Collaborative Filtering On Movielens 20M
Metriken
HR@10
nDCG@10
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | HR@10 | nDCG@10 |
|---|---|---|
| latent-relational-metric-learning-via-memory | 0.8447 | 0.6152 |
| hyperbolic-recommender-systems | 0.8736 | 0.6404 |
| session-based-recommendations-with-recurrent | - | - |
| knowledge-graph-convolutional-networks-for | - | - |
| hierarchical-gating-networks-for-sequential | - | 0.1195 |
| 190503375 | - | - |
| 180809781 | - | - |
| towards-amortized-ranking-critical-training | - | - |
| variational-autoencoders-for-collaborative | - | - |
| recvae-a-new-variational-autoencoder-for-top | - | - |
| bert4rec-sequential-recommendation-with | - | - |
| variational-autoencoders-for-collaborative | - | - |
| actions-speak-louder-than-words-trillion | - | - |
| collaborative-metric-learning | 0.7764 | 0.5301 |
| enhancing-vaes-for-collaborative-filtering | - | - |
| scalable-representation-learning-and | - | - |
| multi-gradient-descent-for-multi-objective | - | - |
| deep-variational-autoencoder-with-shallow | - | - |