2020 · 68 citations · 25 references
ComputingComputer ScienceMachine LearningRecommender SystemsUser Experience DesignCollaborative FilteringOnline RecommendationRecommendation SystemsUser ModelingAdaptive RecommendationLong-term Preference ModelingModel FidelityNew User RecommendationRetraining CostsShort-term Preference Modeling
Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since it can account for both long-term and short-term user preference. However, a full model retraining could be very time-consuming and memory-costly, especially when the scale of historical data is large. In this work, we study the model retraining mechanism for recommender systems, a topic of high practical values but has been relatively little explored in the research community.
25
Steffen Rendle · 2010 · 3.1K citations
Neural Graph Collaborative Filtering
2019 · 3K citations · Full text