EMERGE’s findings will be communicated at scientific conferences and published in open-access journals. Find below the current list of publications.
Access all publication on the project's Zenodo community clicking here.
Non-Dissipative Graph Propagation for Non-Local Community Detection
This work argues that the ability to propagate long-range information during message passing is key to effectively perform community detection in heterophilic graphs.
W. Leeney, A. Gravina and D. Bacciu, 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1-8, doi: 10.1109/IJCNN64981.2025.11228363.
Non-dissipative Reservoir Computing Approaches for Time-Series Classification
This paper studies the behavior of a recently introduced class of alternative RC approaches in which the fixed dynamical component implements a stable but non-dissipative system, so that the driving temporal signal can be propagated through multiple time steps effectively.
Gallicchio, C., Ceni, A. (2024). In Artificial Neural Networks and Machine Learning – ICANN 2024. ICANN 2024. Lecture Notes in Computer Science, vol 15025. doi: 10.1007/978-3-031-72359-9_8
Nonlinear Modes as a Tool for Comparing the Mathematical Structure of Dynamic Models of Soft Robots
This paper proposes to use the recent nonlinear extension in modal theory -called eigenmanifolds- as a means to evaluate control-oriented models for soft robots and compare them.
P. Pustina, D. Calzolari, A. Albu-Schäffer, A. D. Luca and C. D. Santina, 2024 IEEE 7th International Conference on Soft Robotics (RoboSoft), 2024, pp. 779-785, doi: 10.1109/RoboSoft60065.2024.10521987.
On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
This paper introduces a novel perspective to address oversquashing, leveraging dynamical systems properties of global and local non-dissipativity, that enable the maintenance of a constant information flow rate.
Gravina, A., Eliasof, M., Gallicchio, C., Bacciu, D., & Schönlieb, C.-B. (2025). Proceedings of the AAAI Conference on Artificial Intelligence, 39(16), 16906-16914.
On the ethical governance of swarm robotic systems in the real world
In this paper, the authors address the question: what practices would be required for the responsible design and operation of real-world swarm robotic systems?
Alan F. T. Winfield, Matimba Swana, Jonathan Ives and Sabine Hauert. Phil. Trans. R. Soc. A.38320240142 DOI: 10.1098/rsta.2024.0142
Over-Parameterized Neural Models based on Graph Random Features for fast and accurate graph classification
This paper aims to explore a simple form of a randomized graph neural network.
Nicolò Navarin, Luca Pasa, Claudio Gallicchio, Luca Oneto, and Alessandro Sperduti, in "20th International Workshop on Mining and Learning with Graphs In conjunction with ECMLPKDD 2023"
Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
This work conducts an extensive analysis across diverse subjective text classification tasks including hate speech, irony, abusive language, and stance detection, to highlight the importance of capturing human disagreements, often overlooked by traditional aggregation methods.
Benedetta Muscato, Lucia Passaro, Gizem Gezici, Fosca Giannotti, Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence AI and Social Good. Pages 9827-9835. DOI: 10.24963/ijcai.2025/1092
Physics-Informed Neural Networks to Model and Control Robots: A Theoretical and Experimental Investigation
This work concerns the application of physics-informed neural networks to the modeling and control of complex robotic systems.
Liu, J., Borja, P. and Della Santina, C. (2024), Adv. Intell. Syst., 6: 2300385. doi: 10.1002/aisy.202300385
Piecewise Affine Curvature model: a Reduced-Order Model for Soft Robot-Environment Interaction Beyond PCC
In this work, the authors perform an analysis of the trade-off between computational treatability and modelling accuracy, and propose a new kinematic model, the Piecewise Affine Curvature (PAC).
F. Stella, Q. Guan, C. Della Santina and J. Hughes, in 2023 IEEE International Conference on Soft Robotics (RoboSoft), Singapore, Singapore, 2023, pp. 1-7, doi: 10.1109/RoboSoft55895.2023.10121939.
Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
This paper introduces port-Hamiltonian Deep Graph Networks, a novel framework that models neural information flow in graphs by building on the laws of conservation of Hamiltonian dynamical systems.
Simon Heilig, Alessio Gravina, Alessandro Trenta, Claudio Gallicchio, Davide Bacciu, The Thirteenth International Conference on Learning Representations, 2025.
Prescribing Cartesian Stiffness of Soft Robots by Co-Optimization of Shape and Segment-Level Stiffness
In this work, the authors propose a strategy to prescribe variations of the physical stiffness and the robot's posture so to implement a desired Cartesian stiffness and location of the contact point.
Francesco Stella, Josie Hughes, Daniela Rus, and Cosimo Della Santina. Soft Robotics. Aug 2023. 701-712. DOI: 10.1089/soro.2022.0025.
Proprioceptive Sensing of Soft Tentacles with Model Based Reconstruction for Controller Optimization
In this work, the authors propose a new sensing approach for soft underwater slender structures based on embedded pressure sensors and use a learning-based pipeline to link the sensor readings to the shape of the soft structure.
A. Vicari et al., 2023 IEEE International Conference on Soft Robotics (RoboSoft), Singapore, Singapore, 2023, pp. 1-6, doi: 10.1109/RoboSoft55895.2023.10121999.
Quasi-Metacognitive Machines: Why We Don’t Need Morally Trustworthy AI and Communicating Reliability is Enough
This paper argues that developing morally trustworthy AI is not only unethical, as it promotes trust in an entity that cannot be trustworthy, but it is also unnecessary for optimal calibration.
Dorsch, J., Deroy, O. Philos. Technol. 37, 62 (2024). doi: 10.1007/s13347-024-00752-w.
Random Orthogonal Additive Filters: A Solution to the Vanishing/Exploding Gradient of Deep Neural Networks
In this paper, a new idea that permits to solve the V/E gradient issue of deep learning models trained via stochastic gradient descent (SGD) methods is proposed.
A. Ceni, in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2025.3538924.
Random Oscillators Network for Time Series Processing
This paper introduces the Random Oscillators Network (RON), a physically-inspired recurrent model derived from a network of heterogeneous oscillators.
Andrea Ceni, Andrea Cossu, Maximilian W Stölzle, Jingyue Liu, Cosimo Della Santina, Davide Bacciu, Claudio Gallicchio Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:4807-4815, 2024.
Randomly Coupled Oscillators for Time Series Processing
This paper investigates a physically-inspired recurrent neural network derived from a continuous-time ODE modelling a network of coupled oscillators.
Andrea Ceni, Andrea Cossu, Jingyue Liu, Maximilian Stölzle, Cosimo Della Santina, Claudio Gallicchio and Davide Bacciu, ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023.
Replay-free Online Continual Learning with Self-Supervised MultiPatches
This work proposes Continual MultiPatches (CMP), an effective plug-in for existing OCL self-supervised learning strategies that avoids the use of replay samples.
Cignoni, Giacomo & Cossu, Andrea & Gomez-Villa, Alexandra & Weijer, Joost & Carta, Antonio. (2025). 81-86. 10.14428/esann/2025.ES2025-180.
Reservoir Memory Networks
This paper introduces Reservoir Memory Networks (RMNs), a novel class of Reservoir Computing (RC) models that integrate a linear memory cell with a non-linear reservoir to enhance long-term information retention.
Claudio Gallicchio and Andrea Ceni, ESANN 2024 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium) and online event, 9-11 October 2024.
