Research map / Graph learning / Knowledge and temporal graphs
InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions
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 InteractE instead of ConvE | ConvE · FB15k-237 | MRR: .325 -> .354 | Helped |
| Use InteractE instead of ConvE | ConvE · WN18RR | MRR: .43 -> .463 | Helped |
| Use InteractE instead of ConvE | ConvE · YAGO3-10 | MRR: .44 -> .541 | Helped |
| Replace stacked reshaping with alternate reshaping (ablation) | InteractE · FB15k-237 validation; WN18RR validation | MRR | Helped |
| Decrease the alternate-reshaping block size τ (ablation) | InteractE · FB15k-237 validation; WN18RR validation | MRR | Helped |
| Replace alternate or stacked reshaping with checkered reshaping (ablation) | InteractE · FB15k-237 validation; WN18RR validation | MRR | Helped |
| Use circular instead of standard convolution (ablation) | InteractE · FB15k-237 validation; WN18RR validation | MRR | Helped |
| Increase the number of feature permutations (ablation) | InteractE · FB15k-237 validation | MRR | No clear effect |
| Increase the number of feature permutations (ablation) | InteractE · WN18RR validation; YAGO3-10 validation | MRR | Mixed |
| Use more than the saturation point of feature permutations (ablation) | InteractE · FB15k-237 validation; WN18RR validation; YAGO3-10 validation | MRR | Hurt |
Closest papers by meaning
- Convolutional 2D Knowledge Graph Embeddings (AAAI 2018 · similarity 0.92)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.86)
- Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation (NeurIPS 2025 · similarity 0.86)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (NeurIPS 2024 · similarity 0.86)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · 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.