This paper proposes a sparse factorization approach, KGFlex, that represents each item feature as an embedding. With KGFlex, the user-item interactions are a factorized combination of the item features relevant to the user. An entropy-driven module drives the training considering only the feature involved in the user's decision-making process. Extensive experiments confirm the approach's effectiveness, considering the ranking accuracy, diversity, and induced bias. The public implementation of KGFlex is available at https://split.to/kgflex.
Inferring User Decision-Making Processes in Recommender Systems with Knowledge Graphs / Anelli, V. W.; Di Noia, T.; Di Sciascio, E.; Ferrara, A.; Mancino, A. C. M.. - 3194:(2022), pp. 505-513. (Intervento presentato al convegno 30th Italian Symposium on Advanced Database Systems, SEBD 2022 tenutosi a Grand Hotel Continental, ita nel 2022).
Inferring User Decision-Making Processes in Recommender Systems with Knowledge Graphs
Anelli V. W.;Di Noia T.;Di Sciascio E.;Ferrara A.;Mancino A. C. M.
2022-01-01
Abstract
This paper proposes a sparse factorization approach, KGFlex, that represents each item feature as an embedding. With KGFlex, the user-item interactions are a factorized combination of the item features relevant to the user. An entropy-driven module drives the training considering only the feature involved in the user's decision-making process. Extensive experiments confirm the approach's effectiveness, considering the ranking accuracy, diversity, and induced bias. The public implementation of KGFlex is available at https://split.to/kgflex.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
