Research map / Architectures and efficiency / RNNs and normalization
A Neural Autoregressive Approach to Collaborative Filtering
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 |
|---|---|---|---|
| share parameters between different ratings (CF-NADE-S vs regular CF-NADE) (ablation) | CF-NADE · MovieLens 1M | Test RMSE | Helped |
| increase ordinal cost weight lambda from 0 to 1 (ablation) | CF-NADE and CF-NADE-S · MovieLens 1M | Test RMSE | Helped |
| item-based instead of user-based CF-NADE (ablation) | CF-NADE-S · MovieLens 1M | Test RMSE: 0.830 vs 0.850 (single layer) | Helped |
| add second hidden layer (ablation) | I-CF-NADE-S · MovieLens 1M | Test RMSE: 0.830 to 0.829 | Helped |
| add second hidden layer (ablation) | U-CF-NADE-S · MovieLens 10M | Test RMSE: 0.772 to 0.771 | Helped |
| add second hidden layer (ablation) | U-CF-NADE-S · Netflix | Test RMSE: 0.804 to 0.803 | Helped |
| increase number of hidden units (diminishing returns) (ablation) | I-CF-NADE-S · MovieLens 1M | Test RMSE | Helped |
| factorize weight matrices W and V (J=50) | CF-NADE · Netflix | parameter count: about 89 million to about 9 million parameters | Helped |
| single-layer CF-NADE-S beats prior state of the art on MovieLens 1M, 10M and Netflix | CF-NADE-S · MovieLens 10M | Test RMSE: 0.772 vs best baseline 0.782 | Helped |
Closest papers by meaning
- Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach (AAAI 2025 · similarity 0.86)
- DR-VAE: Debiased and Representation-enhanced Variational Autoencoder for Collaborative Recommendation (AAAI 2025 · similarity 0.85)
- TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation (NeurIPS 2025 · similarity 0.85)
- How Does Message Passing Improve Collaborative Filtering? (NeurIPS 2024 · similarity 0.84)
- ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering (ICLR 2024 · similarity 0.84)
- Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering (ICML 2025 · 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.