Feature Removal Is a Unifying Principle for Model Explanation Methods

Covert, Ian; Lundberg, Scott; Lee, Su-In

doi:10.48550/arxiv.2011.03623

Cited by 10 publications

(15 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As illustration, both SHAP [70] and L2X [20] assign relevance scores to single features, however, while SHAP expresses relevance in terms of marginalized contributions of features across all possible subsets, L2X encodes relevance as a notion of informativeness on the response variable through maximizing mutual information. We refer to [12,26,104] for surveys and further details on selection methods.…”

Section: Feature-based Explanationsmentioning

confidence: 99%

Explainability in Music Recommender Systems

Afchar¹,

Melchiorre²,

Schedl³

et al. 2022

Preprint

View full text Add to dashboard Cite

The most common way to listen to recorded music nowadays is via streaming platforms which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of Music Recommender Systems (MRSs) has become essential. Current real-world MRSs are often quite complex and optimized for recommendation accuracy. They combine several building blocks based on collaborative filtering and content-based recommendation. This complexity can hinder the ability to explain recommendations to end users, which is particularly important for recommendations perceived as unexpected or inappropriate.While pure recommendation performance often correlates with user satisfaction, explainability has a positive impact on other factors such as trust and forgiveness, which are ultimately essential to maintain user loyalty.In this article, we discuss how explainability can be addressed in the context of MRSs. We provide perspectives on how explainability could improve music recommendation algorithms and enhance user experience. First, we review common dimensions and goals of recommenders' explainability and in general of eXplainable Artificial Intelligence (XAI), and elaborate on the extent to which these apply -or need to be adapted -to the specific characteristics of music consumption and recommendation. Then, we show how explainability components can be integrated within a MRS and in what form explanations can be provided. Since the evaluation of explanation quality is decoupled from pure accuracy-based evaluation criteria, we also discuss requirements and strategies for evaluating explanations of music recommendations. Finally, we describe the current challenges for introducing explainability within a large-scale industrial music recommender system and provide research perspectives.

show abstract

Section: Feature-based Explanationsmentioning

confidence: 99%

Explainability in Music Recommender Systems

Afchar¹,

Melchiorre²,

Schedl³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast, EP is a representative for perturbation-based methods [7,18,26]. EP searches for a set of a% of input pixels that maximizes the target-class confidence score.…”

Section: Gradcam and Extremal Perturbation (Ep)mentioning

confidence: 99%

“…Since 2013 [56], hundreds of research papers have either used attribution methods or proposed new ones [18,19]. Yet, it remains largely unknown how effective state-of-the-art AMs are in improving the performance of human-AI team on computer vision tasks.…”

Section: Introductionmentioning

confidence: 99%

The effectiveness of feature attribution methods and its correlation with automatic evaluation scores

Nguyen¹,

Kim²,

Nguyen³

2021

Preprint

View full text Add to dashboard Cite

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these tools in their work. However, despite humans being the target end-users, most attribution methods were only evaluated on proxy automatic-evaluation metrics [47,61,63]. In this paper, we conduct the first, large-scale user study on 320 lay and 11 expert users to shed light on the effectiveness of state-of-the-art attribution methods in assisting humans in ImageNet classification, Stanford Dogs fine-grained classification, and these two tasks but when the input image contains adversarial perturbations. We found that, in overall, feature attribution is surprisingly not more effective than showing humans nearest training-set examples. On a hard task of fine-grained dog categorization, presenting attribution maps to humans does not help, but instead hurts the performance of human-AI teams compared to AI alone. Importantly, we found automatic attribution-map evaluation measures to correlate poorly with the actual human-AI team performance. Our findings encourage the community to rigorously test their methods on the downstream human-in-the-loop applications and to rethink the existing evaluation metrics.

show abstract

“…causing black/grey dots in images). Blurring the input image only removed high-frequency signals, but did not remove low-frequency signals [3,27]. To this end, instead of setting specific baseline values, Covert et al [4] determined baseline values conditionally depending on the neighboring contexts.…”

Section: Introductionmentioning

confidence: 99%

Learning Baseline Values for Shapley Values

Ren¹,

Zhou²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper aims to formulate the problem of estimating the optimal baseline values for the Shapley value in game theory. The Shapley value measures the attribution of each input variable of a complex model, which is computed as the marginal benefit from the presence of this variable w.r.t. its absence under different contexts. To this end, people usually set the input variable to its baseline value to represent the absence of this variable (i.e. the no-signal state of this variable). Previous studies usually determine the baseline values in an empirical manner, which hurts the trustworthiness of the Shapley value. In this paper, we revisit the feature representation of a deep model from the perspective of game theory, and define the multi-variate interaction patterns of input variables to define the no-signal state of an input variable. Based on the multi-variate interaction, we learn the optimal baseline value of each input variable. Experimental results have demonstrated the effectiveness of our method.Preprint. Under review.

show abstract

Feature Removal Is a Unifying Principle for Model Explanation Methods

Cited by 10 publications

References 35 publications

Explainability in Music Recommender Systems

Explainability in Music Recommender Systems

The effectiveness of feature attribution methods and its correlation with automatic evaluation scores

Learning Baseline Values for Shapley Values

Contact Info

Product

Resources

About