116 citations · 320 across the 21 of their papers we have counts for
22 papers
BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
Luca Colombo, Fabrizio Pittorino, Daniele Zambon +3
Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy…
The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
Giovanni Donghi, Daniele Zambon, Luca Pasa +2
Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offlin…
Online Continual Graph Learning
Giovanni Donghi, Luca Pasa, Daniele Zambon +2
Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updati…
PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning
Daniele Zambon, Michele Cattaneo, Ivan Marisca +3
Accurate weather forecasts are essential for supporting a wide range of activities and decision-making processes, as well as mitigating the impacts of adverse weather events. While…
Learning Latent Graph Structures and their Uncertainty
Alessandro Manenti, Daniele Zambon, Cesare Alippi
Graph neural networks use relational information as an inductive bias to enhance prediction performance. Not rarely, task-relevant relations are unknown and graph structure learnin…
Temporal Graph ODEs for Irregularly-Sampled Time Series
Alessio Gravina, Daniele Zambon, Davide Bacciu +1
Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social network…
Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
Giovanni De Felice, Andrea Cini, Daniele Zambon +2
Virtual sensing techniques allow for inferring signals at new unmonitored locations by exploiting spatio-temporal measurements coming from physical sensors at different locations.…
Graph Deep Learning for Time Series Forecasting
Andrea Cini, Ivan Marisca, Daniele Zambon +1
Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors…
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection
Ming Jin, Huan Yee Koh, Qingsong Wen +5
Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time…
Graph Kalman Filters
Cesare Alippi, Daniele Zambon
The well-known Kalman filters model dynamical systems by relying on state-space representations with the next state updated, and its uncertainty controlled, by fresh information as…
Taming Local Effects in Graph-based Spatiotemporal Forecasting
Andrea Cini, Ivan Marisca, Daniele Zambon +1
Spatiotemporal graph neural networks have shown to be effective in time series forecasting applications, achieving better performance than standard univariate predictors in several…
Assessment of Spatio-Temporal Predictors in the Presence of Missing and Heterogeneous Data
Daniele Zambon, Cesare Alippi
Deep learning methods achieve remarkable predictive performance in modeling complex, large-scale data. However, assessing the quality of derived models has become increasingly chal…
Graph State-Space Models and Latent Relational Inference
Daniele Zambon, Andrea Cini, Cesare Alippi
State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation i…
Sparse Graph Learning from Spatiotemporal Time Series
Andrea Cini, Daniele Zambon, Cesare Alippi
Outstanding achievements of graph neural networks for spatiotemporal time series analysis show that relational constraints introduce an effective inductive bias into neural forecas…
AZ-whiteness test: a test for uncorrelated noise on spatio-temporal graphs
Daniele Zambon, Cesare Alippi
We present the first whiteness test for graphs, i.e., a whiteness test for multivariate time series associated with the nodes of a dynamic graph. The statistical test aims at findi…
Understanding Pooling in Graph Neural Networks
Daniele Grattarola, Daniele Zambon, Filippo Maria Bianchi +1
Inspired by the conventional pooling layers in convolutional neural networks, many recent works in the field of graph machine learning have introduced pooling operators to reduce t…
Graph Random Neural Features for Distance-Preserving Graph Representations
Daniele Zambon, Cesare Alippi, Lorenzo Livi
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding natura…
Autoregressive Models for Sequences of Graphs
Daniele Zambon, Daniele Grattarola, Lorenzo Livi +1
This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very g…
Anomaly and Change Detection in Graph Streams through Constant-Curvature Manifold Embeddings
Daniele Zambon, Lorenzo Livi, Cesare Alippi
Mapping complex input data into suitable lower dimensional manifolds is a common procedure in machine learning. This step is beneficial mainly for two reasons: (1) it reduces the d…
Change Point Methods on a Sequence of Graphs
Daniele Zambon, Cesare Alippi, Lorenzo Livi
Given a finite sequence of graphs, e.g., coming from technological, biological, and social networks, the paper proposes a methodology to identify possible changes in stationarity i…
Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
Daniele Grattarola, Daniele Zambon, Cesare Alippi +1
The space of graphs is often characterised by a non-trivial geometry, which complicates learning and inference in practical applications. A common approach is to use embedding tech…
Concept Drift and Anomaly Detection in Graph Streams
Daniele Zambon, Cesare Alippi, Lorenzo Livi
Graph representations offer powerful and intuitive ways to describe data in a multitude of application domains. Here, we consider stochastic processes generating graphs and propose…