Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283460463> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4283460463 abstract "While other areas of machine learning have seen more and more automation, designing a high-performing recommender system still requires a high level of human effort. Furthermore, recent work has shown that modern recommender system algorithms do not always improve over well-tuned baselines. A natural follow-up question is, how do we choose the right algorithm for a new dataset and performance metric? In this work, we start by giving the first large-scale study of recommender system approaches by comparing 18 algorithms and 100 sets of hyperparameters across 85 datasets and 315 metrics. We find that the best algorithms and hyperparameters are highly dependent on the dataset and performance metric, however, there are also strong correlations between the performance of each algorithm and various meta-features of the datasets. Motivated by these findings, we create RecZilla, a meta-learning approach to recommender systems that uses a model to predict the best algorithm and hyperparameters for new, unseen datasets. By using far more meta-training data than prior work, RecZilla is able to substantially reduce the level of human involvement when faced with a new recommender system application. We not only release our code and pretrained RecZilla models, but also all of our raw experimental results, so that practitioners can train a RecZilla model for their desired performance metric: https://github.com/naszilla/reczilla." @default.
- W4283460463 created "2022-06-26" @default.
- W4283460463 creator A5013829850 @default.
- W4283460463 creator A5036148540 @default.
- W4283460463 creator A5048078111 @default.
- W4283460463 creator A5066140617 @default.
- W4283460463 creator A5071538560 @default.
- W4283460463 date "2022-06-23" @default.
- W4283460463 modified "2023-10-14" @default.
- W4283460463 title "On the Generalizability and Predictability of Recommender Systems" @default.
- W4283460463 doi "https://doi.org/10.48550/arxiv.2206.11886" @default.
- W4283460463 hasPublicationYear "2022" @default.
- W4283460463 type Work @default.
- W4283460463 citedByCount "0" @default.
- W4283460463 crossrefType "posted-content" @default.
- W4283460463 hasAuthorship W4283460463A5013829850 @default.
- W4283460463 hasAuthorship W4283460463A5036148540 @default.
- W4283460463 hasAuthorship W4283460463A5048078111 @default.
- W4283460463 hasAuthorship W4283460463A5066140617 @default.
- W4283460463 hasAuthorship W4283460463A5071538560 @default.
- W4283460463 hasBestOaLocation W42834604631 @default.
- W4283460463 hasConcept C105795698 @default.
- W4283460463 hasConcept C119857082 @default.
- W4283460463 hasConcept C121332964 @default.
- W4283460463 hasConcept C124101348 @default.
- W4283460463 hasConcept C154945302 @default.
- W4283460463 hasConcept C162324750 @default.
- W4283460463 hasConcept C176217482 @default.
- W4283460463 hasConcept C187736073 @default.
- W4283460463 hasConcept C197640229 @default.
- W4283460463 hasConcept C21547014 @default.
- W4283460463 hasConcept C27158222 @default.
- W4283460463 hasConcept C2780451532 @default.
- W4283460463 hasConcept C2780898871 @default.
- W4283460463 hasConcept C2781002164 @default.
- W4283460463 hasConcept C33923547 @default.
- W4283460463 hasConcept C41008148 @default.
- W4283460463 hasConcept C557471498 @default.
- W4283460463 hasConcept C62520636 @default.
- W4283460463 hasConcept C8642999 @default.
- W4283460463 hasConceptScore W4283460463C105795698 @default.
- W4283460463 hasConceptScore W4283460463C119857082 @default.
- W4283460463 hasConceptScore W4283460463C121332964 @default.
- W4283460463 hasConceptScore W4283460463C124101348 @default.
- W4283460463 hasConceptScore W4283460463C154945302 @default.
- W4283460463 hasConceptScore W4283460463C162324750 @default.
- W4283460463 hasConceptScore W4283460463C176217482 @default.
- W4283460463 hasConceptScore W4283460463C187736073 @default.
- W4283460463 hasConceptScore W4283460463C197640229 @default.
- W4283460463 hasConceptScore W4283460463C21547014 @default.
- W4283460463 hasConceptScore W4283460463C27158222 @default.
- W4283460463 hasConceptScore W4283460463C2780451532 @default.
- W4283460463 hasConceptScore W4283460463C2780898871 @default.
- W4283460463 hasConceptScore W4283460463C2781002164 @default.
- W4283460463 hasConceptScore W4283460463C33923547 @default.
- W4283460463 hasConceptScore W4283460463C41008148 @default.
- W4283460463 hasConceptScore W4283460463C557471498 @default.
- W4283460463 hasConceptScore W4283460463C62520636 @default.
- W4283460463 hasConceptScore W4283460463C8642999 @default.
- W4283460463 hasLocation W42834604631 @default.
- W4283460463 hasOpenAccess W4283460463 @default.
- W4283460463 hasPrimaryLocation W42834604631 @default.
- W4283460463 hasRelatedWork W2904730647 @default.
- W4283460463 hasRelatedWork W2948164010 @default.
- W4283460463 hasRelatedWork W3199608561 @default.
- W4283460463 hasRelatedWork W3200361725 @default.
- W4283460463 hasRelatedWork W4283460463 @default.
- W4283460463 hasRelatedWork W4301772239 @default.
- W4283460463 hasRelatedWork W4311179768 @default.
- W4283460463 hasRelatedWork W4375852175 @default.
- W4283460463 hasRelatedWork W98577079 @default.
- W4283460463 hasRelatedWork W2929271699 @default.
- W4283460463 isParatext "false" @default.
- W4283460463 isRetracted "false" @default.
- W4283460463 workType "article" @default.