STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization

• URL: http://arxiv.org/abs/2505.19547v2
• Date: Tue, 27 May 2025 14:17:24 GMT
• Title: STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
• Authors: Haoyu Zhang, Wentao Zhang, Hao Miao, Xinke Jiang, Yuchen Fang, Yifan Zhang,
• Abstract summary: We propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework, STRAP.<n>During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism.<n>Experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks.
• Score: 34.53308463024231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD) scenarios, where both temporal dynamics and spatial structures evolve beyond the training distribution. To address this problem, we propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework,STRAP, which enhances model generalization by integrating retrieval-augmented learning into the STGNN continue learning pipeline. The core of STRAP is a compact and expressive pattern library that stores representative spatio-temporal patterns enriched with historical, structural, and semantic information, which is obtained and optimized during the training phase. During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism. This not only strengthens spatio-temporal representations but also mitigates catastrophic forgetting. Moreover, STRAP introduces a knowledge-balancing objective to harmonize new information with retrieved knowledge. Extensive experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks, demonstrating its robustness, adaptability, and strong generalization capability without task-specific fine-tuning.

Related papers

• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• Multivariate Long-term Time Series Forecasting with Fourier Neural Filter [55.09326865401653]
  We introduce FNF as the backbone and DBD as architecture to provide excellent learning capabilities and optimal learning pathways for spatial-temporal modeling.<n>We show that FNF unifies local time-domain and global frequency-domain information processing within a single backbone that extends naturally to spatial modeling.
  arXiv  Detail & Related papers  (2025-06-10T18:40:20Z)
• Multi-Head Self-Attending Neural Tucker Factorization [5.734615417239977]
  We introduce a neural network-based tensor factorization approach tailored for learning representations of high-dimensional and incomplete (HDI) tensors.<n>The proposed MSNTucF model demonstrates superior performance compared to state-of-the-art benchmark models in estimating missing observations.
  arXiv  Detail & Related papers  (2025-01-16T13:04:15Z)
• 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)
• DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models [16.435352947791923]
  We propose a novel Dynamic Graph structure learning framework with the Selective State Space Models (Mamba)<n>Our framework is superior to state-of-the-art baselines against adversarial attacks.
  arXiv  Detail & Related papers  (2024-12-11T07:32:38Z)
• GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks [24.323017830938394]
  This work aims to address challenges by introducing a pre-training framework that seamlessly integrates with baselines and enhances their performance. The framework is built upon two key designs: (i) We propose a. apple-to-apple mask autoencoder as a pre-training model for learning-temporal dependencies. These modules are specifically designed to capture intra-temporal customized representations and semantic- and inter-cluster relationships.
  arXiv  Detail & Related papers  (2023-11-07T02:36:24Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting [52.47493322446537]
  We develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets.
  arXiv  Detail & Related papers  (2023-05-22T13:39:44Z)
• Attention-based Spatial-Temporal Graph Convolutional Recurrent Networks for Traffic Forecasting [12.568905377581647]
  Traffic forecasting is one of the most fundamental problems in transportation science and artificial intelligence. Existing methods cannot accurately model both long-term and short-term temporal correlations simultaneously. We propose a novel spatial-temporal neural network framework, which consists of a graph convolutional recurrent module (GCRN) and a global attention module.
  arXiv  Detail & Related papers  (2023-02-25T03:37:00Z)
• SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss [4.504870356809408]
  We propose a novel loss objective combined with -GAN based on an autogressive embedding to reinforce the learning oftemporal dynamics. We show that our embedding loss improves performance without any changes to the architecture of -GAN, highlighting our model's increased capacity for autocorrelationre structures.
  arXiv  Detail & Related papers  (2021-09-30T12:10:05Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)

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.