Daniele Zambon
Hello! My name is Daniele, I am a postdoctoral researcher at the University of Florence, Italy.
The focus of my research is learning in non-stationary environments, graph representation learning, and time series analysis.
News!
- [02-2026] Two new accepted papers: Binary Error Propagation at ICLR 2026 and AZ-analysis at Neurocomputing!
- [10-2025] We have released two preprints presenting a new online formulation for graph continual learning and a surprisingly effective approach designed for it.
- [8-2025] I’ve become member of the IEEE Task Force on AI for Time Series and Spatio-Temporal Data.
- [6-2025] Together with MeteoSwiss, we’ve released PeakWeather — a benchmark-ready dataset for spatiotemporal weather modeling, featuring over 8 years of 10-minute observations from 302 stations across Switzerland.
- [5-2025] ACM Computing Surveys accepted our tutorial paper on graph deep learning for time series forecasting.
- [5-2025] Happy to share that our paper on learning latent graph distributions has been accepted at ICML ‘25!
- [3-2025] Green light to our Temporal Graph Learning 2025 workshop at KDD ‘25!
- [11-2024] We will deliver a tutorial on graph deep learning for time series processing at the LoG conference (Nov 28, 2024) and its Italy Meetup in the gorgeous Siena (Dec 6, 2024).
- [9-2024] ESANN 2025 will host our special session on foundation and generative models for graphs! Deadline for paper submission is November 20, 2024.
- [8-2024] Our survey of GNN for time series has been accepted at IEEE TPAMI.
- [4-2024] New paper on irregularly-sampled time series accepted at IJCAI ‘24!
- [1-2024] New paper on virtual sensing accepted at ICLR ‘24!
Short bio
I am a postdoc at the University of Florence in Italy. Previously, I have been postdoc at the Dalle Molle Institute for Artificial Intelligence (IDSIA), Università della Svizzera italiana (USI) in Switzerland , within the Graph Machine Learning Group. I am member of the IEEE Task Forces on Learning for Graphs and AI for Time Series and Spatio-Temporal Data.
I earned my Ph.D. in Informatics from USI (Jan ‘22), focusing on statistical tests for anomaly and change detection, graph representation learning, and learning in non-stationary environments. Prior to my PhD, I graduated with honors from the University of Milan (IT, Apr ‘16) with a degree in Mathematics specializing in approximation theory and mathematical statistics. During my doctoral studies, I have been visiting researcher at the University of Florida (US, Nov ‘19–Feb ‘20) and at the University of Exeter (UK, Sep ‘17, Oct ‘18). I have also been an intern at STMicroelectronics (IT, May ‘15–Apr ‘16, May ‘16–Sep ‘16) where I developed my Master’s thesis on sparse models for anomaly detection and co-authored a patent.
My work has been published in top-tier journals and conferences of the field, including JMLR, IEEE TPAMI, IEEE TNNLS, IEEE TSP, NeurIPS, ICLR, and ICML. I am associate editor for IEEE TNNLS. I hold a patent. I have co-organized workshops, special sessions and tutorials at international conferences on graph deep learning.
Publications
Please, find a list of my publications here and on Google Scholar .
Teaching
I regularly serve as a teacher in Master’s and Bachelor’s degree programs at USI, holding lectures, lab sessions, and examinations. Find a detailed list here .