CLAUDIO BATTILORO

Dottore di ricerca

ciclo: XXXVI


relatore: prof. Paolo Di Lorenzo

Titolo della tesi: Signal Processing and Learning over Topological Spaces

The aim of this thesis is to introduce a variety of signal processing methodologies specifically designed to model, interpret, and learn from data structured within topological spaces. These spaces are loosely characterized as a collection of points together with a neighborhood notion among points. The methodologies and tools discussed herein hold particular relevance and utility when applied to signals defined over combinatorial topological spaces, such as cell complexes, or within metric spaces that exhibit non-trivial properties, such as Riemann manifolds with non-flat metrics. One of the primary motivations behind this research is to address and surmount the constraints encountered with traditional graph-based representations when they are employed to depict intricate systems. This thesis emphasizes the necessity to account for sophisticated, multiway, and geometry-sensitive interactions that are not adequately captured by conventional graph models. The contributions of this work include but are not limited to the development of methodologies for sparse signal representations over simplicial/cell complexes, attentional deep neural networks for data defined over simplicial/cell complexes, and the establishment of an inaugural signal processing framework specifically devised for signals that are defined over the tangent bundles of Riemann manifolds, that we formally connect with cellular sheaves over undirected graphs. The implications of these developments are potentially profound for the signal processing community, which only recently has started to synergize its historical founding concepts with tools from algebraic topology and differential geometry. Moreover, we put particular attention on making the presentation on this work, on the one hand, accessible to a broader SP audience and, on the other hand, complementary to related results from the (pure) machine learning community.

Produzione scientifica

11573/1687987 - 2023 - Tangent Bundle Filters and Neural Networks: From Manifolds to Cellular Sheaves and Back
Battiloro, C.; Wang, Z.; Riess, H.; Di Lorenzo, P.; Ribeiro, A. - 04b Atto di convegno in volume
congresso: IEEE ICASSP 2023 (Rhodes, Greece)
libro: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2023 - (978-1-7281-6327-7)

11573/1687992 - 2023 - Topological Slepians: Maximally Localized Representations of Signals Over Simplicial Complexes
Battiloro, Claudio; Di Lorenzo, Paolo; Barbarossa, Sergio - 04b Atto di convegno in volume
congresso: IEEE ICASSP 2023 (Rhodes, Greece)
libro: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - (978-1-7281-6327-7)

11573/1695677 - 2023 - Parametric dictionary learning for topological signal representation
Battiloro, Claudio; Di Lorenzo, Paolo; Ribeiro, Alejandro - 04b Atto di convegno in volume
congresso: 31st European Signal Processing Conference, EUSIPCO 2023 (Helsinki; Finland)
libro: European Signal Processing Conference - (978-9-4645-9360-0)

11573/1687989 - 2023 - Topological signal processing over weighted simplicial complexes
Battiloro, Claudio; Sardellitti, Stefania; Barbarossa, Sergio; Di Lorenzo, Paolo - 04b Atto di convegno in volume
congresso: 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023Rhodes Island (Rhodes; Greece)
libro: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings - (978-1-7281-6327-7)

11573/1687995 - 2023 - Pooling strategies for simplicial convolutional networks
Cinque, Domenico Mattia; Battiloro, Claudio; Di Lorenzo, Paolo - 04b Atto di convegno in volume
congresso: 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 (Rhodes; Greece)
libro: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - (978-1-7281-6327-7)

11573/1687999 - 2023 - Cell Attention Networks
Giusti, Lorenzo; Battiloro, Claudio; Testa, Lucia; Di Lorenzo, Paolo; Sardellitti, Stefania; Barbarossa, Sergio - 04b Atto di convegno in volume
congresso: International Joint Conference on Neural Networks (IJCNN) 2023 (Gold Coast, Australia)
libro: 2023 International Joint Conference on Neural Networks (IJCNN) - (978-1-6654-8867-9)

11573/1695410 - 2023 - ICML 2023 topological deep learning challenge. Design and results
Papillon, Mathilde; Hajij, Mustafa; Frantzen, Florian; Hoppe, Josef; Jenne, Helen; Mathe, Johan; Myers, Audun; Papamarkou, Theodore; Schaub, Michael T.; Zamzmi, Ghada; Birdal, Tolga; Dey, Tamal; Doster, Timothy; Emerson, Tegan H.; Gopalakrishnan, Gurusankar; Govil, D.; Grande, Vincent P.; Guzm'an-S'aenz, Aldo; Kvinge, Henry; Livesay, Neal; Meisner, Jan; Mukherjee, Soham; Samaga, Shreyas N.; Natesan Ramamurthy, Karthikeyan; Reddy Karri, Maneel; Rosen, Paul; Sanborn, Sophia; Scholkemper, Michael; Walters, Robin; Agerberg, Jens; Bokman, Georg; Barikbin, Sadrodin; Battiloro, Claudio; Bazhenov, Gleb; Bern('A)Rdez, Guillermo; Brent, Aiden; Escalera, Sergio; Fiorellino, Simone; Gavrilev, Dmitrii; Hassanin, Mohammed; Hausner, Paul; Hoff Gardaa, Odin; Khamis, Abdelwahed; Lecha, M; Magai, German; Malygina, Tatiana; Melnyk, Pavlo; Ballester, Rub('E)N; Varma Nadimpalli, Kalyan; Nikitin, Alexander; Rabinowitz, Abraham; Salatiello, Alessandro; Scardapane, Simone; Scofano, Luca; Singh, Suraj; Sjolund, Jens; Snopov, Paul; Spinelli, Indro; Telyatnikov, Lev; Testa, Lucia; Yang, Maosheng; Yue, Yixiao; Zaghen, Olga; Zia, Ali; Miolane, Nina - 04b Atto di convegno in volume
congresso: 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning, TAG-ML 2023, held at the International Conference on Machine Learning, ICML 2023 (Honolulu; Hawaii)
libro: Proceedings of Machine Learning Research - ()

