Search

Recommender Systems (RS) often suffer from popularity bias, where a small set of popular items dominate the recommendation results due to their high interaction rates, leaving many less popular items overlooked. This phenomenon disproportionately benefits users with mainstream tastes while neglecting those with niche interests, leading to unfairness among users and exacerbating disparities in recommendation quality across different user groups. In this paper, we propose an in-processing approach to address this issue by intervening in the training process of recommendation models. Drawing inspiration from fair empirical risk minimization in machine learning, we augment the objective function of the recommendation model with an additional term aimed at minimizing the disparity in loss values across different item groups during the training process. Our approach is evaluated through extensive experiments on two real-world datasets and compared against state-of-the-art baselines. The results demonstrate the superior efficacy of our method in mitigating the unfairness of popularity bias while incurring only negligible loss in recommendation accuracy.

Exposure bias is a well-known issue in recommender systems where items and suppliers are not equally represented in the recommendation results. This bias becomes particularly problematic over time as a few items are repeatedly over-represented in recommendation lists, leading to a feedback loop that further amplifies this bias. Although extensive research has addressed this issue in model-based or neighborhood-based recommendation algorithms, less attention has been paid to online recommendation models, such as those based on top-K contextual bandits, where recommendation models are dynamically updated with ongoing user feedback. In this paper, we study exposure bias in a class of well-known contextual bandit algorithms known as Linear Cascading Bandits. We analyze these algorithms in their ability to handle exposure bias and provide a fair representation of items in the recommendation results. Our analysis reveals that these algorithms fail to mitigate exposure bias in the long run during the course of ongoing user interactions. We propose an Exposure-Aware reward model that updates the model parameters based on two factors: 1) implicit user feedback and 2) the position of the item in the recommendation list. The proposed model mitigates exposure bias by controlling the utility assigned to the items based on their exposure in the recommendation list. Our experiments with two real-world datasets show that our proposed reward model improves the exposure fairness of the linear cascading bandits over time while maintaining the recommendation accuracy. It also outperforms the current baselines. Finally, we prove a high probability upper regret bound for our proposed model, providing theoretical guarantees for its performance.

Calibration in recommender systems is an important performance criterion that ensures consistency between the distribution of user preference categories and that of recommendations generated by the system. Standard methods for mitigating miscalibration typically assume that user preference profiles are static, and they measure calibration relative to the full history of user's interactions, including possibly outdated and stale preference categories. We conjecture that this approach can lead to recommendations that, while appearing calibrated, in fact, distort users' true preferences. In this paper, we conduct a preliminary investigation of recommendation calibration at a more granular level, taking into account evolving user preferences. By analyzing differently sized training time windows from the most recent interactions to the oldest, we identify the most relevant segment of user's preferences that optimizes the calibration metric. We perform an exploratory analysis with datasets from different domains with distinctive user-interaction characteristics. We demonstrate how the evolving nature of user preferences affects recommendation calibration, and how this effect is manifested differently depending on the characteristics of the data in a given domain. Datasets, codes, and more detailed experimental results are available at: https://github.com/nicolelin13/DynamicCalibrationUMAP., Comment: 8 pages, 4 figures, accepted as LBR paper at UMAP '24 -- ACM Conference on User Modeling, Adaptation and Personalization 2024

Two typical forms of bias in user interaction data with recommender systems (RSs) are popularity bias and positivity bias, which manifest themselves as the over-representation of interactions with popular items or items that users prefer, respectively. Debiasing methods aim to mitigate the effect of selection bias on the evaluation and optimization of RSs. However, existing debiasing methods only consider single-factor forms of bias, e.g., only the item (popularity) or only the rating value (positivity). This is in stark contrast with the real world where user selections are generally affected by multiple factors at once. In this work, we consider multifactorial selection bias in RSs. Our focus is on selection bias affected by both item and rating value factors, which is a generalization and combination of popularity and positivity bias. While the concept of multifactorial bias is intuitive, it brings a severe practical challenge as it requires substantially more data for accurate bias estimation. As a solution, we propose smoothing and alternating gradient descent techniques to reduce variance and improve the robustness of its optimization. Our experimental results reveal that, with our proposed techniques, multifactorial bias corrections are more effective and robust than single-factor counterparts on real-world and synthetic datasets., Comment: SIGIR 2024

