Collaborative Filtering (CF) based recommenders often exhibit model biases, delivering strong recommendation utility to certain users or items at the expense of others. Prior research approaches these biases as isolated and standalone issues, ignoring their interconnected nature and developing separate methods, thereby compromising the specialized debiasing efforts. Thus, we introduce a boosting-based framework designed to alleviate a broad spectrum of biases. This framework employs a series of sub-models, each tailored for different user and item subgroups. Theoretically, our model ensures an exponentially decreasing upper bound on the training loss across all user and item types with increasing boosting iterations. Extensive experiments demonstrate its superior debiasing capabilities against state-of-the-art methods across four model bias types. Appendix, data and code are available at https://github.com/JP-25/CFBoost

Effective labeled data collection plays a critical role in developing and fine-tuning robust streaming analytics systems. However, continuously labeling documents to filter relevant information poses significant challenges like limited labeling budget or lack of high-quality labels. There is a need for efficient human-in-the-loop machine learning (HITL-ML) design to improve streaming analytics systems. One particular HITL-ML approach is online active learning, which involves iteratively selecting a small set of the most informative documents for labeling to enhance the ML model performance. The performance of such algorithms can get affected due to human errors in labeling. To address these challenges, we propose ORIS, a method to perform Online active learning using Reinforcement learning-based Inclusive Sampling of documents for labeling. ORIS aims to create a novel Deep Q-Network-based strategy to sample incoming documents that minimize human errors in labeling and enhance the ML model performance. We evaluate the ORIS method on emotion recognition tasks, and it outperforms traditional baselines in terms of both human labeling performance and the ML model performance. The code for this research is available at https://github.com/rpandey4/oris.

Cross-domain recommendation (CDR) has emerged as a promising solution to alleviating the cold-start problem by leveraging information from an auxiliary source domain to generate recommendations in a target domain. Most CDR techniques fall into a category known as bridge-based methods, but many of them fail to account for the structure and rating behavior of target users from the source domain into the recommendation process. Therefore, we present a novel framework called Vietoris-Rips Complex for Cross-Domain Recommendation (VRCDR), which utilizes the Vietoris-Rips Complex (a technique from computational geometry) to understand the underlying structure in user behavior from the source domain, and includes the learned information into recommendations in the target domain to make the recommendations more personalized to users' niche preferences. Extensive experiments on large, real-world datasets demonstrate that VRCDR consistently improves recommendations compared to state-of-the-art bridge-based CDR methods.

Machine Unlearning (MU) algorithms have become increasingly critical due to the imperative adherence to data privacy regulations.The primary objective of MU is to erase the influence of specific data samples on a given model without the need to retrain it from scratch.Accordingly, existing methods focus on maximizing user privacy protection.However, there are different degrees of privacy regulations for each real-world web-based application.Exploring the full spectrum of trade-offs between privacy, model utility, and runtime efficiency is critical for practical unlearning scenarios.Furthermore, designing the MU algorithm with simple control of the aforementioned trade-off is desirable but challenging due to the inherent complex interaction.To address the challenges, we present Controllable Machine Unlearning (ConMU), a novel framework designed to facilitate the calibration of MU.The ConMU framework contains three integral modules: an important data selection module that reconciles the runtime efficiency and model generalization, a progressive Gaussian mechanism module that balances privacy and model generalization, and an unlearning proxy that controls the trade-offs between privacy and runtime efficiency.Comprehensive experiments on various benchmark datasets have demonstrated the robust adaptability of our control mechanism and its superiority over established unlearning methods.ConMU explores the full spectrum of the Privacy-Utility-Efficiency trade-off and allows practitioners to account for different real-world regulations.

This paper addresses the critical gap in the unbiased estimation of post-click conversion rate (CVR) in recommender systems. Existing CVR prediction methods, such as Inverse Propensity Score (IPS) and various Doubly Robust (DR) based estimators, overlook the impact of propensity estimation on the model bias and variance, thus leading to a debiasing performance gap. We propose a Generalized Propensity Learning (GPL) framework to directly minimize the bias and variance in CVR prediction models. The proposed method works as a complement to existing methods like IPS, DR, MRDR, and DRMSE to improve prediction performance by reducing their bias and variance. Extensive experiments on real-world datasets and semi-synthetic datasets demonstrate the significant performance promotion brought by our proposed method. Data and code can be found at: https://github.com/yuqing-zhou/GPL.

