Long Range Propagation on Continuous-Time Dynamic Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gravina, Alessio, Lovisotto, Giulio, Gallicchio, Claudio, Bacciu, Davide, Grohnfeldt, Claas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912270441775104
author Gravina, Alessio
Lovisotto, Giulio
Gallicchio, Claudio
Bacciu, Davide
Grohnfeldt, Claas
author_facet Gravina, Alessio
Lovisotto, Giulio
Gallicchio, Claudio
Bacciu, Davide
Grohnfeldt, Claas
contents Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurrent- or self-attention-based methods perform poorly on long-range tasks. These tasks require correlating information that occurred "far" away from the current event, either spatially (higher-order node information) or along the time dimension (events occurred in the past). To address long-range dependencies, we introduce Continuous-Time Graph Anti-Symmetric Network (CTAN). Grounded within the ordinary differential equations framework, our method is designed for efficient propagation of information. In this paper, we show how CTAN's (i) long-range modeling capabilities are substantiated by theoretical findings and how (ii) its empirical performance on synthetic long-range benchmarks and real-world benchmarks is superior to other methods. Our results motivate CTAN's ability to propagate long-range information in C-TDGs as well as the inclusion of long-range tasks as part of temporal graph models evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02740
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Long Range Propagation on Continuous-Time Dynamic Graphs
Gravina, Alessio
Lovisotto, Giulio
Gallicchio, Claudio
Bacciu, Davide
Grohnfeldt, Claas
Machine Learning
Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurrent- or self-attention-based methods perform poorly on long-range tasks. These tasks require correlating information that occurred "far" away from the current event, either spatially (higher-order node information) or along the time dimension (events occurred in the past). To address long-range dependencies, we introduce Continuous-Time Graph Anti-Symmetric Network (CTAN). Grounded within the ordinary differential equations framework, our method is designed for efficient propagation of information. In this paper, we show how CTAN's (i) long-range modeling capabilities are substantiated by theoretical findings and how (ii) its empirical performance on synthetic long-range benchmarks and real-world benchmarks is superior to other methods. Our results motivate CTAN's ability to propagate long-range information in C-TDGs as well as the inclusion of long-range tasks as part of temporal graph models evaluation.
title Long Range Propagation on Continuous-Time Dynamic Graphs
topic Machine Learning
url https://arxiv.org/abs/2406.02740