To date, graph collaborative filtering (CF) strategies have been shown to outperform pure CF models in generating accurate recommendations. Nevertheless, recent works have raised concerns about fairness and potential biases in the recommendation landscape since unfair recommendations may harm the interests of Consumers and Producers (CP). Acknowledging that the literature lacks a careful evaluation of graph CF on CP-aware fairness measures, we initially evaluated the effects on CP-aware fairness measures of eight state-of-the-art graph models with four pure CF recommenders. Unexpectedly, the observed trends show that graph CF solutions do not ensure a large item exposure and user fairness. To disentangle this performance puzzle, we formalize a taxonomy for graph CF based on the mathematical foundations of the different approaches. The proposed taxonomy shows differences in node representation and neighbourhood exploration as dimensions characterizing graph CF. Under this lens, the experimental outcomes become clear and open the doors to a multi-objective CP-fairness analysis (Codes are available at: https://github.com/sisinflab/ECIR2023-Graph-CF.).
Auditing Consumer- and Producer-Fairness in Graph Collaborative Filtering / Anelli, V. W.; Deldjoo, Y.; Di Noia, T.; Malitesta, D.; Paparella, V.; Pomo, C.. - 13980:(2023), pp. 33-48. (Intervento presentato al convegno 45th European Conference on Information Retrieval, ECIR 2023 tenutosi a irl nel 2023) [10.1007/978-3-031-28244-7_3].
Auditing Consumer- and Producer-Fairness in Graph Collaborative Filtering
Anelli V. W.;Deldjoo Y.;Di Noia T.;Malitesta D.;Pomo C.
2023-01-01
Abstract
To date, graph collaborative filtering (CF) strategies have been shown to outperform pure CF models in generating accurate recommendations. Nevertheless, recent works have raised concerns about fairness and potential biases in the recommendation landscape since unfair recommendations may harm the interests of Consumers and Producers (CP). Acknowledging that the literature lacks a careful evaluation of graph CF on CP-aware fairness measures, we initially evaluated the effects on CP-aware fairness measures of eight state-of-the-art graph models with four pure CF recommenders. Unexpectedly, the observed trends show that graph CF solutions do not ensure a large item exposure and user fairness. To disentangle this performance puzzle, we formalize a taxonomy for graph CF based on the mathematical foundations of the different approaches. The proposed taxonomy shows differences in node representation and neighbourhood exploration as dimensions characterizing graph CF. Under this lens, the experimental outcomes become clear and open the doors to a multi-objective CP-fairness analysis (Codes are available at: https://github.com/sisinflab/ECIR2023-Graph-CF.).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
