Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment

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.

arXiv commentarXiv admin note: text overlap with arXiv:2004.07173

References in corpus (13)

• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Methods for Interpreting and Understanding Deep Neural Networks
• One pixel attack for fooling deep neural networks
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
• Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices
• FA*IR: A Fair Top-k Ranking Algorithm
• Understanding the Role of Individual Units in a Deep Neural Network
• Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
• Discrimination through optimization: How Facebook's ad delivery can lead to skewed outcomes
• Demographic Bias in Biometrics: A Survey on an Emerging Challenge
• Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation
• Right for the Right Reason: Training Agnostic Networks

Cited by in corpus (8)

• From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape
• Leveraging Large Language Models for Topic Classification in the Domain of Public Affairs
• mEBAL2 Database and Benchmark: Image-based Multispectral Eyeblink Detection
• Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics
• SMARTe-VR: Student Monitoring and Adaptive Response Technology for e-Learning in Virtual Reality
• A Data-to-Product Multimodal Conceptual Framework to Achieve Automated Software Evolution for Context-rich Intelligent Applications
• Is It Really You? Exploring Biometric Verification Scenarios in Photorealistic Talking-Head Avatar Videos
• Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs