A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction

• URL: http://arxiv.org/abs/2506.13678v2
• Date: Wed, 18 Jun 2025 16:04:08 GMT
• Title: A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction
• Authors: Yi Wang, Zhenghong Wang, Fan Zhang, Chengling Tang, Chaogui Kang, Di Zhu, Zhongfu Ma, Sijie Ruan, Weiyu Zhang, Yu Zheng, Philip S. Yu, Yu Liu,
• Abstract summary: This work proposes a physics-informed deep learning framework, namely Gravity-informedtemporal Transformer (Gravityformer)<n>The underlying law of human activity can be explicitly modeled by the proposed adaptive gravity model.<n>Experiments on six real-world large-scale activity datasets demonstrate the superiority of our approach over state-of-the-art benchmarks.
• Score: 38.98706592466946
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Human activity intensity prediction is a crucial to many location-based services. Although tremendous progress has been made to model dynamic spatiotemporal patterns of human activity, most existing methods, including spatiotemporal graph neural networks (ST-GNNs), overlook physical constraints of spatial interactions and the over-smoothing phenomenon in spatial correlation modeling. To address these limitations, this work proposes a physics-informed deep learning framework, namely Gravity-informed Spatiotemporal Transformer (Gravityformer) by refining transformer attention to integrate the universal law of gravitation and explicitly incorporating constraints from spatial interactions. Specifically, it (1) estimates two spatially explicit mass parameters based on inflow and outflow, (2) models the likelihood of cross-unit interaction using closed-form solutions of spatial interactions to constrain spatial modeling randomness, and (3) utilizes the learned spatial interaction to guide and mitigate the over-smoothing phenomenon in transformer attention matrices. The underlying law of human activity can be explicitly modeled by the proposed adaptive gravity model. Moreover, a parallel spatiotemporal graph convolution transformer structure is proposed for achieving a balance between coupled spatial and temporal learning. Systematic experiments on six real-world large-scale activity datasets demonstrate the quantitative and qualitative superiority of our approach over state-of-the-art benchmarks. Additionally, the learned gravity attention matrix can be disentangled and interpreted based on geographical laws. This work provides a novel insight into integrating physical laws with deep learning for spatiotemporal predictive learning.

Related papers

• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Smooth and Sparse Latent Dynamics in Operator Learning with Jerk Regularization [1.621267003497711]
  This paper introduces a continuous operator learning framework that incorporates jagged regularization into the learning of the compressed latent space. The framework allows for inference at any desired spatial or temporal resolution. The effectiveness of this framework is demonstrated through a two-dimensional unsteady flow problem governed by the Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-02-23T22:38:45Z)
• Triplet Attention Transformer for Spatiotemporal Predictive Learning [9.059462850026216]
  We propose an innovative triplet attention transformer designed to capture both inter-frame dynamics and intra-frame static features. The model incorporates the Triplet Attention Module (TAM), which replaces traditional recurrent units by exploring self-attention mechanisms in temporal, spatial, and channel dimensions.
  arXiv  Detail & Related papers  (2023-10-28T12:49:33Z)
• Spatio-Temporal Branching for Motion Prediction using Motion Increments [55.68088298632865]
  Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications. Traditional methods rely on hand-crafted features and machine learning techniques. We propose a noveltemporal-temporal branching network using incremental information for HMP.
  arXiv  Detail & Related papers  (2023-08-02T12:04:28Z)
• Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
  Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
  arXiv  Detail & Related papers  (2022-10-13T10:00:30Z)
• Motion Prediction via Joint Dependency Modeling in Phase Space [40.54430409142653]
  We introduce a novel convolutional neural model to leverage explicit prior knowledge of motion anatomy. We then propose a global optimization module that learns the implicit relationships between individual joint features. Our method is evaluated on large-scale 3D human motion benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-07T08:30:01Z)
• Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems [15.923190628643681]
  One of the major challenges is to infer the underlying causes, which generate the perceived data stream. Success of machine learning based predictive models requires massive annotated data for model training. Our experiments on both synthetic and real-world datasets exhibit that the proposed ST-PCNN with active learning converges to optimal accuracy with substantially fewer instances.
  arXiv  Detail & Related papers  (2021-08-11T18:05:55Z)
• A Spatial-Temporal Attentive Network with Spatial Continuity for Trajectory Prediction [74.00750936752418]
  We propose a novel model named spatial-temporal attentive network with spatial continuity (STAN-SC) First, spatial-temporal attention mechanism is presented to explore the most useful and important information. Second, we conduct a joint feature sequence based on the sequence and instant state information to make the generative trajectories keep spatial continuity.
  arXiv  Detail & Related papers  (2020-03-13T04:35:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.