Machine Learning and Intelligent Optimization | Doctoral Program - Information Engineering and Computer Science

Machine Learning and Intelligent Optimization

The LION laboratory (machine Learning and Intelligent OptimizationN) fosters research and development in intelligent optimization and reactive search optimization (RSO) techniques to solve problems in different application areas, including marketing automation and e-commerce, telecommunication networks, ICT, mobile services, big data, cost management, social networks, clustering and pattern recognition in bio-informatics.

We support the integration of different theoretical and practical tools in a creative environment that cuts across the borders of academic disciplines. This is the passion of LION activities. LION is building tools for the new prescriptive analytics wave.

We use data to build models and extract knowledge, we exploit knowledge to automate the discovery of better solutions, we connect insight to decisions and actions.

 

Publications

10 publications for 2 currently enrolled students

2SSP: A Two-Stage Framework for Structured Pruning of LLMs
Sandri, Fabrizio; Cunegatti, Elia; Iacca, Giovanni in TRANSACTIONS ON MACHINE LEARNING RESEARCH, v. 09, (2025). - Publication URL

Macbeth: Multi-Gpu Algorithm for Computing Betweenness Centrality with Explorative and Exploitative Heuristics
Pichetti, Lorenzo; Cunegatti, Elia; Orlando, Dennis; Tumeo, Antonino; Halappanavar, Mahantesh M.; Iacca, Giovanni; Vella, Flavio 2025. - DOI: 10.2139/ssrn.5351222

Multi-objective Evolutionary Optimization of Virtualized Fast Feedforward Networks
Kilic, Renan Beran; Yildirim, Kasim Sinan; Iacca, Giovanni in Applications of Evolutionary Computation. EvoApplications 2025, Cham: Springer Science and Business Media Deutschland GmbH, 2025, p. 270-286. - (LECTURE NOTES IN COMPUTER SCIENCE). - ISBN: 9783031900617. Proceedings of: 28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025, Trieste, 23rd April-25th April 2025. - Publication URL . - DOI: 10.1007/978-3-031-90062-4_17

Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training
Cunegatti, Elia; Custode, Leonardo Lucio; Iacca, Giovanni in TRANSACTIONS ON MACHINE LEARNING RESEARCH, v. 10/2025, (2025). - Publication URL

Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations
Cunegatti, Elia; Farina, Matteo; Bucur, Doina; Iacca, Giovanni in TRANSACTIONS ON MACHINE LEARNING RESEARCH, v. 2024, (2024). - Publication URL
[other topics: Deep and Structured Machine Learning

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
Farina, Matteo; Mancini, Massimiliano; Cunegatti, Elia; Iacca, Giovanni; Ricci, Elisa in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA: IEEE Computer Society, 2024, p. 16185-16195. - (PROCEEDINGS IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION). - ISBN: 9798350353006. Proceedings of: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, 17th June 2024–21st June 2024. - DOI: 10.1109/cvpr52733.2024.01532
[other topics: Deep and Structured Machine Learning

Neuron-centric Hebbian Learning
Ferigo, Andrea; Cunegatti, Elia; Iacca, Giovanni in GECCO '24: Proceedings of the Genetic and Evolutionary Computation Conference, New York, NY, USA: ACM, 2024, p. 87-95. - ISBN: 9798400704949. Proceedings of: 2024 Genetic and Evolutionary Computation Conference, GECCO 2024, Melbourne, 14th July 2024-18th July 2024. - Publication URL . - DOI: 10.1145/3638529.3654011

Many-Objective Evolutionary Influence Maximization: Balancing Spread, Budget, Fairness, and Time
Cunegatti, Elia; Custode, Leonardo; Iacca, Giovanni in GECCO '24 Companion: Proceedings of the Genetic and Evolutionary Computation Conference Companion, New York: Association for Computing Machinery, Inc, 2024, p. 655-658. - ISBN: 9798400704956. Proceedings of: 2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion, Melbourne, 14th July- 18th July 2024. - Publication URL . - DOI: 10.1145/3638530.3654161

Influence Maximization in Hypergraphs Using Multi-Objective Evolutionary Algorithms
Genetti, Stefano; Ribaga, Eros; Cunegatti, Elia; Lotito, Quintino F.; Iacca, Giovanni in Parallel Problem Solving from Nature – PPSN XVIII, Cham: Springer, 2024, p. 217-235. - (LECTURE NOTES IN COMPUTER SCIENCE). - ISBN: 9783031700842. Proceedings of: 18th International Conference on Parallel Problem Solving from Nature, PPSN 2024, Hagenberg, 14th September-18th September 2024. - Publication URL . - DOI: 10.1007/978-3-031-70085-9_14

Fast-Inf: Ultra-Fast Embedded Intelligence on the Batteryless Edge
Custode, Leonardo Lucio; Farina, Pietro; Yildiz, Eren; Kilic, Renan Beran; Yildirim, Kasim Sinan; Iacca, Giovanni in SENSYS '24: Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems, New York: ACM, 2024, p. 239-252. - ISBN: 979-8-4007-0697-4. Proceedings of: 22nd ACM Conference on Embedded Networked Sensor Systems, SenSys 2024, Hangzhou China, 4th –7th November 2024. - Publication URL . - DOI: 10.1145/3666025.3699335

 

Students

Cunegatti, Eliaelia.cunegatti [at] unitn.itwebpage
Kilic, Renan Beranrenanberan.kilic [at] unitn.itwebpage