A Unified Causal Framework for Auditing Recommender Systems for Ethical Concerns
As recommender systems become widely deployed in different domains, they increasingly influence their users' beliefs and preferences. Auditing recommender systems is crucial as it not only ensures the continuous improvement of recommendation algorithms but also safeguards against potential issues like biases and ethical concerns. In this paper, we view recommender system auditing from a causal lens and provide a general recipe for defining auditing metrics. Under this general causal auditing framework, we categorize existing auditing metrics and identify gaps in them -- notably, the lack of metrics for auditing user agency while accounting for the multi-step dynamics of the recommendation process. We leverage our framework and propose two classes of such metrics:future- and past-reacheability and stability, that measure the ability of a user to influence their own and other users' recommendations, respectively. We provide both a gradient-based and a black-box approach for computing these metrics, allowing the auditor to compute them under different levels of access to the recommender system. In our experiments, we demonstrate the efficacy of methods for computing the proposed metrics and inspect the design of recommender systems through these proposed metrics.
Code (0)
등록된 구현이 없습니다.
Tasks
Recommendation SystemsSimilar Papers 제목 키워드 기반
On the Need and Applicability of Causality for Fairness: A Unified Framework for AI Auditing and Legal Analysis
As Artificial Intelligence (AI) increasingly influences decisions in critical societal sectors, understanding and establishing causality becomes essential for evaluating the fairness of automated systems. This article ex…
BIG-bench Machine LearningCausal InferenceDecision MakingEpidemiology+1A Novel Generative Model with Causality Constraint for Mitigating Biases in Recommender Systems
Accurately predicting counterfactual user feedback is essential for building effective recommender systems. However, latent confounding bias can obscure the true causal relationship between user feedback and item exposur…
counterfactualRecommendation SystemsRepresentation LearningA Survey on Causal Inference for Recommendation
Causal inference has recently garnered significant interest among recommender system (RS) researchers due to its ability to dissect cause-and-effect relationships and its broad applicability across multiple fields. It of…
Causal InferencecounterfactualData AugmentationRecommendation Systems+1Causal Inference in Recommender Systems: A Survey and Future Directions
Recommender systems have become crucial in information filtering nowadays. Existing recommender systems extract user preferences based on the correlation in data, such as behavioral correlation in collaborative filtering…
Causal InferenceClick-Through Rate PredictionCollaborative FilteringRecommendation Systems+1On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges
Recently, recommender system (RS) based on causal inference has gained much attention in the industrial community, as well as the states of the art performance in many prediction and debiasing tasks. Nevertheless, a unif…
Causal InferencePredictionRecommendation Systems