Research map / Probabilistic and scientific modeling / Molecules and proteins
Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, Chandan K. Reddy
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| PERM vs best baseline CQD on average across query types | PERM · logical reasoning (all datasets) | HITS@3 avg: 6.2% | Improved |
| PERM vs CQD on union queries | PERM · logical reasoning | HITS@3 2u: 9.5% | Improved |
| PERM vs CQD on union-after-translation queries | PERM · logical reasoning | HITS@3 ut: 93.0 | Improved |
| PERM vs CQD on 2t and 3t queries | PERM · logical reasoning | HITS@3: -0.9 and -2.4 | Hurt |
| PERM vs CQD on NELL995 | PERM · NELL995 | HITS@3 avg: .375 -> .328 | Hurt |
| train only on 1-hop queries (ablation) | PERM · ablation avg | HITS@3 avg: 22.3% | Hurt |
| train on all translation queries only (ablation) | PERM · ablation avg | HITS@3 avg: 12.5% | Hurt |
| train on all single-operator queries only (ablation) | PERM · ablation avg | HITS@3 avg: .387 -> .390 | No clear effect |
| replace attentive union aggregation with vanilla averaging (ablation) | PERM · ablation avg | HITS@3 avg: .390 -> .377 | Hurt |
| replace attentive union aggregation with MLP (ablation) | PERM · ablation avg | HITS@3 avg: .390 -> .385 | Hurt |
| PERM vs CQD for COVID-19 drug recommendation | PERM · DRKG drug recommendation | F1: .232 -> .251 | Improved |
| PERM vs Q2B for drug recommendation | PERM · DRKG drug recommendation | P@10: 11.9% | Improved |
Closest papers by meaning
- A Foundation Model for Zero-shot Logical Query Reasoning (NeurIPS 2024 · similarity 0.86)
- Bayesian Inference with Complex Knowledge Graph Evidence (AAAI 2024 · similarity 0.85)
- Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking (NeurIPS 2025 · similarity 0.84)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.84)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.84)
- EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering (AAAI 2025 · similarity 0.84)
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.
