Counterfactual Explanations for Neural Recommenders

Tran, Khanh Hiep; Ghazimatin, Azin; Roy, Rishiraj Saha

doi:10.1145/3506804

Cited by 14 publications

(15 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this approach is only applicable to PageRank-based recommender models, and cannot be easily adapted to other model categories. In addition, Tran et al [53] propose a white-box explaining approach on Neural-CF models. The approach is based on the influence function [36] which estimates the influence of a training sample on the current model prediction.…”

Section: Counterfactual Machine Learningmentioning

confidence: 99%

Counterfactually Evaluating Explanations in Recommender Systems

Yao¹,

Wang²,

Li³

2022

Preprint

View full text Add to dashboard Cite

Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a significant challenge for researchers and practitioners. Prior work mainly conducts human study to evaluate explanation quality, which is usually expensive, time-consuming, and prone to human bias. In this paper, we propose an offline evaluation method that can be computed without human involvement. To evaluate an explanation, our method quantifies its counterfactual impact on the recommendation. To validate the effectiveness of our method, we carry out an online user study. We show that, compared to conventional methods, our method can produce evaluation scores more correlated with the real human judgments, and therefore can serve as a better proxy for human evaluation. In addition, we show that explanations with high evaluation scores are considered better by humans. Our findings highlight the promising direction of using the counterfactual approach as one possible way to evaluate recommendation explanations.

show abstract

Section: Counterfactual Machine Learningmentioning

confidence: 99%

Counterfactually Evaluating Explanations in Recommender Systems

Yao¹,

Wang²,

Li³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to text-based or image-based explainable recommendation, knowledge-aware explainable recommendation has also attracted research attention recently, such as [3,18,60,63,64]. Works using counterfactual reasoning to improve recommendation explainability [31,[56][57][58]67] have been proposed very recently. Ghazimatin et al [31] tried to generate provider-side counterfactual explanations by looking for a minimal set of user's historical actions (e.g.…”

Section: Explainable Recommendationmentioning

confidence: 99%

“…Xu et al [67] proposed to improve this by using perturbation model to obtain counterfactuals. Tran et al [58] adopted influence functions for identifying training points most relevant to a recommendation while deducing a counterfactual set for explanations. Tan et al [57] proposed to generate and evaluate explanations that considers the causal relations to the outcome.…”

Section: Explainable Recommendationmentioning

confidence: 99%

Explainable Fairness in Recommendation

Ge,

Tan,

Zhu

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing research on fairness-aware recommendation has mainly focused on the quantification of fairness and the development of fair recommendation models, neither of which studies a more substantial problem-identifying the underlying reason of model disparity in recommendation. This information is critical for recommender system designers to understand the intrinsic recommendation mechanism and provides insights on how to improve model fairness to decision makers. Fortunately, with the rapid development of Explainable AI, we can use model explainability to gain insights into model (un)fairness. In this paper, we study the problem of explainable fairness, which helps to gain insights about why a system is fair or unfair, and guides the design of fair recommender systems with a more informed and unified methodology. Particularly, we focus on a common setting with feature-aware recommendation and exposure unfairness, but the proposed explainable fairness framework is general and can be applied to other recommendation settings and fairness definitions. We propose a Counterfactual Explainable Fairness framework, called CEF, which generates explanations about model fairness that can improve the fairness without significantly hurting the performance. The CEF framework formulates an optimization problem to learn the "minimal" change of the input features that changes the recommendation results to a certain level of fairness. Based on the counterfactual recommendation result of each feature, we calculate an explainability score in terms of the fairness-utility trade-off to rank all the feature-based explanations, and select the top ones as fairness explanations. Experimental results on several real-world datasets validate that our method is able to effectively provide explanations to the model disparities and these explanations can achieve better fairness-utility trade-off when using them for recommendation than all the baselines. CCS CONCEPTS• Computing methodologies → Artificial intelligence.

show abstract

“…The former mainly leverages inverse propensity scoring [37,51] and doubly robust [21] to debias user feedback. SCMs typically abstract causal relationships into causal graph and estimate causal effects via intervention [48,57] or counterfactual inference [52,55], which are widely used for debiasing [48], explainable [44,46], and out-ofdistribution recommendations [50]. Nevertheless, using causality for diversity or alleviating filter bubbles receives little scrutiny.…”

Section: Related Workmentioning

confidence: 99%

User-controllable Recommendation Against Filter Bubbles

Wang,

Feng,

Nie

et al. 2022

Preprint

View full text Add to dashboard Cite

Recommender systems usually face the issue of filter bubbles: overrecommending homogeneous items based on user features and historical interactions. Filter bubbles will grow along the feedback loop and inadvertently narrow user interests. Existing work usually mitigates filter bubbles by incorporating objectives apart from accuracy such as diversity and fairness. However, they typically sacrifice accuracy, hurting model fidelity and user experience. Worse still, users have to passively accept the recommendation strategy and influence the system in an inefficient manner with high latency, e.g., keeping providing feedback (e.g., like and dislike) until the system recognizes the user intention.This work proposes a new recommender prototype called User-Controllable Recommender System (UCRS), which enables users to actively control the mitigation of filter bubbles. Functionally, 1) UCRS can alert users if they are deeply stuck in filter bubbles.2) UCRS supports four kinds of control commands for users to mitigate the bubbles at different granularities. 3) UCRS can respond to the controls and adjust the recommendations on the fly. The key to adjusting lies in blocking the effect of out-of-date user representations on recommendations, which contains historical information inconsistent with the control commands. As such, we develop a causality-enhanced User-Controllable Inference (UCI) framework, which can quickly revise the recommendations based on user controls in the inference stage and utilize counterfactual inference to mitigate the effect of out-of-date user representations. Experiments on three datasets validate that the UCI framework can effectively recommend more desired items based on user controls, showing promising performance w.r.t. both accuracy and diversity. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Counterfactual Explanations for Neural Recommenders

Cited by 14 publications

References 0 publications

Counterfactually Evaluating Explanations in Recommender Systems

Counterfactually Evaluating Explanations in Recommender Systems

Explainable Fairness in Recommendation

User-controllable Recommendation Against Filter Bubbles

Contact Info

Product

Resources

About