Investigating the Robustness of Sequential Recommender Systems Against Training Data Perturbations: an Empirical Study.
Filippo BetelloFederico SicilianoPushkar MishraFabrizio SilvestriPublished in: CoRR (2023)
Keyphrases
- recommender systems
- training data
- manually labeled training data
- collaborative filtering
- decision trees
- matrix factorization
- test data
- learning algorithm
- computational efficiency
- supervised learning
- neural network
- trust aware
- cold start problem
- data sets
- domain knowledge
- user preferences
- training set
- recommendation quality
- user profiling
- rating prediction
- classification accuracy
- prior knowledge
- training instances
- personal preferences
- product recommendation
- data sparsity
- input data
- recommendation systems
- generalization error
- active learning
- class labels
- prediction accuracy
- labeled data