Sampling Unknown Decision Functions to Build Classifier Copies

Unceta, Irene; Palacios, Diego Aguilar; Nin, Jordi; Pujol, Oriol

doi:10.1007/978-3-030-57524-3_16

Cited by 5 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It seems to shows interesting results in terms of Information Loss and Disclosure Risk. It is worth noting that the sampling process could be challenging depending on how the process sampling is done [ 46 ].…”

Section: Discussionmentioning

confidence: 99%

Toward a Comparison of Classical and New Privacy Mechanism

Heredia-Ductram

Núñez-del-Prado

Alatrista-Salas

2021

Entropy

View full text Add to dashboard Cite

In the last decades, the development of interconnectivity, pervasive systems, citizen sensors, and Big Data technologies allowed us to gather many data from different sources worldwide. This phenomenon has raised privacy concerns around the globe, compelling states to enforce data protection laws. In parallel, privacy-enhancing techniques have emerged to meet regulation requirements allowing companies and researchers to exploit individual data in a privacy-aware way. Thus, data curators need to find the most suitable algorithms to meet a required trade-off between utility and privacy. This crucial task could take a lot of time since there is a lack of benchmarks on privacy techniques. To fill this gap, we compare classical approaches of privacy techniques like Statistical Disclosure Control and Differential Privacy techniques to more recent techniques such as Generative Adversarial Networks and Machine Learning Copies using an entire commercial database in the current effort. The obtained results allow us to show the evolution of privacy techniques and depict new uses of the privacy-aware Machine Learning techniques.

show abstract

Section: Discussionmentioning

confidence: 99%

Toward a Comparison of Classical and New Privacy Mechanism

Heredia-Ductram

Núñez-del-Prado

Alatrista-Salas

2021

Entropy

View full text Add to dashboard Cite

show abstract

“…Moreover, these samples have been generated assuming a uniform probability distribution throughout the attribute domain. Using more sophisticated sampling techniques may ensure a better representation of the original decision boundary in the synthetic data and hence yield better accuracy results [ 73 ].…”

Section: Methodsmentioning

confidence: 99%

Differential Replication for Credit Scoring in Regulated Environments

Unceta

Nin

Pujol

2021

Entropy

Self Cite

View full text Add to dashboard Cite

Differential replication is a method to adapt existing machine learning solutions to the demands of highly regulated environments by reusing knowledge from one generation to the next. Copying is a technique that allows differential replication by projecting a given classifier onto a new hypothesis space, in circumstances where access to both the original solution and its training data is limited. The resulting model replicates the original decision behavior while displaying new features and characteristics. In this paper, we apply this approach to a use case in the context of credit scoring. We use a private residential mortgage default dataset. We show that differential replication through copying can be exploited to adapt a given solution to the changing demands of a constrained environment such as that of the financial market. In particular, we show how copying can be used to replicate the decision behavior not only of a model, but also of a full pipeline. As a result, we can ensure the decomposability of the attributes used to provide explanations for credit scoring models and reduce the time-to-market delivery of these solutions.

show abstract

“…Copying [41,43] or distilling [21] machine learning models can greatly contribute to model explainability. Overly complex models tend to be difficult to explain [7] and can become unaccountable [38].…”

Section: Fostering Explanations Through Simple Modelsmentioning

confidence: 99%

“…We now define what is copying a machine learning classifier [41][42][43]. We use the term original dataset to refer to a set of pairs 𝑋 = (𝑥 𝑖 , 𝑡 𝑖 ), 𝑖 = 1, ..., 𝑀, where 𝑥 𝑖 ∈ 𝑅 𝑑 is a set of 𝑑-dimensional data points in the original feature space D and 𝑡 𝑖 ∈ 1, ..., 𝐾 their corresponding labels.…”

Section: Fostering Explanations Through Simple Modelsmentioning

confidence: 99%

Desiderata for Explainable AI in Statistical Production Systems of the European Central Bank

Navarro

Kanellos

Gottron

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Explainable AI constitutes a fundamental step towards establishing fairness and addressing bias in algorithmic decision-making. Despite the large body of work on the topic, the benefit of solutions is mostly evaluated from a conceptual or theoretical point of view and the usefulness for real-world use cases remains uncertain. In this work, we aim to state clear user-centric desiderata for explainable AI reflecting common explainability needs experienced in statistical production systems of the European Central Bank. We link the desiderata to archetypical user roles and give examples of techniques and methods which can be used to address the user's needs. To this end, we provide two concrete use cases from the domain of statistical data production in central banks: the detection of outliers in the Centralised Securities Database and the data-driven identification of data quality checks for the Supervisory Banking data system. 1

show abstract

Sampling Unknown Decision Functions to Build Classifier Copies

Cited by 5 publications

References 13 publications

Toward a Comparison of Classical and New Privacy Mechanism

Toward a Comparison of Classical and New Privacy Mechanism

Differential Replication for Credit Scoring in Regulated Environments

Desiderata for Explainable AI in Statistical Production Systems of the European Central Bank

Contact Info

Product

Resources

About