Scope & Topics
The MoST-Rec Workshop aims to connect the domains of Recommender Systems (RS), Model Selection (MS) and Parameter Tuning (PT). The goal is to facilitate knowledge exchange between the communities of these research areas. Therefore, we are looking for topics that explain methods, challenges and insights at the intersection of these domains. In particular, topics of solicited papers include, but are not limited to:
Model Selection and Parameter Tuning for Recommender Systems
- Ensemble methods
- Online model selection / ensembles
- Online boosting
- Parameter tuning
- High noise model selection / tuning
- Sparsely labeled model selection / tuning
- Distributing model selection or parameter tuning
Recommender Systems applying model selection and parameter tuning methods:
- Short term temporal dynamics (Item popularity, trends)
- Long term temporal dynamics (user tastes)
- Continously changing sets of users and items
- Scenarios with sparse rewards
- Tuning robustness, convergence and lerning-rate
- Considerations of popularity bias (in the evaluation metrics, learning procedure)
NEW: All accepted papers will be considered for inclusion in the Special Issue on Data Science for Next-Generation Recommender Systems in Springer International Journal of Data Science and Analytics (JDSA).