Research map / Graph learning / Knowledge and temporal graphs
Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding
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 |
|---|---|---|---|
| Add projection-based entity transformations alongside relational rotations | RotatE-style knowledge graph embeddings · Countries | AUC-PR: 1.00 -> 1.00; 1.00 -> 1.00 | No clear effect |
| Add projection-based entity transformations alongside relational rotations | RotatE-style knowledge graph embeddings · Countries S3 | AUC-PR: 0.95 -> 0.998 | Helped |
| Add projection-based entity transformations alongside relational rotations | RotatE-style knowledge graph embeddings · FB15k-237 | MRR: .338 -> .344 | Helped |
| Add projection-based entity transformations alongside relational rotations | RotatE-style knowledge graph embeddings · WN18RR | MRR: .476 -> .457 | Hurt |
| Add projection-based entity transformations alongside relational rotations | RotatE-style knowledge graph embeddings · YAGO3-10 | Hit@10: .691 -> .699 | Helped |
| Initialize relational rotation phases in (-π/2, π/2) instead of (-π, π) (ablation) | Rot-Pro · YAGO3-10 isLocatedIn S1, S2, S3 | Hit@10 | Helped |
| Restrict relational rotation phases to (-π/2, π/2) during training (ablation) | Rot-Pro · YAGO3-10 isLocatedIn S1, S2, S3 | Hit@10 | Helped |
| Restrict relational rotation phases to (-π/2, π/2) during training (ablation) | Rot-Pro · YAGO3-10 isMarriedTo | symmetry modeling | Hurt |
Closest papers by meaning
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space (ICLR 2019 · similarity 0.90)
- Relational Pattern Benchmarking on the Knowledge Graph Link Prediction Task (NeurIPS 2021 · similarity 0.88)
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction (AAAI 2020 · similarity 0.88)
- SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions (AAAI 2017 · similarity 0.88)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.86)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.85)
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.