Müllner Peter , Lex Elisabeth, Schedl Markus, Kowald Dominik
2024
Collaborative filtering-based recommender systems leverage vast amounts of behavioral user data, which poses severe privacy risks. Thus, often random noise is added to the data to ensure Differential Privacy (DP). However, to date it is not well understood in which ways this impacts personalized recommendations. In this work, we study how DP affects recommendation accuracy and popularity bias when applied to the training data of state-of-the-art recommendation models.Our findings are three-fold: First, we observe that nearly all users' recommendations change when DP is applied. Second, recommendation accuracy drops substantially while recommended item popularity experiences a sharp increase, suggesting that popularity bias worsens. Finally, we find that DP exacerbates popularity bias more severely for users who prefer unpopular items than for users who prefer popular items.
Müllner Peter , Lex Elisabeth, Schedl Markus, Kowald Dominik
2023
State-of-the-art recommender systems produce high-quality recommendations to support users in finding relevant content. However, through the utilization of users' data for generating recommendations, recommender systems threaten users' privacy. To alleviate this threat, often, differential privacy is used to protect users' data via adding random noise. This, however, leads to a substantial drop in recommendation quality. Therefore, several approaches aim to improve this trade-off between accuracy and user privacy. In this work, we first overview threats to user privacy in recommender systems, followed by a brief introduction to the differential privacy framework that can protect users' privacy. Subsequently, we review recommendation approaches that apply differential privacy, and we highlight research that improves the trade-off between recommendation quality and user privacy. Finally, we discuss open issues, e.g., considering the relation between privacy and fairness, and the users' different needs for privacy. With this review, we hope to provide other researchers an overview of the ways in which differential privacy has been applied to state-of-the-art collaborative filtering recommender systems.
Müllner Peter , Lex Elisabeth, Schedl Markus, Kowald Dominik
2023
User-based KNN recommender systems (UserKNN) utilize the rating data of a target user’s k nearest neighbors in the recommendation process. This, however, increases the privacy risk of the neighbors since their rating data might be exposed to other users or malicious parties. To reduce this risk, existing work applies differential privacy by adding randomness to the neighbors’ ratings, which reduces the accuracy of UserKNN. In this work, we introduce ReuseKNN, a novel differentially-private KNN-based recommender system. The main idea is to identify small but highly reusable neighborhoods so that (i) only a minimal set of users requires protection with differential privacy, and (ii) most users do not need to be protected with differential privacy, since they are only rarely exploited as neighbors. In our experiments on five diverse datasets, we make two key observations: Firstly, ReuseKNN requires significantly smaller neighborhoods, and thus, fewer neighbors need to be protected with differential privacy compared to traditional UserKNN. Secondly, despite the small neighborhoods, ReuseKNN outperforms UserKNN and a fully differentially private approach in terms of accuracy. Overall, ReuseKNN leads to significantly less privacy risk for users than in the case of UserKNN.
Duricic Tomislav, Kowald Dominik, Schedl Markus, Lex Elisabeth
2021
Homophily describes the phenomenon that similarity breeds connection, i.e., individuals tend to form ties with other people who are similar to themselves in some aspect(s). The similarity in music taste can undoubtedly influence who we make friends with and shape our social circles. In this paper, we study homophily in an online music platform Last.fm regarding user preferences towards listening to mainstream (M), novel (N), or diverse (D) content. Furthermore, we draw comparisons with homophily based on listening profiles derived from artists users have listened to in the past, i.e., artist profiles. Finally, we explore the utility of users' artist profiles as well as features describing M, N, and D for the task of link prediction. Our study reveals that: (i) users with a friendship connection share similar music taste based on their artist profiles; (ii) on average, a measure of how diverse is the music two users listen to is a stronger predictor of friendship than measures of their preferences towards mainstream or novel content, i.e., homophily is stronger for D than for M and N; (iii) some user groups such as high-novelty-seekers (explorers) exhibit strong homophily, but lower than average artist profile similarity; (iv) using M, N and D achieves comparable results on link prediction accuracy compared with using artist profiles, but the combination of features yields the best accuracy results, and (v) using combined features does not add value if graph-based features such as common neighbors are available, making M, N, and D features primarily useful in a cold-start user recommendation setting for users with few friendship connections. The insights from this study …
Rekabsaz Navi, Kopeinik Simone, Schedl Markus
2021
Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation of BERT Ranker
Lex Elisabeth, Kowald Dominik, Seitlinger Paul, Tran Tran, Felfernig Alexander, Schedl Markus
2021
Psychology-informed Recommender Systems
Kowald Dominik, Müllner Peter , Zangerle Eva, Bauer Christine, Schedl Markus, Lex_KC Elisabeth
2021
Support the Underground: Characteristics of Beyond-Mainstream Music Listeners. EPJ Data Scienc
Schedl Markus, Bauer Christine, Reisinger Wolfgang, Kowald Dominik, Lex_KC Elisabeth
2021
Listener Modeling and Context-Aware Music Recommendation Based on Country Archetyp
Lex Elisabeth, Kowald Dominik, Schedl Markus
2020
In this paper, we address the problem of modeling and predicting the music genre preferences of users. We introduce a novel user modeling approach, BLLu, which takes into account the popularity of music genres as well as temporal drifts of user listening behavior. To model these two factors, BLLu adopts a psychological model that describes how humans access information in their memory. We evaluate our approach on a standard dataset of Last.fm listening histories, which contains fine-grained music genre information. To investigate performance for different types of users, we assign each user a mainstreaminess value that corresponds to the distance between the user’s music genre preferences and the music genre preferences of the (Last.fm) mainstream. We adopt BLLu to model the listening habits and to predict the music genre preferences of three user groups: listeners of (i) niche, low-mainstream music, (ii) mainstream music, and (iii) medium-mainstream music that lies in-between. Our results show that BLLu provides the highest accuracy for predicting music genre preferences, compared to five baselines: (i) group-based modeling, (ii) user-based collaborative filtering, (iii) item-based collaborative filtering, (iv) frequency-based modeling, and (v) recency-based modeling. Besides, we achieve the most substantial accuracy improvements for the low-mainstream group. We believe that our findings provide valuable insights into the design of music recommender systems
Kowald Dominik, Lex Elisabeth, Schedl Markus
2019