STDCformer: A Transformer-Based Model with a Spatial-Temporal Causal De-Confounding Strategy for Crowd Flow Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: He, Silu, Shen, Peng, Xu, Pingzhen, Luo, Qinyao, Li, Haifeng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929614926905344
author He, Silu
Shen, Peng
Xu, Pingzhen
Luo, Qinyao
Li, Haifeng
author_facet He, Silu
Shen, Peng
Xu, Pingzhen
Luo, Qinyao
Li, Haifeng
contents Existing works typically treat spatial-temporal prediction as the task of learning a function $F$ to transform historical observations to future observations. We further decompose this cross-time transformation into three processes: (1) Encoding ($E$): learning the intrinsic representation of observations, (2) Cross-Time Mapping ($M$): transforming past representations into future representations, and (3) Decoding ($D$): reconstructing future observations from the future representations. From this perspective, spatial-temporal prediction can be viewed as learning $F = E \cdot M \cdot D$, which includes learning the space transformations $\left\{{E},{D}\right\}$ between the observation space and the hidden representation space, as well as the spatial-temporal mapping $M$ from future states to past states within the representation space. This leads to two key questions: \textbf{Q1: What kind of representation space allows for mapping the past to the future? Q2: How to achieve map the past to the future within the representation space?} To address Q1, we propose a Spatial-Temporal Backdoor Adjustment strategy, which learns a Spatial-Temporal De-Confounded (STDC) representation space and estimates the de-confounding causal effect of historical data on future data. This causal relationship we captured serves as the foundation for subsequent spatial-temporal mapping. To address Q2, we design a Spatial-Temporal Embedding (STE) that fuses the information of temporal and spatial confounders, capturing the intrinsic spatial-temporal characteristics of the representations. Additionally, we introduce a Cross-Time Attention mechanism, which queries the attention between the future and the past to guide spatial-temporal mapping.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle STDCformer: A Transformer-Based Model with a Spatial-Temporal Causal De-Confounding Strategy for Crowd Flow Prediction
He, Silu
Shen, Peng
Xu, Pingzhen
Luo, Qinyao
Li, Haifeng
Artificial Intelligence
Existing works typically treat spatial-temporal prediction as the task of learning a function $F$ to transform historical observations to future observations. We further decompose this cross-time transformation into three processes: (1) Encoding ($E$): learning the intrinsic representation of observations, (2) Cross-Time Mapping ($M$): transforming past representations into future representations, and (3) Decoding ($D$): reconstructing future observations from the future representations. From this perspective, spatial-temporal prediction can be viewed as learning $F = E \cdot M \cdot D$, which includes learning the space transformations $\left\{{E},{D}\right\}$ between the observation space and the hidden representation space, as well as the spatial-temporal mapping $M$ from future states to past states within the representation space. This leads to two key questions: \textbf{Q1: What kind of representation space allows for mapping the past to the future? Q2: How to achieve map the past to the future within the representation space?} To address Q1, we propose a Spatial-Temporal Backdoor Adjustment strategy, which learns a Spatial-Temporal De-Confounded (STDC) representation space and estimates the de-confounding causal effect of historical data on future data. This causal relationship we captured serves as the foundation for subsequent spatial-temporal mapping. To address Q2, we design a Spatial-Temporal Embedding (STE) that fuses the information of temporal and spatial confounders, capturing the intrinsic spatial-temporal characteristics of the representations. Additionally, we introduce a Cross-Time Attention mechanism, which queries the attention between the future and the past to guide spatial-temporal mapping.
title STDCformer: A Transformer-Based Model with a Spatial-Temporal Causal De-Confounding Strategy for Crowd Flow Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2412.02942