Michela Proietti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Michela Proietti has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Alessio Ragno
LIRIS UMR 5205, INSA Lyon, CNRS
2 shared publications - Roberto Capobianco
Sony AI, Zürich, Switzerland
2 shared publications - Roberto Capobianco
Sony AI Zurich Switzerland
2 shared publications Alessio Ragno
INSA Lyon CNRS, LIRIS UMR 5205 Villeurbanne France
1 shared publication- Alessio Ragno
Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy, & CNRS, LIRIS UMR 5205, INSA Lyon, Villeurbanne, France
1 shared publication - Biagio La Rosa
Department of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University, Rome, Italy
1 shared publication
Latest Publications
- 10 January 2026
- Published by Springer Nature
- p. 525-555
Explainable Artificial Intelligence in Drug Discovery
- 10 January 2026
- Published by Springer Nature
- p. 525-555
Explainable Artificial Intelligence in Drug Discovery
- Open Access
CIP-Net: Continual Interpretable Prototype-based Network
Continual learning constrains models to learn new tasks over time without forgetting what they have already learned. A key challenge in this setting is catastrophic forgetting, where learning new information causes the model to lose its performance on previous tasks. Recently, explainable AI has been proposed as a promising way to better understand and reduce forgetting. In particular, self-explainable models are useful because they generate explanations during prediction, which can help preserve knowledge. However, most existing explainable approaches use post-hoc explanations or require additional memory for each new task, resulting in limited scalability. In this work, we introduce CIP-Net, an exemplar-free self-explainable prototype-based model designed for continual learning. CIP-Net avoids storing past examples and maintains a simple architecture, while still providing useful explanations and strong performance. We demonstrate that CIPNet achieves state-of-the-art performances compared to previous exemplar-free and self-explainable methods in both task- and class-incremental settings, while bearing significantly lower memory-related overhead. This makes it a practical and interpretable solution for continual learning.
Open AccessCIP-Net: Continual Interpretable Prototype-based Network
Continual learning constrains models to learn new tasks over time without forgetting what they have already learned. A key challenge in this setting is catastrophic forgetting, where learning new information causes the model to lose its performance on previous tasks. Recently, explainable AI has been proposed as a promising way to better understand and reduce forgetting. In particular, self-explainable models are useful because they generate explanations during prediction, which can help preserve knowledge. However, most existing explainable approaches use post-hoc explanations or require additional memory for each new task, resulting in limited scalability. In this work, we introduce CIP-Net, an exemplar-free self-explainable prototype-based model designed for continual learning. CIP-Net avoids storing past examples and maintains a simple architecture, while still providing useful explanations and strong performance. We demonstrate that CIPNet achieves state-of-the-art performances compared to previous exemplar-free and self-explainable methods in both task- and class-incremental settings, while bearing significantly lower memory-related overhead. This makes it a practical and interpretable solution for continual learning.
