Balanced Neighborhoods for Fairness-Aware Collaborative Recommendation

Burke, Robin; Sonboli, Nasim; Mansoury, Masoud; Ordonez-Gauger, Aldo

doi:10.18122/b2gq53

Cited by 98 publications

(152 citation statements)

References 11 publications

(9 reference statements)

Supporting

Mentioning

145

Contrasting

Unclassified

Order By: Relevance

“…We later randomly sample 100 products and manually decide if these products preserve any gender constraints based on their descriptions. Although 4 out of 100 products exhibit gender implications, 6 we don't find any strict constraints which prevent the unfavorable user identity group from consuming these products.…”

Section: Electronicsmentioning

confidence: 80%

“…A fairness-aware tensor-based algorithm is proposed to address the absolute statistical parity (i.e., items are expected to be presented at the same rate across groups) [32]. Several fairness metrics and their corresponding algorithms are proposed for both pointwise prediction frameworks [6,30] and pairwise ranking frameworks [3]. Methodologically, these algorithms can be summarized as reweighting schemes where underrepresented samples are upweighted [6,15,26] or schemes where additional fairness terms are added to regularize the model [1,3,30].…”

Section: Related Workmentioning

confidence: 99%

“…to users or items underrepresented in the input data. Such phenomena have already raised some attention from the recommender system community: a handful of types of algorithmic biases have been addressed, including selection bias [26], popularity bias [29], and several fairness-aware recommendation algorithms have been proposed [3,6]. In this paper, we focus on a relatively underexplored factor-marketing bias-in consumer-product interaction data, and study how recommendation algorithms respond to its effect.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Addressing Marketing Bias in Product Recommendations

Wan

Misra

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Modern collaborative filtering algorithms seek to provide personalized product recommendations by uncovering patterns in consumerproduct interactions. However, these interactions can be biased by how the product is marketed, for example due to the selection of a particular human model in a product image. These correlations may result in the underrepresentation of particular niche markets in the interaction data; for example, a female user who would potentially like motorcycle products may be less likely to interact with them if they are promoted using stereotypically 'male' images.In this paper, we first investigate this correlation between users' interaction feedback and products' marketing images on two realworld e-commerce datasets. We further examine the response of several standard collaborative filtering algorithms to the distribution of consumer-product market segments in the input interaction data, revealing that marketing strategy can be a source of bias for modern recommender systems. In order to protect recommendation performance on underrepresented market segments, we develop a framework to address this potential marketing bias. Quantitative results demonstrate that the proposed approach significantly improves the recommendation fairness across different market segments, with a negligible loss (or better) recommendation accuracy.

show abstract

Section: Electronicsmentioning

confidence: 80%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Addressing Marketing Bias in Product Recommendations

Wan

Misra

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…Similarly, Gillen et al [15] considered the fairness problem in online learning scenarios where the main objective is to minimize a game theoretic notion of regret. Also, fairness is studied in many other machine learning settings, including ranking [7], personalization and recommendation [4,5,25], data summarization [6], targeted advertisement [38], fair PCA [34], empirical risk minimization [9,19], privacy preserving [12] and a welfare-based measure of fairness [20]. Finally, due to the massive size of today's datasets, practical algorithms with fairness criteria should be able to scale.…”

Section: Related Workmentioning

confidence: 99%

Eliminating Latent Discrimination: Train Then Mask

Ghili

Kazemi²,

Karbasi

2019

SSRN Journal

View full text Add to dashboard Cite

How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness criteria, inspired by the well-understood notion of omitted variable-bias in statistics and econometrics. Our notion of fairness effectively controls for sensitive features and provides diagnostics for deviations from fair decision making. We then establish analytical and algorithmic results about the existence of a fair classifier in the context of supervised learning. Our results readily imply a simple, but rather counter-intuitive, strategy for eliminating latent discrimination. In order to prevent other features proxying for sensitive features, we need to include sensitive features in the training phase, but exclude them in the test/evaluation phase while controlling for their effects. We evaluate the performance of our algorithm on several real-world datasets and show how fairness for these datasets can be improved with a very small loss in accuracy.

show abstract

“…. $15.00 https://doi.org/10.1145/3289600.3291002 might offer unfair or unequal quality of service to indvidual (or groups of) users [5,8] or lead to societal polarization by increasing the divergence between preferences of individual (or groups of) users [13].…”

Section: Introductionmentioning

confidence: 99%

Fighting Fire with Fire

Rastegarpanah

Gummadi

Crovella

2019

Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

The increasing role of recommender systems in many aspects of society makes it essential to consider how such systems may impact social good. Various modifications to recommendation algorithms have been proposed to improve their performance for specific socially relevant measures. However, previous proposals are often not easily adapted to different measures, and they generally require the ability to modify either existing system inputs, the system's algorithm, or the system's outputs. As an alternative, in this paper we introduce the idea of improving the social desirability of recommender system outputs by adding more data to the input, an approach we view as providing 'antidote' data to the system. We formalize the antidote data problem, and develop optimization-based solutions. We take as our model system the matrix factorization approach to recommendation, and we propose a set of measures to capture the polarization or fairness of recommendations. We then show how to generate antidote data for each measure, pointing out a number of computational efficiencies, and discuss the impact on overall system accuracy. Our experiments show that a modest budget for antidote data can lead to significant improvements in the polarization or fairness of recommendations.

show abstract

Balanced Neighborhoods for Fairness-Aware Collaborative Recommendation

Cited by 98 publications

References 11 publications

Addressing Marketing Bias in Product Recommendations

Addressing Marketing Bias in Product Recommendations

Eliminating Latent Discrimination: Train Then Mask

Fighting Fire with Fire

Contact Info

Product

Resources

About