ODformer: Spatial–temporal transformers for long sequence Origin–Destination matrix forecasting against cross application scenario

Bosong, Huang,; Ruan, Ke; Yu, Weihao; Xiao, Jing; Xie, Ruzhong; Huang, Jin

doi:10.1016/j.eswa.2023.119835

Cited by 19 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some traditional methods, like Matrix Factorization (MF) and Collaborative Filtering (CF), have been explored for OD crowd/traffic flow prediction (Deng et al 2016;Gu et al 2020;Ros-Roca et al 2022). With the powerful expressive capability, graph neural networks (GNNs) have been applied to incorporate spatial dependencies in OD representation (Wang et al 2019c;Rong et al 2021;Xu et al 2023;Huang et al 2023;Shi et al 2020;Feng et al 2021). However, none focuses on noise issues or the uncertainty of prediction results.…”

Section: Related Workmentioning

confidence: 99%

Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder

Zhou,

Lu,

et al. 2024

AAAI

View full text Add to dashboard Cite

Origin-destination (OD) crowd flow, if more accurately inferred at a fine-grained level, has the potential to enhance the efficacy of various urban applications. While in practice for mining OD crowd flow with effect, the problem of spatially interpolating OD crowd flow occurs since the ineluctable missing values. This problem is further complicated by the inherent scarcity and noise nature of OD crowd flow data. In this paper, we propose an uncertainty-aware interpolative and explainable framework, namely UApex, for realizing reliable and trustworthy OD crowd flow interpolation. Specifically, we first design a Variational Multi-modal Recurrent Graph Auto-Encoder (VMR-GAE) for uncertainty-aware OD crowd flow interpolation. A key idea here is to formulate the problem as semi-supervised learning on directed graphs. Next, to mitigate the data scarcity, we incorporate a distribution alignment mechanism that can introduce supplementary modals into variational inference. Then, a dedicated decoder with a Poisson prior is proposed for OD crowd flow interpolation. Moreover, to make VMR-GAE more trustworthy, we develop an efficient and uncertainty-aware explainer that can provide explanations from the spatiotemporal topology perspective via the Shapley value. Extensive experiments on two real-world datasets validate that VMR-GAE outperforms the state-of-the-art baselines. Also, an exploratory empirical study shows that the proposed explainer can generate meaningful spatiotemporal explanations.

show abstract

Section: Related Workmentioning

confidence: 99%

Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder

Zhou,

Lu,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Kwon and Lee designed a recurrent Transformer model for coil temperature forecasting which had a good performance but also resulted in more computing burden [ 35 ]. Many other Transformer-based models have also been studied by researchers like CL-former [ 36 ], OD-former [ 37 ], and so on, which can adapt to various time series forecasting issues. All the above models have achieved favorable performance in other fields, thus, Transformer-based models are evaluated in the paper to validate the performance in crude oil prices forecasting.…”

Section: Introductionmentioning

confidence: 99%

DMEformer: A newly designed dynamic model ensemble transformer for crude oil futures prediction

Liu,

Ruan,

2023

Heliyon

View full text Add to dashboard Cite

STS2ANet: Spatio-Temporal Synchronized Sliding Attention Network for Accurate Cross-Day Origin-Destination Prediction

Wang,

Xia,

Yang

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

ODformer: Spatial–temporal transformers for long sequence Origin–Destination matrix forecasting against cross application scenario

Cited by 19 publications

References 16 publications

Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder

Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder

DMEformer: A newly designed dynamic model ensemble transformer for crude oil futures prediction

STS2ANet: Spatio-Temporal Synchronized Sliding Attention Network for Accurate Cross-Day Origin-Destination Prediction

Contact Info

Product

Resources

About