11573/1662612 - 2022 - Lyapunov-based optimization of edge resources for energy-efficient adaptive federated learning
Battiloro, Claudio; Lorenzo, Paolo Di; Merluzzi, Mattia; Barbarossa, Sergio - 01a Articolo in rivista
rivista: IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING ([New York, NY : Institute of Electrical and Electronics Engineers], 1986-) pp. 265-280 - issn: 2473-2400 - wos: WOS:000965528300001 (5) - scopus: 2-s2.0-85133812220 (8)

11573/1669880 - 2022 - Dynamic resource optimization for adaptive federated learning empowered by reconfigurable intelligent surfaces
Battiloro, Claudio; Merluzzi, Mattia; Di Lorenzo, Paolo; Barbarossa, Sergio - 04b Atto di convegno in volume
congresso: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Singapore, Singapore)
libro: {ICASSP} 2022 - 2022 {IEEE} International Conference on Acoustics, Speech and Signal Processing ({ICASSP}) - (978-1-6654-0540-9)

11573/1687902 - 2022 - Graph Convolutional Networks with Autoencoder-Based Compression and Multi-Layer Graph Learning
Giusti, L; Battiloro, C; Di Lorenzo, P; Barbarossa, S - 04b Atto di convegno in volume
congresso: IEEE ICASSP 2022 (Singapore)
libro: IEEE ICASSP 2022 - (978-1-6654-0540-9)

11573/1669879 - 2022 - Graph Convolutional Networks With Autoencoder-Based Compression And Multi-Layer Graph Learning
Giusti, Lorenzo; Battiloro, Claudio; Di Lorenzo, Paolo; Barbarossa, Sergio - 04b Atto di convegno in volume
congresso: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Singapore, Singapore)
libro: {ICASSP} 2022 - 2022 {IEEE} International Conference on Acoustics, Speech and Signal Processing ({ICASSP}) - (978-1-6654-0540-9)

11573/1669877 - 2022 - Energy-efficient classification at the wireless edge with reliability guarantees
Merluzzi, Mattia; Battiloro, Claudio; Di Lorenzo, Paolo; Calvanese Strinati, Emilio - 04b Atto di convegno in volume
congresso: 2022 IEEE International Conference on Communications Workshops (ICC Workshops) (Seul, Republic of Korea)
libro: 2022 {IEEE} International Conference on Communications Workshops ({ICC} Workshops) - (978-1-6654-2671-8)

11573/1478714 - 2021 - Dynamic resource optimization for decentralized estimation in energy harvesting IoT networks
Battiloro, C.; Di Lorenzo, P.; Banelli, P.; Barbarossa, S. - 01a Articolo in rivista
rivista: IEEE INTERNET OF THINGS JOURNAL (Piscataway, NJ : Institute of Electrical and Electronics Engineers, 2014-.) pp. 1-13 - issn: 2327-4662 - wos: WOS:000648206800056 (4) - scopus: 2-s2.0-85098762967 (5)

11573/1615933 - 2021 - Dynamic resource optimization for adaptive federated learning at the wireless network edge
Di Lorenzo, P.; Battiloro, C.; Merluzzi, M.; Barbarossa, S. - 04b Atto di convegno in volume
congresso: 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 (Toronto; Canada)
libro: ICASSP, IEEE International conference on acoustics. Speech and Signal Processing - Proceedings - (978-1-7281-7605-5)

11573/1450433 - 2020 - Distributed tensor completion over networks
Battiloro, C.; Di Lorenzo, P. - 04b Atto di convegno in volume
congresso: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 (Barcelona)
libro: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings - (978-1-5090-6631-5)

11573/1450457 - 2019 - Dynamic resource optimization for decentralized signal estimation in energy harvesting wireless sensor networks
Di Lorenzo, P.; Battiloro, C.; Banelli, P.; Barbarossa, S. - 04b Atto di convegno in volume
congresso: 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 (Brighton; United Kingdom)
libro: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings - (978-1-4799-8131-1)

¬© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma