Research map / Learning theory and algorithms / Matrix and tensor methods
Deep Models of Interactions Across Sets
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 conditional sampling instead of uniform sampling for minibatches (ablation) | Exchangeable matrix models · MovieLens-100K | RMSE | Helped |
| Use minibatch subsampling instead of full-batch training (ablation) | Exchangeable matrix models · MovieLens-100K | RMSE | Hurt |
| Add channel-wise dropout (ablation) | Self-Supervised Model · MovieLens-100K | RMSE | Helped |
| Add channel-wise dropout (ablation) | Factorized EAE · Matrix completion | RMSE | Helped |
| Train on MovieLens-100K, then evaluate on a new dataset without retraining (ablation) | Factorized EAE · Flixster | RMSE: 0.908 -> 0.987 | Hurt |
| Train on MovieLens-100K, then evaluate on a new dataset without retraining (ablation) | Factorized EAE · Douban | RMSE: 0.738 -> 0.766 | Hurt |
| Train on MovieLens-100K, then evaluate on a new dataset without retraining (ablation) | Factorized EAE · YahooMusic | RMSE: 20.0 -> 23.3 | Hurt |
Closest papers by meaning
- Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning (ICML 2024 · similarity 0.85)
- Interaction Asymmetry: A General Principle for Learning Composable Abstractions (ICLR 2025 · similarity 0.84)
- REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS (ICLR 2025 · similarity 0.84)
- Learning symmetries via weight-sharing with doubly stochastic tensors (NeurIPS 2024 · similarity 0.84)
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.83)
- On the Joint Interaction of Models, Data, and Features (ICLR 2024 · similarity 0.83)
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.