Alessio Mora

We investigate a scenario where multiple sources independently and voluntarily contribute status reports, which are then aggregated through a federated process. To address the challenge of partial participation in distributed systems, we introduce the age of federated information (AoFI), a novel metric that quantifies data freshness. This metric is specifically designed to bridge the gap between classical age of information, which is unsuitable for collaborative tasks, and the often impractical age of correlated information, which requires full participation. To model distributed optimization across multiple independent sources, we adopt a game-theoretic framework. In this framework, users strategically minimize their individual penalty, computed as a global-local combination of the overall AoFI on the common receiver’s side and their individual energy expenditure. We derive the worst-case Nash equilibrium of this game and compare its efficiency with the centralized optimization optimum. Our efficiency analysis reveals a critical design tradeoff for practical industrial internet of things (IIoT) deployments: while decentralized coordination is highly efficient in high-participation regimes, performance in low-participation regimes is paradoxically optimized by actively restricting the number of sources to prevent strategic inefficiencies.

Federated learning (FL) enables collaborative training of a machine learning (ML) model across multiple parties, facilitating the preservation of users’ and institutions’ privacy by maintaining data stored locally. Instead of centralizing raw data, FL exchanges locally refined model parameters to build a global model incrementally. While FL is more compliant with emerging regulations such as the European General Data Protection Regulation (GDPR), ensuring the right to be forgotten in this context—allowing FL participants to remove their data contributions from the learned model—remains unclear. In addition, it is recognized that malicious clients may inject backdoors into the global model through updates, e.g., to generate mispredictions on specially crafted data examples. Consequently, there is the need for mechanisms that can guarantee individuals the possibility to remove their data and erase malicious contributions even after aggregation, without compromising the already acquired “good” knowledge. This highlights the necessity for novel federated unlearning (FU) algorithms, which can efficiently remove specific clients’ contributions without full model retraining. This article provides background concepts, empirical evidence, and practical guidelines to design/implement efficient FU schemes. This study includes a detailed analysis of the metrics for evaluating unlearning in FL and presents an in-depth literature review categorizing state-of-the-art FU contributions under a novel taxonomy. Finally, we outline the most relevant and still open technical challenges, by identifying the most promising research directions in the field.