Conversational recommenders are emerging as a powerful tool to personalize a user’s recommendation experience. Through a back-and-forth dialogue, users can quickly hone in on just the right items. Many approaches to conversational recommendation, however, only partially explore the user preference space and make limiting assumptions about how user feedback can be best incorporated, resulting in long dialogues and poor recommendation performance. In this paper, we propose a novel conversational recommendation framework with two unique features: (i) a greedy NDCG attribute selector, to enhance user personalization in the interactive preference elicitation process by prioritizing attributes that most effectively represent the actual preference space of the user; and (ii) a user representation refiner, to effectively fuse together the user preferences collected from the interactive elicitation process to obtain a more personalized understanding of the user. Through extensive experiments on four frequently used datasets, we find the proposed framework not only outperforms all the state-of-the-art conversational recommenders (in terms of both recommendation performance and conversation efficiency), but also provides a more personalized experience for the user under the proposed multi-groundtruth multi-round conversational recommendation setting.

Conversational recommender systems (CRS) have shown great success in accurately capturing a user's current and detailed preference through the multi-round interaction cycle while effectively guiding users to a more personalized recommendation. Perhaps surprisingly, conversational recommender systems can be plagued by popularity bias, much like traditional recommender systems. In this paper, we systematically study the problem of popularity bias in CRSs. We demonstrate the existence of popularity bias in existing state-of-the-art CRSs from an exposure rate, a success rate, and a conversational utility perspective, and propose a suite of popularity bias metrics designed specifically for the CRS setting. We then introduce a debiasing framework with three unique features: (i) Popularity-Aware Focused Learning, to reduce the popularity-distorting impact on preference prediction; (ii) Cold-Start Item Embedding Reconstruction via Attribute Mapping, to improve the modeling of cold-start items; and (iii) Dual-Policy Learning, to better guide the CRS when dealing with either popular or unpopular items. Through extensive experiments on two frequently used CRS datasets, we find the proposed model-agnostic debiasing framework not only mitigates the popularity bias in state-of-the-art CRSs but also improves the overall recommendation performance.

In collaborative filtering, the quality of recommendations critically relies on how easily a model can find similar users for a target user. Hence, a niche user who prefers items out of the mainstream may receive poor recommendations, while a mainstream user sharing interests with many others will likely receive recommendations of higher quality. In this work, we study this mainstream bias centering around three key thrusts. First, to distinguish mainstream and niche users, we explore four approaches based on outlier detection techniques to identify a mainstream score indicating the mainstream level for each user. Second, we empirically show that severe mainstream bias is produced by conventional recommendation models. Last, we explore both global and local methods to mitigate the bias. Concretely, we propose two global models: Distribution Calibration (DC) and Weighted Loss (WL) methods; and one local method: Local Fine Tuning (LFT) method. Extensive experiments show the effectiveness of the proposed methods to improve utility for niche users and also show that the proposed LFT can improve the utility for mainstream users at the same time.

The learning-to-rank problem aims at ranking items to maximize exposure of those most relevant to a user query. A desirable property of such ranking systems is to guarantee some notion of fairness among specified item groups. While fairness has recently been considered in the context of learning-to-rank systems, current methods cannot provide guarantees on the fairness of the predicted rankings. This paper addresses this gap and introduces Smart Predict and Optimize for Fair Ranking (SPOFR), an integrated optimization and learning framework for fairness-constrained learning to rank. The end-to-end SPOFR framework includes a constrained optimization sub-model and produces ranking policies that are guaranteed to satisfy fairness constraints, while allowing for fine control of the fairness-utility tradeoff. SPOFR is shown to significantly improve on current state-of-the-art fair learning-to-rank systems with respect to established performance metrics.