- Open Access
- 22 October 2025
- Published by Wiley in WIREs Data Mining and Knowledge Discovery
- Vol. 15 (4)
XAI ‐Guided Continual Learning: Rationale, Methods, and Future Directions
Providing neural networks with the ability to learn new tasks sequentially represents one of the main challenges in artificial intelligence. Unlike humans, neural networks are prone to losing previously acquired knowledge upon learning new information, a phenomenon known as catastrophic forgetting. Continual learning proposes diverse solutions to mitigate this problem, but only a few leverage explainable artificial intelligence. This work justifies using explainability techniques in continual learning, emphasizing the need for greater transparency and trustworthiness in these systems and grounding our approach in empirical findings from neuroscience that highlight parallels between forgetting in biological and artificial neural networks. Finally, we review existing work applying explainability methods to address catastrophic forgetting and propose potential avenues for future research. This article is categorized under: Fundamental Concepts of Data and Knowledge > Explainable AI Technologies > Artificial Intelligence Technologies > Cognitive Computing
- 22 October 2025
- Published by Wiley in WIREs Data Mining and Knowledge Discovery
- Vol. 15 (4)
Open AccessXAI ‐Guided Continual Learning: Rationale, Methods, and Future Directions
Providing neural networks with the ability to learn new tasks sequentially represents one of the main challenges in artificial intelligence. Unlike humans, neural networks are prone to losing previously acquired knowledge upon learning new information, a phenomenon known as catastrophic forgetting. Continual learning proposes diverse solutions to mitigate this problem, but only a few leverage explainable artificial intelligence. This work justifies using explainability techniques in continual learning, emphasizing the need for greater transparency and trustworthiness in these systems and grounding our approach in empirical findings from neuroscience that highlight parallels between forgetting in biological and artificial neural networks. Finally, we review existing work applying explainability methods to address catastrophic forgetting and propose potential avenues for future research. This article is categorized under: Fundamental Concepts of Data and Knowledge > Explainable AI Technologies > Artificial Intelligence Technologies > Cognitive Computing
- Open Access
Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
Understanding the alignment between large language models (LLMs) and human brain activity can reveal computational principles underlying language processing. We introduce a fine-grained input attribution method to identify the specific words most important for brain-LLM alignment, and leverage it to study a contentious research question about brain-LLM alignment: the relationship between brain alignment (BA) and next-word prediction (NWP). Our findings reveal that BA and NWP rely on largely distinct word subsets: NWP exhibits recency and primacy biases with a focus on syntax, while BA prioritizes semantic and discourse-level information with a more targeted recency effect. This work advances our understanding of how LLMs relate to human language processing and highlights differences in feature reliance between BA and NWP. Beyond this study, our attribution method can be broadly applied to explore the cognitive relevance of model predictions in diverse language processing tasks.
Open AccessFine-grained Analysis of Brain-LLM Alignment through Input Attribution
Understanding the alignment between large language models (LLMs) and human brain activity can reveal computational principles underlying language processing. We introduce a fine-grained input attribution method to identify the specific words most important for brain-LLM alignment, and leverage it to study a contentious research question about brain-LLM alignment: the relationship between brain alignment (BA) and next-word prediction (NWP). Our findings reveal that BA and NWP rely on largely distinct word subsets: NWP exhibits recency and primacy biases with a focus on syntax, while BA prioritizes semantic and discourse-level information with a more targeted recency effect. This work advances our understanding of how LLMs relate to human language processing and highlights differences in feature reliance between BA and NWP. Beyond this study, our attribution method can be broadly applied to explore the cognitive relevance of model predictions in diverse language processing tasks.
- Open Access
- 31 October 2023
- Published by Springer Nature in Machine Learning
- Vol. 113 (4) , 2013-2044
Explainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening
Molecular property prediction is a fundamental task in the field of drug discovery. Several works use graph neural networks to leverage molecular graph representations. Although they have been successfully applied in a variety of applications, their decision process is not transparent. In this work, we adapt concept whitening to graph neural networks. This approach is an explainability method used to build an inherently interpretable model, which allows identifying the concepts and consequently the structural parts of the molecules that are relevant for the output predictions. We test popular models on several benchmark datasets from MoleculeNet. Starting from previous work, we identify the most significant molecular properties to be used as concepts to perform classification. We show that the addition of concept whitening layers brings an improvement in both classification performance and interpretability. Finally, we provide several structural and conceptual explanations for the predictions.
- 31 October 2023
- Published by Springer Nature in Machine Learning
- Vol. 113 (4) , 2013-2044
Open AccessExplainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening
Molecular property prediction is a fundamental task in the field of drug discovery. Several works use graph neural networks to leverage molecular graph representations. Although they have been successfully applied in a variety of applications, their decision process is not transparent. In this work, we adapt concept whitening to graph neural networks. This approach is an explainability method used to build an inherently interpretable model, which allows identifying the concepts and consequently the structural parts of the molecules that are relevant for the output predictions. We test popular models on several benchmark datasets from MoleculeNet. Starting from previous work, we identify the most significant molecular properties to be used as concepts to perform classification. We show that the addition of concept whitening layers brings an improvement in both classification performance and interpretability. Finally, we provide several structural and conceptual explanations for the predictions.