Popularity bias is a well-known issue in recommender systems where few popular items are over-represented in the input data, while majority of other less popular items are under-represented. This disparate representation often leads to bias in exposure given to the items in the recommendation results. Extensive research examined this bias from item perspective and attempted to mitigate it by enhancing the recommendation of less popular items. However, a recent research has revealed the impact of this bias on users. Users with different degree of tolerance toward popular items are not fairly served by the recommendation system: users interested in less popular items receive more popular items in their recommendations, while users interested in popular items are recommended what they want. This is mainly due to the popularity bias that popular items are over-recommended. In this paper, we aim at investigating the factors leading to this user-side unfairness of popularity bias in recommender systems. In particular, we investigate two factors: 1) the relationship between this unfairness and users' interest toward items' categories (e.g., movie genres), 2) the relationship between this unfairness and the diversity of the popularity group in users' profile (the degree to which the user is interested in items with different degree of popularity). Experiments on a movie recommendation dataset using multiple recommendation algorithms show that these two factors are significantly correlated with the degree of popularity unfairness in the recommendation results.

Societal biases that are contained in retrieved documents have received increased interest. Such biases, which are often prevalent in the training data and learned by the model, can cause societal harms, by misrepresenting certain groups, and by enforcing stereotypes. Mitigating such biases demands algorithms that balance the trade-off between maximized utility for the user with fairness objectives, which incentivize unbiased rankings. Prior work on bias mitigation often assumes that ranking scores, which correspond to the utility that a document holds for a user, can be accurately determined. In reality, there is always a degree of uncertainty in the estimate of expected document utility. This uncertainty can be approximated by viewing ranking models through a Bayesian perspective, where the standard deterministic score becomes a distribution. In this work, we investigate whether uncertainty estimates can be used to decrease the amount of bias in the ranked results, while minimizing loss in measured utility. We introduce a simple method that uses the uncertainty of the ranking scores for an uncertainty-aware, post hoc approach to bias mitigation. We compare our proposed method with existing baselines for bias mitigation with respect to the utility-fairness trade-off, the controllability of methods, and computational costs. We show that an uncertainty-based approach can provide an intuitive and flexible trade-off that outperforms all baselines without additional training requirements, allowing for the post hoc use of this approach on top of arbitrary retrieval models.

This study explores the potential of reinforcement learning algorithms to enhance career planning processes. Leveraging data from Randstad The Netherlands, the study simulates the Dutch job market and develops strategies to optimize employees' long-term income. By formulating career planning as a Markov Decision Process (MDP) and utilizing machine learning algorithms such as Sarsa, Q-Learning, and A2C, we learn optimal policies that recommend career paths with high-income occupations and industries. The results demonstrate significant improvements in employees' income trajectories, with RL models, particularly Q-Learning and Sarsa, achieving an average increase of 5% compared to observed career paths. The study acknowledges limitations, including narrow job filtering, simplifications in the environment formulation, and assumptions regarding employment continuity and zero application costs. Future research can explore additional objectives beyond income optimization and address these limitations to further enhance career planning processes., Comment: accepted for publication at RecSys in HR '23 (at the 17th ACM Conference on Recommender Systems)

Exposure bias is a well-known issue in recommender systems where the exposure is not fairly distributed among items in the recommendation results. This is especially problematic when bias is amplified over time as a few items (e.g., popular ones) are repeatedly over-represented in recommendation lists and users' interactions with those items will amplify bias towards those items over time resulting in a feedback loop. This issue has been extensively studied in the literature in static recommendation environment where a single round of recommendation result is processed to improve the exposure fairness. However, less work has been done on addressing exposure bias in a dynamic recommendation setting where the system is operating over time, the recommendation model and the input data are dynamically updated with ongoing user feedback on recommended items at each round. In this paper, we study exposure bias in a dynamic recommendation setting. Our goal is to show that existing bias mitigation methods that are designed to operate in a static recommendation setting are unable to satisfy fairness of exposure for items in long run. In particular, we empirically study one of these methods and show that repeatedly applying this method fails to fairly distribute exposure among items in long run. To address this limitation, we show how this method can be adapted to effectively operate in a dynamic recommendation setting and achieve exposure fairness for items in long run. Experiments on a real-world dataset confirm that our solution is superior in achieving long-term exposure fairness for the items while maintaining the recommendation accuracy.

