English
Related papers

Related papers: Learning Time-Varying Graph Signals via Koopman

200 papers

Variational autoencoder (VAE) neural networks can be trained to generate power system states that capture both marginal distribution and multivariate dependencies of historical data. The coordinates of the latent space codes of VAEs have…

Systems and Control · Electrical Eng. & Systems 2023-03-22 Chenguang Wang , Ensieh Sharifnia , Simon H. Tindemans , Peter Palensky

Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables and these models use a nonlinear function (generator) to map latent samples into the data space.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Pourya Shamsolmoali , Masoumeh Zareapoor , Huiyu Zhou , Dacheng Tao , Xuelong Li

Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, which is in contrast with advances in generative models for images and text. Is it…

Machine Learning · Computer Science 2018-02-13 Martin Simonovsky , Nikos Komodakis

Neural networks for structured data like graphs have been studied extensively in recent years. To date, the bulk of research activity has focused mainly on static graphs. However, most real-world networks are dynamic since their topology…

Machine Learning · Computer Science 2020-03-03 Changmin Wu , Giannis Nikolentzos , Michalis Vazirgiannis

While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored. We aim to close this gap by proposing a unified probabilistic model for…

Machine Learning · Computer Science 2019-07-15 Qingyu Zhao , Ehsan Adeli , Nicolas Honnorat , Tuo Leng , Kilian M. Pohl

Graph-based methods for signal processing have shown promise for the analysis of data exhibiting irregular structure, such as those found in social, transportation, and sensor networks. Yet, though these systems are often dynamic,…

Machine Learning · Computer Science 2016-06-23 Nathanael Perraudin , Andreas Loukas , Francesco Grassi , Pierre Vandergheynst

Graphs are commonly used to represent objects, such as images and text, for pattern classification. In a dynamic world, an object may continuously evolve over time, and so does the graph extracted from the underlying object. These changes…

Data Structures and Algorithms · Computer Science 2017-06-14 Haishuai Wang

Spatial-temporal graph representations play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, a key challenge lies in the noisy and sparse…

Machine Learning · Computer Science 2025-08-15 Qianru Zhang , Xinyi Gao , Haixin Wang , Dong Huang , Siu-Ming Yiu , Hongzhi Yin

The rising use of machine learning in various fields requires robust methods to create synthetic tabular data. Data should preserve key characteristics while addressing data scarcity challenges. Current approaches based on Generative…

Machine Learning · Computer Science 2024-11-15 Patricia A. Apellániz , Juan Parras , Santiago Zazo

Dynamic systems of graph signals are encountered in various applications, including social networks, power grids, and transportation. While such systems can often be described as state space (SS) models, tracking graph signals via…

Signal Processing · Electrical Eng. & Systems 2023-11-29 Itay Buchnik , Guy Sagi , Nimrod Leinwand , Yuval Loya , Nir Shlezinger , Tirza Routtenberg

Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically…

Machine Learning · Computer Science 2020-12-11 Mariella Dimiccoli , Herwig Wendt

We present the Evolving Graph Fourier Transform (EFT), the first invertible spectral transform that captures evolving representations on temporal graphs. We motivate our work by the inadequacy of existing methods for capturing the evolving…

Machine Learning · Computer Science 2024-04-19 Anson Bastos , Kuldeep Singh , Abhishek Nadgeri , Manish Singh , Toyotaro Suzumura

This paper introduces the temporally-consistent bilinearly recurrent autoencoder (tcBLRAN), a Koopman operator based neural network architecture for modeling a control-affine nonlinear control system. The proposed method extends traditional…

Systems and Control · Electrical Eng. & Systems 2025-03-26 Ananda Chakrabarti , Indranil Nayak , Debdipta Goswami

How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently…

Machine Learning · Computer Science 2018-03-20 Rakshit Trivedi , Mehrdad Farajtabar , Prasenjeet Biswal , Hongyuan Zha

This study presents a framework for predicting unsteady transonic wing pressure distributions, integrating an autoencoder architecture with graph convolutional networks and graph-based temporal layers to model time dependencies. The…

Machine Learning · Computer Science 2024-11-19 Gabriele Immordino , Andrea Vaiuso , Andrea Da Ronch , Marcello Righi

Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work…

Machine Learning · Computer Science 2024-01-15 Bozhen Hu , Zelin Zang , Jun Xia , Lirong Wu , Cheng Tan , Stan Z. Li

In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases to improve accuracy and generalization of the resulting…

Machine Learning · Computer Science 2022-06-07 Quercus Hernández , Alberto Badías , Francisco Chinesta , Elías Cueto

This paper introduces new model parameterizations for learning discrete-time dynamical systems from data via the Koopman operator and studies their properties. Whereas most existing works on Koopman learning do not take into account the…

Systems and Control · Electrical Eng. & Systems 2025-05-09 Fletcher Fan , Bowen Yi , David Rye , Guodong Shi , Ian R. Manchester

Representation learning on static graph-structured data has shown a significant impact on many real-world applications. However, less attention has been paid to the evolving nature of temporal networks, in which the edges are often changing…

Machine Learning · Computer Science 2021-08-24 Jing Ma , Qiuchen Zhang , Jian Lou , Li Xiong , Joyce C. Ho

We consider the problem of encoding pairwise correlations between coupled dynamical systems in a low-dimensional latent space based on few distinct observations. We used variational autoencoders (VAE) to embed temporal correlations between…