Salvato in:
Dettagli Bibliografici
Autori principali: Mo, Zhaobin, Liu, Qingyuan, Yan, Baohua, Zhang, Longxiang, Di, Xuan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.16142
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917847739924480
author Mo, Zhaobin
Liu, Qingyuan
Yan, Baohua
Zhang, Longxiang
Di, Xuan
author_facet Mo, Zhaobin
Liu, Qingyuan
Yan, Baohua
Zhang, Longxiang
Di, Xuan
contents Spatiotemporal prediction over graphs (STPG) is crucial for transportation systems. In existing STPG models, an adjacency matrix is an important component that captures the relations among nodes over graphs. However, most studies calculate the adjacency matrix by directly memorizing the data, such as distance- and correlation-based matrices. These adjacency matrices do not consider potential pattern shift for the test data, and may result in suboptimal performance if the test data has a different distribution from the training one. This issue is known as the Out-of-Distribution generalization problem. To address this issue, in this paper we propose a Causal Adjacency Learning (CAL) method to discover causal relations over graphs. The learned causal adjacency matrix is evaluated on a downstream spatiotemporal prediction task using real-world graph data. Results demonstrate that our proposed adjacency matrix can capture the causal relations, and using our learned adjacency matrix can enhance prediction performance on the OOD test data, even though causal learning is not conducted in the downstream task.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16142
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Causal Adjacency Learning for Spatiotemporal Prediction Over Graphs
Mo, Zhaobin
Liu, Qingyuan
Yan, Baohua
Zhang, Longxiang
Di, Xuan
Machine Learning
Spatiotemporal prediction over graphs (STPG) is crucial for transportation systems. In existing STPG models, an adjacency matrix is an important component that captures the relations among nodes over graphs. However, most studies calculate the adjacency matrix by directly memorizing the data, such as distance- and correlation-based matrices. These adjacency matrices do not consider potential pattern shift for the test data, and may result in suboptimal performance if the test data has a different distribution from the training one. This issue is known as the Out-of-Distribution generalization problem. To address this issue, in this paper we propose a Causal Adjacency Learning (CAL) method to discover causal relations over graphs. The learned causal adjacency matrix is evaluated on a downstream spatiotemporal prediction task using real-world graph data. Results demonstrate that our proposed adjacency matrix can capture the causal relations, and using our learned adjacency matrix can enhance prediction performance on the OOD test data, even though causal learning is not conducted in the downstream task.
title Causal Adjacency Learning for Spatiotemporal Prediction Over Graphs
topic Machine Learning
url https://arxiv.org/abs/2411.16142