XAI for Predictive Maintenance

PRESENTERS: Joao Gama, Slawomir Nowaczyk, Sepideh Pashami, Rita P. Ribeiro, Bruno Veloso, Szymon Bobek

Real-world applications of PM are increasingly complex, with intricate interactions of many components. AI solutions are a very popular technique in this domain, and especially black-box models based on deep learning approaches are showing promising results in predictive accuracy and capability of modelling complex systems.

WEBSITE

Social Dynamics and Evolutionary Game Theory

PRESENTERS: Elias Fernández Domingos

This tutorial will provide an overview of the Evolutionary Game Theory (EGT) field with emphasis on its applicability to characterize hybrid human-AI multi-agent systems. We will introduce the main research questions and practical challenges of implementing EGT models.

WEBSITE

Formal Methods for Machine Ethics

PRESENTERS: Emiliano Lorini

In this tutorial we will show how to leverage formal methods for modeling ethical concepts and for endowing AI systems with ethical reasoning and ethical decision-making capabilities. The tutorial focuses specifically on the use of logic, planning and game theory for machine ethics.

WEBSITE

Automated Reasoning for Social Choice Theory

PRESENTERS: Ulle Endriss

One of the most exciting developments in the field of computational social choice in recent years has been the use of SAT solvers to automate the task of proving theorems regarding the design of methods for multiagent decision making. This tutorial will offer a hands-on introduction to this powerful new approach.

WEBSITE

Robust Explainable AI: the Case of Counterfactual Explanations

PRESENTERS: Francesco Leofante

Counterfactual explanations (CXs) are routinely used to shed light on the decisions of machine learning models; however, CX generation strategies often lack robustness, which may jeopardise their explanatory function. This tutorial aims at introducing Robust Explainable AI, a rapidly growing field that offers novel solutions to alleviate this problem and improve the trustworthiness of CXs.

WEBSITE

Hypervolume Approximation for Many-objective Optimization and Learning

PRESENTERS: Ke Shang, Hisao Ishibuchi

This tutorial discusses the hypervolume approximation methods in multi-objective optimization and learning. Some applications and future research directions are highlighted, particularly focusing on the deep learning approach.

WEBSITE

Introduction to Responsible and Explainable AI

PRESENTERS: Leila Methnani, Andreas Theodorou, Virginia Dignum

This tutorial presents ongoing research in the field of Responsible Artificial Intelligence by introducing core concepts and means of operationalising AI ethics. Attendees will—through both lectures and problem-based learning exercises—get experience in implementing and testing systems for policy compliance.

WEBSITE

Decentralized Federated Learning: Enabling Collaborative AI With Enhanced Trust and Efficiency

PRESENTERS: Alberto Huertas Celdrán, Gregorio Martínez Pérez, Enrique Tomás Martínez Beltrán, Pedro Miguel Sánchez Sánchez, Gérôme Bovet, Burkhard Stiller

This tutorial presents a rigorous examination of Decentralized Federated Learning (DFL), an emergent field that fortifies the intersection of collaboration, efficiency, and privacy in artificial intelligence systems. The tutorial systematically explores the underlying principles, architectures, components, security strategies, and optimization techniques inherent to DFL. Moreover, participants will have the opportunity to gain hands-on experience with Fedstellar, a platform for training DFL models, and delve into real-world use cases, effectively marrying theory with practice. Attendees will gain an understanding of practical applications, as well as a vision of future trends, encapsulating the transformative potential of DFL in the realm of Artificial Intelligence (AI) and associated domains.

WEBSITE

The AI4Europe AI Reproducibility Initiative

PRESENTERS: Barry O’Sullivan, Gabriel Gonzalez-Castane, Rafael Tolosana-Calasanz

Reproducibility is crucial for scientific and technical research, confirming the validity of discoveries, ensuring trustworthiness, and enabling dissemination and adoption. This tutorial introduces the European Project AI4Europe Reproducibility Initiative, which recognizes the significance of reproducibility in AI to establish methods and tools, with high standards and practices specific to AI.

WEBSITE

Solving Multi-agent Games on Networks by Strategic Agents

PRESENTERS: Yair Vaknin, Amnon Meisels

Games on networks (GoNs), played by multi-agents, will be described with special focus on Public Goods Games. The tutorial will focus on search methods for finding good solutions to GoNs, on the idea of side-payments among interacting agents and on a mechanism that enforces truthful behavior among strategic agents.

WEBSITE