Publications
Network Pruning
2SSP: A Two-Stage Framework for Structured Pruning of LLMs
Fabrizio Sandri* , Elia Cunegatti* , Giovanni Iacca
Workshop on Sparsity in LLMs (SLLM) @ ICLR 2025
* Equal contribution
Paper - Code
Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training
Elia Cunegatti, Leonardo Lucio Custode, Giovanni Iacca
Workshop on Sparsity in LLMs (SLLM) @ ICLR 2025
Paper - Code
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
Matteo Farina, Massimiliano Mancini, Elia Cunegatti, Gaowen Liu, Giovanni Iacca, Elisa Ricci
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2024
Paper - Code
Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations
Elia Cunegatti, Matteo Farina, Doina Bucur, Giovanni Iacca
Transaction of Machine Learning (TMLR), April 2024
Paper - Code
Pruning at initialization vs random pruning: Do they produce topologically different sparse neural networks?
Elia Cunegatti, Doina Bucur, Giovanni Iacca
Workshop on Sparsity in Neural Networks @ ICLR 2023, May 2023
Paper
Evolutionary Algorithms / Graph Theory / Others 🙃
Influence Maximization in Hypergraphs using Multi-Objective Evolutionary Algorithms
Stefano Genetti, Eros Ribaga, Elia Cunegatti, Quintino F. Lotito, Giovanni Iacca
International Conference on Parallel Problem Solving from Nature (PPSN), September 2024
Paper - Code
Neuron-centric Hebbian Learning
Andrea Ferigo, Elia Cunegatti, Giovanni Iacca
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), July 2024
Paper - Code
Many-Objective Evolutionary Influence Maximization: Balancing Spread, Budget, Fairness, and Time
Elia Cunegatti, Leonardo Lucio Custode, Giovanni Iacca
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), July 2024
Paper - Code
Large-scale multi-objective influence maximisation with network downscaling
Elia Cunegatti, Giovanni Iacca, Doina Bucur
International Conference on Parallel Problem Solving from Nature (PPSN), September 2022
Paper - Code
Kudos to all the co-authors!! 🎉👌🏻