Popularity bias is a long-standing challenge in recommender systems: popular items are overly recommended at the expense of less popular items that users may be interested in being under-recommended. Such a bias exerts detrimental impact on both users and item providers, and many efforts have been dedicated to studying and solving such a bias. However, most existing works situate the popularity bias in a static setting, where the bias is analyzed only for a single round of recommendation with logged data. These works fail to take account of the dynamic nature of real-world recommendation process, leaving several important research questions unanswered: how does the popularity bias evolve in a dynamic scenario? what are the impacts of unique factors in a dynamic recommendation process on the bias? and how to debias in this long-term dynamic process? In this work, we investigate the popularity bias in dynamic recommendation and aim to tackle these research gaps. Concretely, we conduct an empirical study by simulation experiments to analyze popularity bias in the dynamic scenario and propose a dynamic debiasing strategy and a novel False Positive Correction method utilizing false positive signals to debias, which show effective performance in extensive experiments.

Session-based recommender systems aim to improve recommendations in short-term sessions that can be found across many platforms.A critical challenge is to accurately model user intent with only limited evidence in these short sessions.For example, is a flower bouquet being viewed meant as part of a wedding purchase or for home decoration?Such different perspectives greatly impact what should be recommended next.Hence, this paper proposes a novel sessionbased recommendation system empowered by hypergraph attention networks.Three unique properties of the proposed approach are: (i) it constructs a hypergraph for each session to model the item correlations defined by various contextual windows in the session simultaneously, to uncover item meanings; (ii) it is equipped with hypergraph attention layers to generate item embeddings by flexibly aggregating the contextual information from correlated items in the session; and (iii) it aggregates the dynamic item representations for each session to infer the general purpose and current need, which is decoded to infer the next interesting item in the session.Through experiments on three benchmark datasets, we find the proposed model is effective in generating informative dynamic item embeddings and providing more accurate recommendations compared to the state-of-the-art.

This paper investigates recommendation fairness among new items. While previous efforts have studied fairness in recommender systems and shown success in improving fairness, they mainly focus on scenarios where unfairness arises due to biased prior user-feedback history (like clicks or views). Yet, it is unknown whether new items without any feedback history can be recommended fairly, and if unfairness does exist, how can we provide fair recommendations among these new items in such a cold-start scenario. In detail, we first formalize fairness among new items with the well-known concepts of equal opportunity and Rawlsian Max-Min fairness. We empirically show the prevalence of unfairness in cold start recommender systems. Then we propose a novel learnable post-processing framework as a model blueprint for enhancing fairness, with which we propose two concrete models: a joint-learning generative model, and a score scaling model. Extensive experiments over four public datasets show the effectiveness of the proposed models for enhancing fairness while also preserving recommendation utility.

This paper connects equal opportunity to popularity bias in implicit recommenders to introduce the problem of popularity-opportunity bias. That is, conditioned on user preferences that a user likes both items, the more popular item is more likely to be recommended (or ranked higher) to the user than the less popular one. This type of bias is harmful, exerting negative effects on the engagement of both users and item providers. Thus, we conduct a three-part study: (i) By a comprehensive empirical study, we identify the existence of the popularity-opportunity bias in fundamental matrix factorization models on four datasets; (ii) coupled with this empirical study, our theoretical study shows that matrix factorization models inherently produce the bias; and (iii) we demonstrate the potential of alleviating this bias by both in-processing and post-processing algorithms. Extensive experiments on four datasets show the effective debiasing performance of these proposed methods compared with baselines designed for conventional popularity bias.

To mitigate the rabbit hole effect in recommendations, conventional distribution-aware recommendation systems aim to ensure that a user’s prior interest areas are reflected in the recommendations that the system makes. For example, a user who historically prefers comedies to dramas by 2:1 should see a similar ratio in recommended movies. Such approaches have proven to be an important building block for recommendation tasks. However, existing distribution-aware approaches enforce that the target taste distribution should exactly match a user’s prior interests (typically revealed through training data), based on the assumption that users’ taste distribution is fundamentally static. This assumption can lead to large estimation errors. We empirically identify this taste distortion problem through a data-driven study over multiple datasets. We show how taste preferences dynamically shift and how the design of a calibration mechanism should be designed with these shifts in mind. We further demonstrate how to incorporate these shifts into a taste enhanced calibrated recommender system, which results in simultaneously mitigated both the rabbit hole effect and taste distortion problem.

