Collaborative Filtering On Million Song
Métriques
Recall@20
Recall@50
nDCG@100
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Recall@20 | Recall@50 | nDCG@100 | Paper Title | Repository |
|---|---|---|---|---|---|
| RecVAE | 0.276 | 0.374 | 0.326 | RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback | |
| Mult-VAE PR | 0.266 | 0.364 | 0.316 | Variational Autoencoders for Collaborative Filtering | |
| RaCT | 0.268 | 0.364 | 0.319 | Towards Amortized Ranking-Critical Training for Collaborative Filtering | |
| EASE | 0.333 | 0.428 | 0.389 | Embarrassingly Shallow Autoencoders for Sparse Data | |
| Mult-DAE | 0.266 | 0.363 | 0.313 | Variational Autoencoders for Collaborative Filtering | |
| SANSA | 0.332 | 0.427 | 0.388 | Scalable Approximate NonSymmetric Autoencoder for Collaborative Filtering | |
| CML | - | 0.2460 | - | Collaborative Metric Learning |
0 of 7 row(s) selected.