Ranking Data Slices for ML Model Validation: A Shapley Value Approach

Farchi, Eitan; Narayanam, Ramasuri; Nagalapatti, Lokesh

doi:10.1109/icde51399.2021.00180

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…if E is empty then Algorithm 5 SliceLine Enumeration Algorithm [62] Input: Feature matrix 𝑋 0 , errors 𝑒, 𝐾 = 4, 𝜎 = 32, 𝛼 = 0. Farchi et al [23] propose Shapley Slice Ranking Mechanism with focus on Error concentration (SSR-E) as an approach to rank data slices by the order of being problematic. However, they assume the slices are given as an input and they use the notion of Shapley value to rank the slices.…”

mentioning

confidence: 99%

Representation Bias in Data: A Survey on Identification and Resolution Techniques

Shahbazi¹,

Li²,

Asudeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

The grand goal of data-driven decision-making is to help humans make decisions, not only easily and at scale but also wisely, accurately, and just. However, data-driven algorithms are only as good as the data they work with, while data sets, especially social data, often miss representing minorities. Representation Bias in data can happen due to various reasons ranging from historical discrimination to selection and sampling biases in the data acquisition and preparation methods. One cannot expect AI-based societal solutions to have equitable outcomes without addressing the representation bias. This paper surveys the existing literature on representation bias in the data. It presents a taxonomy to categorize the studied techniques based on multiple design dimensions and provide a side-by-side comparison of their properties. There is still a long way to fully address representation bias issues in data. The authors hope that this survey motivates researchers to approach these challenges in the future by observing existing work within their respective domains.

show abstract

mentioning

confidence: 99%

Representation Bias in Data: A Survey on Identification and Resolution Techniques

Shahbazi¹,

Li²,

Asudeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The rank is calculated by a smooth polynomial fit on these two properties across all slices found on the dataset. An alternative ranking is presented in[8].…”

mentioning

confidence: 99%

“…Available at https://archive.ics.uci.edu/ml/datasets/adult6 Original paper,[5]; available at https://archive.ics.uci.edu/ml/datasets/Avila#7 Original paper,[17]; available at https://archive.ics.uci.edu/ml/datasets/default+of+ credit+card+clients8 Original paper,[3]; available at https://archive.ics.uci.edu/ml/datasets/Electrical+ Grid+Stability+Simulated+Data+…”

mentioning

confidence: 99%

FreaAI: Automated Extraction of Data Slices to Test Machine Learning Models

Ackerman

Raz

Zalmanovici

2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

Machine learning (ML) solutions are prevalent. However, many challenges exist in making these solutions businessgrade. One major challenge is to ensure that the ML solution provides its expected business value. In order to do that, one has to bridge the gap between the way ML model performance is measured and the solution requirements. In previous work (Barash et al. 2019) we demonstrated the effectiveness of utilizing feature models in bridging this gap. Whereas ML performance metrics, such as the accuracy or F1-score of a classifier, typically measure the average ML performance, feature models shed light on explainable data slices that are too far from that average, and therefore might indicate unsatisfied requirements. For example, the overall accuracy of a bank text terms classifier may be very high, say 98% ± 2%, yet it might perform poorly for terms that include short descriptions and originate from commercial accounts. A business requirement, which may be implicit in the training data, may be to perform well regardless of the type of account and length of the description. Therefore, the under-performing data slice that includes short descriptions and commercial accounts suggests poorly-met requirements. In this paper we show the feasibility of automatically extracting feature models that result in explainable data slices over which the ML solution under-performs. Our novel technique, IBM FreaAI aka FreaAI, extracts such slices from structured ML test data or any other labeled data. We demonstrate that FreaAI can automatically produce explainable and statistically-significant data slices over seven open datasets.

show abstract