Search Results for author:
Found 46 papers, 22 papers with code
Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
Virtual sensing techniques allow for inferring signals at new unmonitored locations by exploiting spatio-temporal measurements coming from physical sensors at different locations.
Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
The input time series are progressively coarsened over time and space, obtaining a pool of representations that capture heterogeneous temporal and spatial dynamics.
Graph Deep Learning for Time Series Forecasting
The conditioning can take the form of an architectural inductive bias on the neural forecasting architecture, resulting in a family of deep learning models called spatiotemporal graph neural networks.
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection
In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation.
Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting
Existing relationships among time series can be exploited as inductive biases in learning effective forecasting models.
Feudal Graph Reinforcement Learning
In this work, we propose a novel methodology, named Feudal Graph Reinforcement Learning (FGRL), that addresses such challenges by relying on hierarchical RL and a pyramidal message-passing architecture.
Relational Inductive Biases for Object-Centric Image Generation
Conditioning image generation on specific features of the desired output is a key ingredient of modern generative models.
Graph Kalman Filters
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 associated with newly observed system outputs.
Taming Local Effects in Graph-based Spatiotemporal Forecasting
Spatiotemporal graph neural networks have shown to be effective in time series forecasting applications, achieving better performance than standard univariate predictors in several settings.
Where and How to Improve Graph-based Spatio-temporal Predictors
The proposed AZ-analysis constitutes a valuable asset for discovering and highlighting those space-time regions where the model can be improved with respect to performance.
Graph state-space models
State-space models constitute an effective modeling tool to describe multivariate time series and operate by maintaining an updated representation of the system state from which predictions are made.
A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream Classification
In real-world applications, the process generating the data might suffer from nonstationary effects (e. g., due to seasonality, faults affecting sensors or actuators, and changes in the users' behaviour).
Scalable Spatiotemporal Graph Neural Networks
The training procedure can then be parallelized node-wise by sampling the node embeddings without breaking any dependency, thus enabling scalability to large networks.
Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations
In particular, we propose a novel class of attention-based architectures that, given a set of highly sparse discrete observations, learn a representation for points in time and space by exploiting a spatiotemporal propagation architecture aligned with the imputation task.
Sparse Graph Learning from Spatiotemporal Time Series
Outstanding achievements of graph neural networks for spatiotemporal time series analysis show that relational constraints introduce an effective inductive bias into neural forecasting architectures.
AZ-whiteness test: a test for uncorrelated noise on spatio-temporal graphs
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.
A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
The design of efficient hardware accelerators for high-throughput data-processing applications, e. g., deep neural networks, is a challenging task in computer architecture design.
Graph neural network-based fault diagnosis: a review
Graph neural network (GNN)-based fault diagnosis (FD) has received increasing attention in recent years, due to the fact that data coming from several application domains can be advantageously represented as graphs.
Learning Graph Cellular Automata
Cellular automata (CA) are a class of computational models that exhibit rich dynamics emerging from the local interaction of cells arranged in a regular lattice.
Understanding Pooling in Graph Neural Networks
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 the size of graphs.
Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks
In particular, we introduce a novel graph neural network architecture, named GRIN, which aims at reconstructing missing data in the different channels of a multivariate time series by learning spatio-temporal representations through message passing.
Ranked #1 on
Traffic Data Imputation
on PEMS-BAY Point Missing
Graph Edit Networks
With this result, we hope to provide a firm theoretical basis for a next generation of time series prediction models.
Learn to Synchronize, Synchronize to Learn
In recent years, the machine learning community has seen a continuous growing interest in research aimed at investigating dynamical aspects of both training procedures and machine learning models.
Graph Neural Networks in TensorFlow and Keras with Spektral
In this paper we present Spektral, an open-source Python library for building graph neural networks with TensorFlow and the Keras application programming interface.
Input-to-State Representation in linear reservoirs dynamics
Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance.
Deep Reinforcement Learning with Weighted Q-Learning
In this regard, Weighted Q-Learning (WQL) effectively reduces bias and shows remarkable results in stochastic environments.
Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations.
Ranked #1 on
Graph Classification
on Bench-hard
Mincut Pooling in Graph Neural Networks
For each node, our method learns a soft cluster assignment vector that depends on the node features, the target inference task (e. g., a graph classification loss), and, thanks to the minCut objective, also on the connectivity structure of the graph.
Graph Random Neural Features for Distance-Preserving Graph Representations
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.
Distributed Deep Convolutional Neural Networks for the Internet-of-Things
Severe constraints on memory and computation characterizing the Internet-of-Things (IoT) units may prevent the execution of Deep Learning (DL)-based solutions, which typically demand large memory and high processing load.
Deep Learning for Time Series Forecasting: The Electric Load Case
Management and efficient operations in critical infrastructure such as Smart Grids take huge advantage of accurate power load forecasting which, due to its nonlinear nature, remains a challenging task.
Spectral Clustering with Graph Neural Networks for Graph Pooling
Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph.
Echo State Networks with Self-Normalizing Activations on the Hyper-Sphere
Finding such a region requires searching in hyper-parameter space in a sensible way: hyper-parameter configurations marginally outside such a region might yield networks exhibiting fully developed chaos, hence producing unreliable computations.
Autoregressive Models for Sequences of Graphs
This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models.
Graph Neural Networks with convolutional ARMA filters
Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters.
Ranked #4 on
Skeleton Based Action Recognition
on SBU
Adversarial Autoencoders with Constant-Curvature Latent Manifolds
Constant-curvature Riemannian manifolds (CCMs) have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for some relevant properties of data, like hierarchy and circularity.
A characterization of the Edge of Criticality in Binary Echo State Networks
Echo State Networks (ESNs) are simplified recurrent neural network models composed of a reservoir and a linear, trainable readout layer.
Change Point Methods on a Sequence of Graphs
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 in the stochastic process generating the graphs.
Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited for embedding graphs.
Anomaly and Change Detection in Graph Streams through Constant-Curvature Manifold Embeddings
The proposed methodology consists in embedding graphs into a geometric space and perform change detection there by means of conventional methods for numerical streams.
Concept Drift and Anomaly Detection in Graph Streams
Graph representations offer powerful and intuitive ways to describe data in a multitude of application domains.
Multiplex visibility graphs to investigate recurrent neural networks dynamics
We show that topological properties of such a multiplex reflect important features of RNN dynamics and are used to guide the tuning procedure.
One-class classifiers based on entropic spanning graphs
The final partition is derived by exploiting a criterion based on mutual information minimization.
Determination of the edge of criticality in echo state networks through Fisher information maximization
In this paper, we aim at addressing this issue by proposing a theoretically motivated, unsupervised method based on Fisher information for determining the edge of criticality in recurrent neural networks.
Investigating echo state networks dynamics by means of recurrence analysis
We verify that the determination of the edge of stability provided by such RQA measures is more accurate than two well-known criteria based on the Jacobian matrix of the reservoir.
Change Detection in Multivariate Datastreams: Likelihood and Detectability Loss
We address the problem of detecting changes in multivariate datastreams, and we investigate the intrinsic difficulty that change-detection methods have to face when the data dimension scales.
