Counterfactual explanations (CEs) provide an intuitive way to understand recommender systems by identifying minimal modifications to user-item interactions that alter recommendation outcomes. Existing CE methods for recommender systems, however, have been evaluated under heterogeneous protocols, using different datasets, recommenders, metrics, and even explanation formats, which hampers reproducibility and fair comparison. Our paper systematically reproduces, re-implement, and re-evaluate eleven state-of-the-art CE methods for recommender systems, covering both native explainers (e.g., LIME-RS, SHAP, PRINCE, ACCENT, LXR, GREASE) and specific graph-based explainers originally proposed for GNNs. Here, a unified benchmarking framework is proposed to assess explainers along three dimensions: explanation format (implicit vs. explicit), evaluation level (item-level vs. list-level), and perturbation scope (user interaction vectors vs. user-item interaction graphs). Our evaluation protocol includes effectiveness, sparsity, and computational complexity metrics, and extends existing item-level assessments to top-K list-level explanations. Through extensive experiments on three real-world datasets and six representative recommender models, we analyze how well previously reported strengths of CE methods generalize across diverse setups. We observe that the trade-off between effectiveness and sparsity depends strongly on the specific method and evaluation setting, particularly under the explicit format; in addition, explainer performance remains largely consistent across item level and list level evaluations, and several graph-based explainers exhibit notable scalability limitations on large recommender graphs. Our results refine and challenge earlier conclusions about the robustness and practicality of CE generation methods in recommender systems: https://github.com/L2R-UET/CFExpRec.

The commodity and widespread use of online shopping are having an unprecedented impact on climate, with emission figures from key actors that are easily comparable to those of a large-scale metropolis. Despite online shopping being fueled by recommender systems (RecSys) algorithms, the role and potential of the latter in promoting more sustainable choices is little studied. One of the main reasons for this could be attributed to the lack of a dataset containing carbon footprint emissions for the items. While building such a dataset is a rather challenging task, its presence is pivotal for opening the doors to novel perspectives, evaluations, and methods for RecSys research. In this article, we target this bottleneck and study the environmental role of RecSys algorithms. First, we mine a dataset that includes carbon footprint emissions for its items. Then, we benchmark conventional RecSys algorithms in terms of accuracy and sustainability as two faces of the same coin. We find that RecSys algorithms optimized for accuracy overlook greenness and that longer recommendation lists are greener but less accurate. Then, we show that a simple reranking approach that accounts for the item’s carbon footprint can establish a better trade-off between accuracy and greenness. This reranking approach is modular, ready to use, and can be applied to any RecSys algorithm without the need to alter the underlying mechanisms or retrain models. Our results show that a small sacrifice of accuracy can lead to significant improvements of recommendation greenness across all algorithms and list lengths. Arguably, this accuracy-greenness trade-off could even be seen as an enhancement of user satisfaction, particularly for purpose-driven users who prioritize the environmental impact of their choices. We anticipate this work will serve as the starting point for studying RecSys for more sustainable recommendations.

Popularity bias is a well-known challenge in recommender systems, where a small number of popular items receive disproportionate attention, while the majority of less popular items are largely overlooked.This imbalance often results in reduced recommendation quality and unfair exposure of items.Although existing mitigation techniques address this bias to some extent, they typically lack transparency in how they operate.In this paper, we propose a post-hoc method using a Sparse Autoencoder (SAE) to interpret and mitigate popularity bias in deep recommendation models.The SAE is trained to replicate a pre-trained model's behavior while enabling neuron-level interpretability.By introducing synthetic users with clear preferences for either popular or unpopular items, we identify neurons encoding popularity signals based on their activation patterns.We then adjust the activations of the most biased neurons to steer recommendations toward fairer exposure.Experiments on two public datasets using a sequential recommendation model show that our method significantly improves fairness with minimal impact on accuracy.Moreover, it offers interpretability and fine-grained control over the fairness-accuracy trade-off.

