Research map / Graph learning / Knowledge and temporal graphs
Holographic Embeddings of 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 |
|---|---|---|---|
| replace tensor product with circular correlation as compositional operator | RESCAL-style compositional KG embedding · WN18 | filtered MRR: 0.890 -> 0.938 | Helped |
| replace tensor product with circular correlation | RESCAL · FB15k | filtered MRR: 0.354 -> 0.524 | Helped |
| replace tensor product with circular correlation | RESCAL · FB15k | parameters: 32.5M -> 3.3M | Helped |
| HolE instead of TransE | KG link prediction · FB15k | Hits@10: 74.9 -> 73.9 | Hurt |
| HolE instead of RESCAL/ER-MLP | relational learning · Countries S3 | AUC-PR: 0.652 -> 0.697 | Helped |
| retrain all baselines with identical AdaGrad + ranking loss | TransE and RESCAL · WN18 and FB15k | MRR | Helped |
Closest papers by meaning
- Expanding Holographic Embeddings for Knowledge Completion (NeurIPS 2018 · similarity 0.92)
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction (AAAI 2020 · similarity 0.87)
- Complex Embeddings for Simple Link Prediction (ICML 2016 · similarity 0.87)
- Improved Knowledge Graph Embedding Using Background Taxonomic Information (AAAI 2019 · similarity 0.87)
- HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces (AAAI 2024 · similarity 0.85)
- Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization (ICML 2024 · 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.