Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment
Preprint
Abstract
The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. All these four Human-Centric requirements are closely related to each other. With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious case study focused on automated recruitment: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles including image, text, and structured data, which are consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind automatic recruitment tools built this way (a common practice in many other application scenarios beyond recruitment) to extract sensitive information from unstructured data and exploit it in combination to data biases in undesirable (unfair) ways. We present an overview of recent works developing techniques capable of removing sensitive information and biases from the decision-making process of deep learning architectures, as well as commonly used databases for fairness research in AI. We demonstrate how learning approaches developed to guarantee privacy in latent spaces can lead to unbiased and fair automatic decision-making process.Keywords
All Related Versions
- Version 1, 2023-02-13, ArXiv
- Published version: SN Computer Science, 4 (5), 1.
This publication has 28 references indexed in Scilit:
- Sensitive loss: Improving accuracy and fairness of face representations with discrimination-aware deep learningArtificial Intelligence, 2022
- Understanding the role of individual units in a deep neural networkProceedings of the National Academy of Sciences of the United States of America, 2020
- Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosisProceedings of the National Academy of Sciences, 2020
- AI-enabled recruiting: What is it and how should a manager use it?Business Horizons, 2020
- Multiple classifiers in biometrics. part 1: Fundamentals and reviewInformation Fusion, 2018
- Word embeddings quantify 100 years of gender and ethnic stereotypesProceedings of the National Academy of Sciences of the United States of America, 2018
- Methods for interpreting and understanding deep neural networksDigital Signal Processing, 2018
- Multi-biometric template protection based on Homomorphic EncryptionPattern Recognition, 2017
- A data-driven approach to predict the success of bank telemarketingDecision Support Systems, 2014
- A simple procedure for pruning back-propagation trained neural networksIEEE Transactions on Neural Networks, 1990