paper-with-me

홈 › Papers

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

2024-12-04 · Silu He, Peng Shen, Pingzhen Xu, Qinyao Luo, Haifeng Li

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.

📄 PDF Abstract BibTeX arXiv:2412.02942

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Temporal-Spatial Entropy Balancing for Causal Continuous Treatment-Effect Estimation

2023-12-14 · Tao Hu, Honglong Zhang, Fan Zeng, Min Du 외

In the field of intracity freight transportation, changes in order volume are significantly influenced by temporal and spatial factors. When building subsidy and pricing strategies, predicting the causal effects of these…

Estimating Direct and Indirect Causal Effects of Spatiotemporal Interventions in Presence of Spatial Interference

2024-05-13 · Sahara Ali, Omar Faruque, Jianwu Wang

Spatial interference (SI) occurs when the treatment at one location affects the outcomes at other locations. Accounting for spatial interference in spatiotemporal settings poses further challenges as interference violate…

Causal Inference

SpaCE: The Spatial Confounding Environment

2023-12-01 · Mauricio Tec, Ana Trisovic, Michelle Audirac, Sophie Woodward 외

Spatial confounding poses a significant challenge in scientific studies involving spatial data, where unobserved spatial variables can influence both treatment and outcome, possibly leading to spurious associations. To a…

Causal Inference

Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference

2025-10-09 · Ayush Khot, Miruna Oprescu, Maresa Schröder, Ai Kagawa 외 arxiv

Causal inference in spatial domains faces two intertwined challenges: (1) unmeasured spatial factors, such as weather, air pollution, or mobility, that confound treatment and outcome, and (2) interference from nearby tre…

Causal Inference

Long-term Causal Inference via Modeling Sequential Latent Confounding

2025-02-26 · Weilin Chen, Ruichu Cai, Yuguang Yan, Zhifeng Hao 외

Long-term causal inference is an important but challenging problem across various scientific domains. To solve the latent confounding problem in long-term observational studies, existing methods leverage short-term exper…

Causal Inference