Exposure bias is a well-known issue in recommender systems where items and suppliers are not equally represented in the recommendation results. This is especially problematic when bias is amplified over time as a few items (e.g., popular ones) are repeatedly over-represented in recommendation lists and users' interactions with those items will amplify bias towards those items over time resulting in a feedback loop. This issue has been extensively studied in the literature on model-based or neighborhood-based recommendation algorithms, but less work has been done on online recommendation models, such as those based on top-K contextual bandits, where recommendation models are dynamically updated with ongoing user feedback. In this paper, we study exposure bias in a class of well-known contextual bandit algorithms known as Linear Cascading Bandits. We analyze these algorithms on their ability to handle exposure bias and provide a fair representation for items in the recommendation results. Our analysis reveals that these algorithms tend to amplify exposure disparity among items over time. In particular, we observe that these algorithms do not properly adapt to the feedback provided by the users and frequently recommend certain items even when those items are not selected by users. To mitigate this bias, we propose an Exposure-Aware (EA) reward model that updates the model parameters based on two factors: 1) user feedback (i.e., clicked or not), and 2) position of the item in the recommendation list. This way, the proposed model controls the utility assigned to items based on their exposure in the recommendation list. Extensive experiments on two real-world datasets using three contextual bandit algorithms show that the proposed reward model reduces exposure bias amplification in long run while maintaining the recommendation accuracy.

Fairness is a critical system-level objective in recommender systems that has been the subject of extensive recent research. It is especially important in multi-sided recommendation platforms where it may be crucial to optimize utilities not just for the end user, but also for other actors such as item sellers or producers who desire a fair representation of their items. Existing solutions do not properly address various aspects of multi-sided fairness in recommendations as they may either solely have one-sided view (i.e. improving the fairness only for one side), or do not appropriately measure the fairness for each actor involved in the system. In this thesis, I aim at first investigating the impact of unfair recommendations on the system and how these unfair recommendations can negatively affect major actors in the system. Then, I seek to propose solutions to tackle the unfairness of recommendations. I propose a rating transformation technique that works as a pre-processing step before building the recommendation model to alleviate the inherent popularity bias in the input data and consequently to mitigate the exposure unfairness for items and suppliers in the recommendation lists. Also, as another solution, I propose a general graph-based solution that works as a post-processing approach after recommendation generation for mitigating the multi-sided exposure bias in the recommendation results. For evaluation, I introduce several metrics for measuring the exposure fairness for items and suppliers, and show that these metrics better capture the fairness properties in the recommendation results. I perform extensive experiments to evaluate the effectiveness of the proposed solutions. The experiments on different publicly-available datasets and comparison with various baselines confirm the superiority of the proposed solutions in improving the exposure fairness for items and suppliers., Comment: Doctoral thesis

Exposure bias is a well-known issue in recommender systems where items and suppliers are not equally represented in the recommendation results. This is especially problematic when bias is amplified over time as a few popular items are repeatedly over-represented in recommendation lists. This phenomenon can be viewed as a recommendation feedback loop: the system repeatedly recommends certain items at different time points and interactions of users with those items will amplify bias towards those items over time. This issue has been extensively studied in the literature on model-based or neighborhood-based recommendation algorithms, but less work has been done on online recommendation models such as those based on multi-armed Bandit algorithms. In this paper, we study exposure bias in a class of well-known bandit algorithms known as Linear Cascade Bandits. We analyze these algorithms on their ability to handle exposure bias and provide a fair representation for items and suppliers in the recommendation results. Our analysis reveals that these algorithms fail to treat items and suppliers fairly and do not sufficiently explore the item space for each user. To mitigate this bias, we propose a discounting factor and incorporate it into these algorithms that controls the exposure of items at each time step. To show the effectiveness of the proposed discounting factor on mitigating exposure bias, we perform experiments on two datasets using three cascading bandit algorithms and our experimental results show that the proposed method improves the exposure fairness for items and suppliers.

