Research map / Graph learning / Knowledge and temporal graphs
Temporal Knowledge Graph Completion Using Box Embeddings
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 BoxTE with relation-specific temporal bumps (k=5) | BoxE · GDELT | MRR: .275 -> .352 | Helped |
| Use BoxTE with relation-specific temporal bumps (k=2) | BoxE · ICEWS14 | MRR: .625 -> .615 | Hurt |
| Use BoxTE with relation-specific temporal bumps (k=5) | BoxE · ICEWS5-15 | MRR: .691 -> .667 | Hurt |
| Use BoxTE with relation-specific temporal bumps (k=3) | BoxE under a parameter bound · ICEWS14 | MRR: .526 -> .582 | Helped |
| Use BoxTE with relation-specific temporal bumps (k=3) | BoxE under a parameter bound · ICEWS5-15 | MRR: .600 -> .570 | Hurt |
| Use BoxTE with relation-specific temporal bumps (k=1) | BoxE under a parameter bound · GDELT | MRR: .230 -> .250 | Helped |
| Increase k from 1 to 3 (ablation) | BoxTE under a parameter bound · ICEWS14 | MRR: .576 -> .582 | Helped |
| Increase k from 1 to 3 (ablation) | BoxTE under a parameter bound · ICEWS5-15 | MRR: .564 -> .570 | Helped |
| Increase k from 1 to 5 (ablation) | BoxTE under a parameter bound · GDELT | MRR: .250 -> .236 | Hurt |
| Train without temporal smoothness regularization (ablation) | BoxTE · ICEWS14, ICEWS5-15, and GDELT | MRR | No clear effect |
| Use cross-entropy loss instead of negative-sampling loss (ablation) | BoxTE · TKGC benchmarks | performance | Helped |
Closest papers by meaning
- Diachronic Embedding for Temporal Knowledge Graph Completion (AAAI 2020 · similarity 0.92)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces (AAAI 2024 · similarity 0.88)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.87)
- Integrating Large Language Models and Möbius Group Transformations for Temporal Knowledge Graph Embedding on the Riemann Sphere (AAAI 2025 · similarity 0.86)
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.