Alessandro Sperduti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Alessandro Sperduti has a total of 153 co-authors. Here are the top co-authors by number of shared publications:
- Nicolò Navarin
University of Padova, Padua, Italy
29 shared publications - Luca Pasa
University of Padova, Padua, Italy
11 shared publications - Davide Bacciu
University of Pisa, Pisa, Italy
10 shared publications - Davide Rigoni
University of Padua
7 shared publications - Alessio Micheli
University of Pisa
6 shared publications - Antonio Carta
University of Pisa
6 shared publications
Latest Publications
- 22 September 2026
- Published by Springer Nature
- p. 396-408
SeeAct-VC: Improving Browser Automation Through Complementary Visual Clues
- 22 September 2026
- Published by Springer Nature
- p. 396-408
SeeAct-VC: Improving Browser Automation Through Complementary Visual Clues
- 15 September 2026
- Published by Springer Nature
- p. 704-716
Integrating Data-Driven Symbolic Fundamental Diagrams into Physics-Informed Neural Networks for Traffic State Estimation
- 15 September 2026
- Published by Springer Nature
- p. 704-716
Integrating Data-Driven Symbolic Fundamental Diagrams into Physics-Informed Neural Networks for Traffic State Estimation
- Open Access
- 9 September 2026
- Published by Elsevier in Artificial Intelligence
- Vol. 360
Learning neuro-symbolic convergent term rewriting systems
- 9 September 2026
- Published by Elsevier in Artificial Intelligence
- Vol. 360
Open AccessLearning neuro-symbolic convergent term rewriting systems
- Open Access
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 908-916
Iterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 908-916
Open AccessIterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks
- Open Access
- 4 March 2026
- Published by Elsevier in Neurocomputing
- Vol. 679
D4: Distance diffusion for a truly equivariant molecular design
- 4 March 2026
- Published by Elsevier in Neurocomputing
- Vol. 679
Open AccessD4: Distance diffusion for a truly equivariant molecular design
- Open Access
Analysis of Dirichlet Energies as Over-smoothing Measures
We analyze the distinctions between two functionals often used as over-smoothing measures: the Dirichlet energies induced by the unnormalized graph Laplacian and the normalized graph Laplacian. We demonstrate that the latter fails to satisfy the axiomatic definition of a node-similarity measure proposed by Rusch \textit{et al.} By formalizing fundamental spectral properties of these two definitions, we highlight critical distinctions necessary to select the metric that is spectrally compatible with the GNN architecture, thereby resolving ambiguities in monitoring the dynamics.
Open AccessAnalysis of Dirichlet Energies as Over-smoothing Measures
We analyze the distinctions between two functionals often used as over-smoothing measures: the Dirichlet energies induced by the unnormalized graph Laplacian and the normalized graph Laplacian. We demonstrate that the latter fails to satisfy the axiomatic definition of a node-similarity measure proposed by Rusch \textit{et al.} By formalizing fundamental spectral properties of these two definitions, we highlight critical distinctions necessary to select the metric that is spectrally compatible with the GNN architecture, thereby resolving ambiguities in monitoring the dynamics.
- 23 September 2025
- Published by Springer Nature
- p. 201-212
A Spectral Interpretation of Redundancy in a Graph Reservoir
- 23 September 2025
- Published by Springer Nature
- p. 201-212
A Spectral Interpretation of Redundancy in a Graph Reservoir
- Open Access
Unveiling the Actual Performance of Neural-based Models for Equation Discovery on Graph Dynamical Systems
The ``black-box'' nature of deep learning models presents a significant barrier to their adoption for scientific discovery, where interpretability is paramount. This challenge is especially pronounced in discovering the governing equations of dynamical processes on networks or graphs, since even their topological structure further affects the processes' behavior. This paper provides a rigorous, comparative assessment of state-of-the-art symbolic regression techniques for this task. We evaluate established methods, including sparse regression and MLP-based architectures, and introduce a novel adaptation of Kolmogorov-Arnold Networks (KANs) for graphs, designed to exploit their inherent interpretability. Across a suite of synthetic and real-world dynamical systems, our results demonstrate that both MLP and KAN-based architectures can successfully identify the underlying symbolic equations, significantly surpassing existing baselines. Critically, we show that KANs achieve this performance with greater parsimony and transparency, as their learnable activation functions provide a clearer mapping to the true physical dynamics. This study offers a practical guide for researchers, clarifying the trade-offs between model expressivity and interpretability, and establishes the viability of neural-based architectures for robust scientific discovery on complex systems.
Open AccessUnveiling the Actual Performance of Neural-based Models for Equation Discovery on Graph Dynamical Systems
The ``black-box'' nature of deep learning models presents a significant barrier to their adoption for scientific discovery, where interpretability is paramount. This challenge is especially pronounced in discovering the governing equations of dynamical processes on networks or graphs, since even their topological structure further affects the processes' behavior. This paper provides a rigorous, comparative assessment of state-of-the-art symbolic regression techniques for this task. We evaluate established methods, including sparse regression and MLP-based architectures, and introduce a novel adaptation of Kolmogorov-Arnold Networks (KANs) for graphs, designed to exploit their inherent interpretability. Across a suite of synthetic and real-world dynamical systems, our results demonstrate that both MLP and KAN-based architectures can successfully identify the underlying symbolic equations, significantly surpassing existing baselines. Critically, we show that KANs achieve this performance with greater parsimony and transparency, as their learnable activation functions provide a clearer mapping to the true physical dynamics. This study offers a practical guide for researchers, clarifying the trade-offs between model expressivity and interpretability, and establishes the viability of neural-based architectures for robust scientific discovery on complex systems.
- Open Access
- 24 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 108029
On the application of neural networks for structured domains to fMRI data
- 24 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 108029
Open AccessOn the application of neural networks for structured domains to fMRI data
- Open Access
- 15 April 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (25) , 21351-21352
Correction: Object search by a concept-conditioned object detector
- 15 April 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (25) , 21351-21352
Open AccessCorrection: Object search by a concept-conditioned object detector