Modern recommenders usually consider both collaborative features from user behavior data (e.g., clicks) and content information about the users and items (e.g., user ages or item images) for improved recommendations. While encouraging, the uncovered user preference representations derived from these collaborative and content-based perspectives can be entangled by intermixing the influence from each other, leading to sub-optimal performance and unstable recommendations. Hence, we propose to disentangle representations learned from user behavior data and content information. Specifically, we propose a novel two-level disentanglement generative recommendation model (DICER) that supports both content-collaborative disentanglement and feature disentanglement: for the content-collaborative disentanglement, DICER decomposes the features by their marginal distributions based on content and user-item interactions, to ensure the learned features from each type are statistically independent. For feature disentanglement, by decomposing the Kullback-Leibler divergence, we theoretically show that extracted features within each type are disentangled at a granular level. Furthermore, DICER utilizes a co-decoder that simultaneously decodes the content and user-item interactions to ensure the high-quality of learned features. Through extensive experiments on three real-world datasets, results show that DICER significantly outperforms other state-of-the-art methods by 13.5% in NDCG and 14.4% in hit ratio on average.

This paper focuses on how to generate unbiased recommendations based on biased implicit user-item interactions. We propose a combinational joint learning framework to simultaneously learn unbiased user-item relevance and unbiased propensity. More specifically, we first present a new unbiased objective function for estimating propensity. We then show how a naïve joint learning approach faces an estimation-training overlap problem. Hence, we propose to jointly train multiple sub-models from different parts of the training dataset to avoid this problem. Finally, we show how to incorporate residual components trained by the complete training data to complement the relevance and propensity sub-models. Extensive experiments on two public datasets demonstrate the effectiveness of the proposed model with an improvement of 4% on average over the best alternatives.

The cold start problem is a long-standing challenge in recommender systems. That is, how to recommend for new users and new items without any historical interaction record? Recent ML-based approaches have made promising strides versus traditional methods. These ML approaches typically combine both user-item interaction data of existing warm start users and items (as in CF-based methods) with auxiliary information of users and items such as user profiles and item content information (as in content-based methods). However, such approaches face key drawbacks including the error superimposition issue that the auxiliary-to-CF transformation error increases the final recommendation error; the ineffective learning issue that long distance from transformation functions to model output layer leads to ineffective model learning; and the unified transformation issue that applying the same transformation function for different users and items results in poor transformation.

Recommendation algorithms typically build models based on user-item interactions (e.g., clicks, likes, or ratings) to provide a personalized ranked list of items. These interactions are often distributed unevenly over different groups of items due to varying user preferences. However, we show that recommendation algorithms can inherit or even amplify this imbalanced distribution, leading to item under-recommendation bias. Concretely, we formalize the concepts of ranking-based statistical parity and equal opportunity as two measures of item under-recommendation bias. Then, we empirically show that one of the most widely adopted algorithms -- Bayesian Personalized Ranking -- produces biased recommendations, which motivates our effort to propose the novel debiased personalized ranking model. The debiased model is able to improve the two proposed bias metrics while preserving recommendation performance. Experiments on three public datasets show strong bias reduction of the proposed model versus state-of-the-art alternatives.

Recommendation systems typically rely on the interactions between a crowd of ordinary users and items, ignoring the fact that many real-world communities are notably influenced by a small group of key opinion leaders, whose feedback on items wields outsize influence. With important positions in the community (e.g. have a large number of followers), their elite opinions are able to diffuse to the community and further impact what items we buy, what media we consume, and how we interact with online platforms. Hence, this paper investigates how to develop a novel recommendation system by explicitly capturing the influence from key opinion leaders to the whole community. Centering around opinion elicitation and diffusion, we propose an end-to-end Graph-based neural model - GoRec. Specifically, to preserve the multi-relations between key opinion leaders and items, GoRec elicits the opinions from key opinion leaders with a translation-based embedding method. Moreover, GoRec adopts the idea of Graph Neural Networks to model the elite opinion diffusion process for improved recommendation. Through experiments on Goodreads and Epinions, the proposed model outperforms state-of-the-art approaches by 10.75% and 9.28% on average in Top-K item recommendation.