Fairness is a critical system-level objective in recommender systems that has been the subject of extensive recent research. A specific form of fairness is supplier exposure fairness where the objective is to ensure equitable coverage of items across all suppliers in recommendations provided to users. This is especially important in multistakeholder recommendation scenarios where it may be important to optimize utilities not just for the end-user, but also for other stakeholders such as item sellers or producers who desire a fair representation of their items. This type of supplier fairness is sometimes accomplished by attempting to increasing aggregate diversity in order to mitigate popularity bias and to improve the coverage of long-tail items in recommendations. In this paper, we introduce FairMatch, a general graph-based algorithm that works as a post processing approach after recommendation generation to improve exposure fairness for items and suppliers. The algorithm iteratively adds high quality items that have low visibility or items from suppliers with low exposure to the users' final recommendation lists. A comprehensive set of experiments on two datasets and comparison with state-of-the-art baselines show that FairMatch, while significantly improves exposure fairness and aggregate diversity, maintains an acceptable level of relevance of the recommendations., Comment: arXiv admin note: substantial text overlap with arXiv:2005.01148

Recommendation and ranking systems are known to suffer from popularity bias; the tendency of the algorithm to favor a few popular items while under-representing the majority of other items. Prior research has examined various approaches for mitigating popularity bias and enhancing the recommendation of long-tail, less popular, items. The effectiveness of these approaches is often assessed using different metrics to evaluate the extent to which over-concentration on popular items is reduced. However, not much attention has been given to the user-centered evaluation of this bias; how different users with different levels of interest towards popular items are affected by such algorithms. In this paper, we show the limitations of the existing metrics to evaluate popularity bias mitigation when we want to assess these algorithms from the users' perspective and we propose a new metric that can address these limitations. In addition, we present an effective approach that mitigates popularity bias from the user-centered point of view. Finally, we investigate several state-of-the-art approaches proposed in recent years to mitigate popularity bias and evaluate their performances using the existing metrics and also from the users' perspective. Our experimental results using two publicly-available datasets show that existing popularity bias mitigation techniques ignore the users' tolerance towards popular items. Our proposed user-centered method can tackle popularity bias effectively for different users while also improving the existing metrics., Comment: Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP '21), June 21--25, 2021, Utrecht, Netherlands. arXiv admin note: text overlap with arXiv:2007.12230

Recently there has been a growing interest in fairness-aware recommender systems including fairness in providing consistent performance across different users or groups of users. A recommender system could be considered unfair if the recommendations do not fairly represent the tastes of a certain group of users while other groups receive recommendations that are consistent with their preferences. In this paper, we use a metric called miscalibration for measuring how a recommendation algorithm is responsive to users' true preferences and we consider how various algorithms may result in different degrees of miscalibration for different users. In particular, we conjecture that popularity bias which is a well-known phenomenon in recommendation is one important factor leading to miscalibration in recommendation. Our experimental results using two real-world datasets show that there is a connection between how different user groups are affected by algorithmic popularity bias and their level of interest in popular items. Moreover, we show that the more a group is affected by the algorithmic popularity bias, the more their recommendations are miscalibrated., Comment: Accepted at the 14th ACM Conference on Recommender Systems (RecSys 2020) Late Breaking Results Track. arXiv admin note: substantial text overlap with arXiv:1910.05755

Recommendation algorithms are known to suffer from popularity bias; a few popular items are recommended frequently while the majority of other items are ignored. These recommendations are then consumed by the users, their reaction will be logged and added to the system: what is generally known as a feedback loop. In this paper, we propose a method for simulating the users interaction with the recommenders in an offline setting and study the impact of feedback loop on the popularity bias amplification of several recommendation algorithms. We then show how this bias amplification leads to several other problems such as declining the aggregate diversity, shifting the representation of users' taste over time and also homogenization of the users experience. In particular, we show that the impact of feedback loop is generally stronger for the users who belong to the minority group.

