Research map / Label-efficient and robust learning / Recognition and long-tail
Discriminative Gaifman Models
Mathias Niepert
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 |
|---|---|---|---|
| Increase neighborhood depth r from 1 to 3 (with k=20, w=5, w̃=25) (ablation) | Gaifman model · FB15K | Hits@10: 82.1 -> 84.2 | Improved |
| Increase neighborhood depth r from 1 to 2 (k=20, w=5, w̃=25) (ablation) | Gaifman model · WN18 | Hits@10: 93.6 -> 93.9 | Improved |
| Use more neighborhood samples at inference (N=1 to 3 averaged) and more training neighborhoods (w=1,w̃=2 to w=5,w̃=25) (ablation) | Gaifman model · FB15K | Hits@1: 60.1 -> 65.6 | Improved |
| Use more training neighborhood samples (w=1,w̃=2 to w=5,w̃=25) with k=20, r=1 (ablation) | Gaifman model · WN18 | Hits@10: 88.1 -> 93.6 | Improved |
| Remove size bound k (use full 1-neighborhood) instead of k=20 (ablation) | Gaifman model · FB15K | Hits@10: 82.1 -> 78.1 | Hurt |
| Remove size bound k (use full 1-neighborhood) instead of k=20 (ablation) | Gaifman model · WN18 | Hits@10: 93.9 vs 93.6 | No clear effect |
| Gaifman model with k=20 bounded neighborhoods vs TransE baseline | Gaifman model · FB15K | Hits@1: 28.1 -> 65.6 | Improved |
| Use neighborhood-based Gaifman models (r=1, k=20) instead of DistMult on WN18 | Gaifman model · WN18 | Hits@10: 93.6 vs 93.7 | Mixed |
Closest papers by meaning
- Relational Concept Bottleneck Models (NeurIPS 2024 · similarity 0.84)
- Relational Proxies: Emergent Relationships as Fine-Grained Discriminators (NeurIPS 2022 · similarity 0.84)
- Towards Foundation Models for Knowledge Graph Reasoning (ICLR 2024 · similarity 0.83)
- Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective (ICML 2024 · similarity 0.83)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.82)
- How Expressive are Knowledge Graph Foundation Models? (ICML 2025 · similarity 0.82)
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.