Recommender systems are known to exhibit fairness issues, particularly on the product side, where products and their associated suppliers receive unequal exposure in recommended results. While this problem has been widely studied in traditional recommendation settings, its implications for bundle recommendation (BR) remain largely unexplored. This emerging task introduces additional complexity: recommendations are generated at the bundle level, yet user satisfaction and product (or supplier) exposure depend on both the bundle and the individual items it contains. Existing fairness frameworks and metrics designed for traditional recommender systems may not directly translate to this multi-layered setting. In this paper, we conduct a comprehensive reproducibility study of product-side fairness in BR across three real-world datasets using four state-of-the-art BR methods. We analyze exposure disparities at both the bundle and item levels using multiple fairness metrics, uncovering important patterns. Our results show that exposure patterns differ notably between bundles and items, revealing the need for fairness interventions that go beyond bundle-level assumptions. We also find that fairness assessments vary considerably depending on the metric used, reinforcing the need for multi-faceted evaluation. Furthermore, user behavior plays a critical role: when users interact more frequently with bundles than with individual items, BR systems tend to yield fairer exposure distributions across both levels. Overall, our findings offer actionable insights for building fairer bundle recommender systems and establish a vital foundation for future research in this emerging domain.

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.

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.

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.

Recommender Systems are becoming an inherent part of today’s Internet. They can be found anywhere from e-commerce platforms (eBay, Amazon) to music or movie streaming (Spotify, Netflix), social media (Facebook, Instagram, TikTok), travel platforms (Booking.com, Expedia), and much more. Whether a recommendation is successful or not can rely on multiple objectives such as user satisfaction, business value, and societal issues. In addition, the long-term happiness (along with short-term excitements and delight) of the users is critical for a recommender system to be considered successful. MORS workshop brings together researchers and practitioners to discuss the importance of these aspects of recommender systems and find ways to develop algorithms to build multi-objective recommenders and also evaluation metrics to assess their success.

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 increase aggregate diversity to mitigate popularity bias and to improve the coverage of long-tail items in recommendations. In this article, 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, although it significantly improves exposure fairness and aggregate diversity, maintains an acceptable level of relevance of the recommendations.

Recommender systems are complex. They integrate the individual needs of users with the characteristics of particular domains of application which may span items from large and potentially heterogeneous collections. Extensive experimentation is required to understand the multidimensional properties of recommendation algorithms and the fit between algorithm and application. librec-auto is a tool that automates many aspects of off-line batch recommender system experimentation. It has a large library of state-of-the-art and historical recommendation algorithms and a wide variety of evaluation metrics. It further supports the study of diversity and fairness in recommendation through the integration of re-ranking algorithms and fairness-aware metrics. It supports declarative configuration for reproducible experiment management and supports multiple forms of hyper-parameter optimization.

Historically, the main criterion for a successful recommender system was the relevance of the recommended items to the user. In other words, the only objective for the recommendation algorithm was to learn user’s preferences for different items and generate recommendations accordingly. However, real-world recommender systems are well beyond a simple objective and often need to take into account multiple objectives simultaneously. These objectives can be either from the users’ perspective or they could come from other stakeholders such as item providers or any party that could be impacted by the recommendations. Such multi-objective and multi-stakeholder recommenders present unique challenges and these challenges were the focus of the MORS workshop.

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 important to optimize utilities not just for the end user, but also for other entities such as item sellers or producers who desire a fair representation of their items. Existing solutions either lack the multi-sided nature of fairness in recommendations, or do not properly address various aspects of multi-sided fairness in recommendations. In this thesis, we aim at first investigating the impact of unfair recommendations on the system and how it can negatively affect major entities in the system. Then, we seek to propose a general graph-based solution that works as a post processing approach after recommendation generation to tackle the unfairness of recommendations. We plan to perform extensive experiments to evaluate the effectiveness of the proposed approach.

It is well known that explicit user ratings in recommender systems are biased toward 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 a lack of 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 that a smoothed version of this transformation can yield more intuitive results for users with very narrow rating distributions. A comprehensive set of experiments, with state-of-the-art recommendation algorithms in four real-world datasets, show improved ranking performance for these percentile transformations.

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. In particular, we show that the impact of feedback loop is generally stronger for the users who belong to the minority group.

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.

Comparative experimentation is important for studying reproducibility in recommender systems. This is particularly true in areas without well-established methodologies, such as fairness-aware recommendation. In this paper, we describe fairness-aware enhancements to our recommender systems experimentation tool librec-auto. These enhancements include metrics for various classes of fairness definitions, extension of the experimental model to support result re-ranking and a library of associated re-ranking algorithms, and additional support for experiment automation and reporting. The associated demo will help attendees move quickly to configuring and running their own experiments with librec-auto.

Recommender systems research often requires the creation and execution of large numbers of algorithmic experiments to determine the sensitivity of results to the values of various hyperparameters. Existing recommender systems platforms fail to provide a basis for systematic experimentation of this type. In this paper, we describe librec-auto, a wrapper for the well-known LibRec library, which provides an environment that supports automated experimentation.