (ablation) | NQE · WD50K-NFOL | AVG_p MRR (%): 33.47 -> 36.87 | Helped |
| Use parallel processing rather than non-parallel processing (ablation) | NQE · WD50K-NFOL | AVG_n MRR (%): 12.45 -> 14.06 | Helped |
Closest papers by meaning
- Fuzzy Logic Based Logical Query Answering on Knowledge Graphs (AAAI 2022 · similarity 0.93)
- Query Embedding on Hyper-Relational Knowledge Graphs (ICLR 2022 · similarity 0.92)
- A Foundation Model for Zero-shot Logical Query Reasoning (NeurIPS 2024 · similarity 0.90)
- ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs (NeurIPS 2021 · similarity 0.90)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.90)
- Is Complex Query Answering Really Complex? (ICML 2025 · similarity 0.89)
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.