Research map / Detection and segmentation / Open-set and few-shot detection
RelNN: A Deep Neural Model for Relational Learning
Seyed Mehran Kazemi, David Poole
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 |
|---|---|---|---|
| Use RelNN instead of Matrix Factorization | MovieLens Gender prediction · MovieLens Gender | accuracy: 0.7550 ± 0.0073 -> 0.7902 ± 0.0051 | Improved |
| Use RelNN instead of Matrix Factorization | MovieLens Gender prediction · MovieLens Gender | log loss: 0.7318 ± 0.0073 -> 0.6548 ± 0.0026 | Improved |
| Use RelNN instead of Matrix Factorization | MovieLens Gender prediction · MovieLens Gender | MSE: 0.1649 ± 0.0026 -> 0.1459 ± 0.0009 | Improved |
| Use RelNN instead of Collaborative Filtering | PAKDD Gender prediction · PAKDD Gender | accuracy: 0.8806 -> 0.8853 ± 0.0002 | Improved |
| Use RelNN instead of Collaborative Filtering | PAKDD Gender prediction · PAKDD Gender | log loss: 0.5135 -> 0.5093 ± 0.0037 | Improved |
| Use RelNN instead of Collaborative Filtering | PAKDD Gender prediction · PAKDD Gender | MSE: 0.1026 -> 0.1009 ± 0.0008 | Improved |
| Use RelNN instead of Collaborative Filtering | Yelp Business Prediction · Yelp Business Prediction | accuracy: 0.6712 -> 0.6927 ± 0.0077 | Improved |
| Use RelNN instead of Collaborative Filtering | Yelp Business Prediction · Yelp Business Prediction | log loss: 0.8757 -> 0.8531 ± 0.0090 | Improved |
| Use RelNN instead of Collaborative Filtering | Yelp Business Prediction · Yelp Business Prediction | MSE: 0.2084 -> 0.2023 ± 0.0024 | Improved |
| Use RelNN instead of Collaborative Filtering | MovieLens Age prediction · MovieLens Age | MSE: 90.8742 -> 62.7000 ± 0.7812 | Improved |
| Add hidden layers (ablation) | RelNN on MovieLens · MovieLens gender and age prediction | log loss | Improved |
| Add hidden layers (ablation) | RelNN on MovieLens · MovieLens gender and age prediction | MSE | Improved |
Closest papers by meaning
- RelGNN: Composite Message Passing for Relational Deep Learning (ICML 2025 · similarity 0.88)
- Position: Relational Deep Learning - Graph Representation Learning on Relational Databases (ICML 2024 · similarity 0.85)
- When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning (NeurIPS 2025 · similarity 0.85)
- Relational DNN Verification With Cross Executional Bound Refinement (ICML 2024 · similarity 0.84)
- Relational Concept Bottleneck Models (NeurIPS 2024 · similarity 0.84)
- RelAgent: LLM Agents as Data Scientists for Relational Learning (NeurIPS 2026 · 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.