Popularity bias is a well-known phenomenon in recommender systems: popular items are recommended even more frequently than their popularity would warrant, amplifying long-tail effects already present in many recommendation domains. Prior research has examined various approaches for mitigating popularity bias and enhancing the recommendation of long-tail items overall. The effectiveness of these approaches, however, has not been assessed in multistakeholder environments where in addition to the users who receive the recommendations, the utility of the suppliers of the recommended items should also be considered. In this paper, we propose the concept of popularity calibration which measures the match between the popularity distribution of items in a user's profile and that of the recommended items. We also develop an algorithm that optimizes this metric. In addition, we demonstrate that existing evaluation metrics for popularity bias do not reflect the performance of the algorithms when it is measured from the perspective of different stakeholders. Using music and movie datasets, we empirically show that our approach outperforms the existing state-of-the-art approaches in addressing popularity bias by calibrating the recommendations to users' preferences. We also show that our proposed algorithm has a secondary effect of improving supplier fairness.

Academic research in recommender systems has been greatly focusing on the accuracy-related measures of recommendations. Even when non-accuracy measures such as popularity bias, diversity, and novelty are studied, it is often solely from the users' perspective. However, many real-world recommenders are often multi-stakeholder environments in which the needs and interests of several stakeholders should be addressed in the recommendation process. In this paper, we focus on the popularity bias problem which is a well-known property of many recommendation algorithms where few popular items are over-recommended while the majority of other items do not get proportional attention and address its impact on different stakeholders. Using several recommendation algorithms and two publicly available datasets in music and movie domains, we empirically show the inherent popularity bias of the algorithms and how this bias impacts different stakeholders such as users and suppliers of the items. We also propose metrics to measure the exposure bias of recommendation algorithms from the perspective of different stakeholders., Comment: Accepted at the International Workshop on Industrial Recommendation Systems (IRS2020) in Conjunction with ACM KDD 2020

Recommender systems are often biased toward popular items. In other words, few items are frequently recommended while the majority of items do not get proportionate attention. That leads to low coverage of items in recommendation lists across users (i.e. low aggregate diversity) and unfair distribution of recommended items. In this paper, we introduce FairMatch, a general graph-based algorithm that works as a post-processing approach after recommendation generation for improving aggregate diversity. The algorithm iteratively finds items that are rarely recommended yet are high-quality and add them to the users' final recommendation lists. This is done by solving the maximum flow problem on the recommendation bipartite graph. While we focus on aggregate diversity and fair distribution of recommended items, the algorithm can be adapted to other recommendation scenarios using different underlying definitions of fairness. A comprehensive set of experiments on two datasets and comparison with state-of-the-art baselines show that FairMatch, while significantly improving aggregate diversity, provides comparable recommendation accuracy.

Fairness in machine learning has been studied by many researchers. In particular, fairness in recommender systems has been investigated to ensure the recommendations meet certain criteria with respect to certain sensitive features such as race, gender etc. However, often recommender systems are multi-stakeholder environments in which the fairness towards all stakeholders should be taken care of. It is well-known that the recommendation algorithms suffer from popularity bias; few popular items are over-recommended which leads to the majority of other items not getting proportionate attention. This bias has been investigated from the perspective of the users and how it makes the final recommendations skewed towards popular items in general. In this paper, however, we investigate the impact of popularity bias in recommendation algorithms on the provider of the items (i.e. the entities who are behind the recommended items). Using a music dataset for our experiments, we show that, due to some biases in the algorithms, different groups of artists with varying degrees of popularity are systematically and consistently treated differently than others.

The proliferation of personalized recommendation technologies has raised concerns about discrepancies in their recommendation performance across different genders, age groups, and racial or ethnic populations. This varying degree of performance could impact users' trust in the system and may pose legal and ethical issues in domains where fairness and equity are critical concerns, like job recommendation. In this paper, we investigate several potential factors that could be associated with discriminatory performance of a recommendation algorithm for women versus men. We specifically study several characteristics of user profiles and analyze their possible associations with disparate behavior of the system towards different genders. These characteristics include the anomaly in rating behavior, the entropy of users' profiles, and the users' profile size. Our experimental results on a public dataset using four recommendation algorithms show that, based on all the three mentioned factors, women get less accurate recommendations than men indicating an unfair nature of recommendation algorithms across genders.

