paper-with-me

홈 › Papers

Temporal Graph ODEs for Irregularly-Sampled Time Series

2024-04-30 · Alessio Gravina, Daniele Zambon, Davide Bacciu, Cesare Alippi

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 networks and physical systems are characterized by continuous dynamics and sporadic observations. To address this limitation, we introduce the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced. We empirically validate the proposed approach on several graph benchmarks, showing that TG-ODE can achieve state-of-the-art performance in irregular graph stream tasks.

📄 PDF Abstract BibTeX arXiv:2404.19508

Code (1)

gravins/tg-ode 공식 구현 pytorch

Tasks

Graph Representation LearningRepresentation LearningTime Series

Similar Papers 제목 키워드 기반

Forecasting Irregularly Sampled Time Series using Graphs

2023-05-22 · Vijaya Krishna Yalavarthi, Kiran Madhusudhanan, Randolf Sholz, Nourhan Ahmed 외

Forecasting irregularly sampled time series with missing values is a crucial task for numerous real-world applications such as healthcare, astronomy, and climate sciences. State-of-the-art approaches to this problem rely…

AstronomyMissing ValuesMultivariate Time Series ForecastingTime Series

STONet: A Neural-Operator-Driven Spatio-temporal Network

2022-04-18 · Haitao Lin, Guojiang Zhao, Lirong Wu, Stan Z. Li

Graph-based spatio-temporal neural networks are effective to model the spatial dependency among discrete points sampled irregularly from unstructured grids, thanks to the great expressiveness of graph neural networks. Ho…

Missing ValuesTime SeriesTime Series Analysis

Graph-Guided Network for Irregularly Sampled Multivariate Time Series

2021-10-11 · ICLR 2022 4 · Xiang Zhang, Marko Zeman, Theodoros Tsiligkaridis, Marinka Zitnik

In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with varying time intervals between successive readouts and different subsets of variables (sensors) observed at di…

Graph Neural NetworkTime SeriesTime Series Analysis

Latent ODEs for Irregularly-Sampled Time Series

2019-07-08 · Yulia Rubanova, Ricky T. Q. Chen, David Duvenaud

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinar…

Multivariate Time Series ForecastingMultivariate Time Series ImputationTime SeriesTime Series Analysis+1

Compatible Transformer for Irregularly Sampled Multivariate Time Series

2023-10-17 · Yuxi Wei, Juntong Peng, Tong He, Chenxin Xu 외

To analyze multivariate time series, most previous methods assume regular subsampling of time series, where the interval between adjacent measurements and the number of samples remain unchanged. Practically, data collect…

Time Series