We propose a personalized user recommendation framework for content curation platforms that models preferences for both users and the items they engage with simultaneously. In this way, user preferences for specific item types (e.g., fantasy novels) can be balanced with user specialties (e.g., reviewing novels with strong female protagonists). In particular, the proposed model has three unique characteristics: (i) it simultaneously learns both user-item and user-user preferences through a multi-aspect autoencoder model; (ii) it fuses the latent representations of user preferences on users and items to construct shared factors through an adversarial framework; and (iii) it incorporates an attention layer to produce weighted aggregations of different latent representations, leading to improved personalized recommendation of users and items. Through experiments against state-of-the-art models, we find the proposed framework leads to a 18.43% (Goodreads) and 6.14% (Spotify) improvement in top-k user recommendation.

The importance of the distribution of ratings on recommender systems (RS) is well-recognized. And yet, recommendation approaches based on latent factor models and recently introduced neural variants (e.g., NCF) optimize for the head of these distributions, potentially leading to large estimation errors for tail ratings. These errors in tail ratings that are far from the mean predicted rating fall out of a uni-modal assumption underlying these popular models, as we show in this paper. We propose to improve the estimation of tail ratings by extending traditional single latent representations (e.g., an item is represented by a single latent vector) with new multi-latent representations for better modeling these tail ratings. We show how to incorporate these multi-latent representations in an end-to-end neural prediction model that is designed to better reflect the underlying ratings distributions of items. Through experiments over six datasets, we find the proposed model leads to a significant improvement in RMSE versus a suite of benchmark methods. We also find that the predictions for the most polarized items are improved by more than 15%.

Predicting the potential target customers for a product is essential. However, traditional recommender systems typically aim to optimize an engagement metric without considering the overall distribution of target customers, thereby leading to serious distortion problems. In this paper, we conduct a data-driven study to reveal several distortions that arise from conventional recommenders. Toward overcoming these issues, we propose a target customer re-ranking algorithm to adjust the population distribution and composition in the Top-k target customers of an item while maintaining recommendation quality. By applying this proposed algorithm onto a real-world dataset, we find the proposed method can effectively make the class distribution of items’ target customers close to the desired distribution, thereby mitigating distortion.

In this paper, we propose a Joint Collaborative Autoencoder framework that learns both user-user and item-item correlations simultaneously, leading to a more robust model and improved top-K recommendation performance. More specifically, we show how to model these user-item correlations and demonstrate the importance of careful normalization to alleviate the influence of feedback heterogeneity. Further, we adopt a pairwise hinge-based objective function to maximize the top-K precision and recall directly for top-K recommenders. Finally, a mini-batch optimization algorithm is proposed to train the proposed model. Extensive experiments on three public datasets show the effectiveness of the proposed framework over state-of-the-art non-neural and neural alternatives.

Tensor-based methods have shown promise in improving upon traditional matrix factorization methods for recommender systems. But tensors may achieve improved recommendation quality while worsening the fairness of the recommendations. Hence, we propose a novel fairness-aware tensor recommendation framework that is designed to maintain quality while dramatically improving fairness. Four key aspects of the proposed framework are: (i) a new sensitive latent factor matrix for isolating sensitive features; (ii) a sensitive information regularizer that extracts sensitive information which can taint other latent factors; (iii) an effective algorithm to solve the proposed optimization model; and (iv) extension to multi-feature and multi-category cases which previous efforts have not addressed. Extensive experiments on real-world and synthetic datasets show that the framework enhances recommendation fairness while preserving recommendation quality in comparison with state-of-the-art alternatives.

We propose PsiRec, a novel user preference propagation recommender that incorporates pseudo-implicit feedback for enriching the original sparse implicit feedback dataset. Three of the unique characteristics of PsiRec are: (i) it views user-item interactions as a bipartite graph and models pseudo-implicit feedback from this perspective; (ii) its random walks-based approach extracts graph structure information from this bipartite graph, toward estimating pseudo-implicit feedback; and (iii) it adopts a Skip-gram inspired measure of confidence in pseudo-implicit feedback that captures the pointwise mutual information between users and items. This pseudo-implicit feedback is ultimately incorporated into a new latent factor model to estimate user preference in cases of extreme sparsity. PsiRec results in improvements of 21.5% and 22.7% in terms of Precision@10 and Recall@10 over state-of-the-art Collaborative Denoising Auto-Encoders. Our implementation is available at https://github.com/heyunh2015/PsiRecICDM2018.