Fairness in recommender systems has recently received attention from researchers. Unfair recommendations have negative impact on the effectiveness of recommender systems as it may degrade users' satisfaction, loyalty, and at worst, it can lead to or perpetuate undesirable social dynamics. One of the factors that may impact fairness is calibration, the degree to which users' preferences on various item categories are reflected in the recommendations they receive. The ability of a recommendation algorithm for generating effective recommendations may depend on the meaningfulness of the input data and the amount of information available in users' profile. In this paper, we aim to explore the relationship between the consistency of users' ratings behavior and the degree of calibrated recommendations they receive. We conduct our analysis on different groups of users based on the consistency of their ratings. Our experimental results on a movie dataset and several recommendation algorithms show that there is a positive correlation between the consistency of users' ratings behavior and the degree of calibration in their recommendations, meaning that user groups with higher inconsistency in their ratings receive less calibrated recommendations.

Recently there has been a growing interest in fairness-aware recommender systems, including fairness in providing consistent performance across different users or groups of users. A recommender system could be considered unfair if the recommendations do not fairly represent the tastes of a certain group of users while other groups receive recommendations that are consistent with their preferences. In this paper, we use a metric called miscalibration for measuring how a recommendation algorithm is responsive to users' true preferences and we consider how various algorithms may result in different degrees of miscalibration. A well-known type of bias in recommendation is popularity bias where few popular items are over-represented in recommendations, while the majority of other items do not get significant exposure. We conjecture that popularity bias is one important factor leading to miscalibration in recommendation. Our experimental results using two real-world datasets show that there is a strong correlation between how different user groups are affected by algorithmic popularity bias and their level of interest in popular items. Moreover, we show algorithms with greater popularity bias amplification tend to have greater miscalibration.

Research on fairness in machine learning has been recently extended to recommender systems. One of the factors that may impact fairness is bias disparity, the degree to which a group's preferences on various item categories fail to be reflected in the recommendations they receive. In some cases biases in the original data may be amplified or reversed by the underlying recommendation algorithm. In this paper, we explore how different recommendation algorithms reflect the tradeoff between ranking quality and bias disparity. Our experiments include neighborhood-based, model-based, and trust-aware recommendation algorithms., Comment: Workshop on Recommendation in Multi-Stakeholder Environments (RMSE) at ACM RecSys 2019, Copenhagen, Denmark

Recommender systems are known to suffer from the popularity bias problem: popular (i.e. frequently rated) items get a lot of exposure while less popular ones are under-represented in the recommendations. Research in this area has been mainly focusing on finding ways to tackle this issue by increasing the number of recommended long-tail items or otherwise the overall catalog coverage. In this paper, however, we look at this problem from the users' perspective: we want to see how popularity bias causes the recommendations to deviate from what the user expects to get from the recommender system. We define three different groups of users according to their interest in popular items (Niche, Diverse and Blockbuster-focused) and show the impact of popularity bias on the users in each group. Our experimental results on a movie dataset show that in many recommendation algorithms the recommendations the users get are extremely concentrated on popular items even if a user is interested in long-tail and non-popular items showing an extreme bias disparity.

It is well known that explicit user ratings in recommender systems are biased towards high ratings, and that users differ significantly in their usage of the rating scale. Implementers usually compensate for these issues through rating normalization or the inclusion of a user bias term in factorization models. However, these methods adjust only for the central tendency of users' distributions. In this work, we demonstrate that lack of \textit{flatness} in rating distributions is negatively correlated with recommendation performance. We propose a rating transformation model that compensates for skew in the rating distribution as well as its central tendency by converting ratings into percentile values as a pre-processing step before recommendation generation. This transformation flattens the rating distribution, better compensates for differences in rating distributions, and improves recommendation performance. We also show a smoothed version of this transformation designed to yield more intuitive results for users with very narrow rating distributions. A comprehensive set of experiments show improved ranking performance for these percentile transformations with state-of-the-art recommendation algorithms in four real-world data sets.