Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training

• URL: http://arxiv.org/abs/2602.19113v2
• Date: Mon, 02 Mar 2026 08:35:46 GMT
• Title: Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training
• Authors: Wei Chen, Junle Chen, Yuqian Wu, Yuxuan Liang, Xiaofang Zhou,
• Abstract summary: Training deep learning models on massive, often redundant datasets presents a significant computational bottleneck.<n>In this paper, we explore a novel training techniques, namely learning from complexity with dynamic sample pruning.<n>We show that ST-Prune significantly accelerates the training speed while maintaining or even improving the model performance.
• Score: 36.98769959300113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatio-temporal forecasting is fundamental to intelligent systems in transportation, climate science, and urban planning. However, training deep learning models on the massive, often redundant, datasets from these domains presents a significant computational bottleneck. Existing solutions typically focus on optimizing model architectures or optimizers, while overlooking the inherent inefficiency of the training data itself. This conventional approach of iterating over the entire static dataset each epoch wastes considerable resources on easy-to-learn or repetitive samples. In this paper, we explore a novel training-efficiency techniques, namely learning from complexity with dynamic sample pruning, ST-Prune, for spatio-temporal forecasting. Through dynamic sample pruning, we aim to intelligently identify the most informative samples based on the model's real-time learning state, thereby accelerating convergence and improving training efficiency. Extensive experiments conducted on real-world spatio-temporal datasets show that ST-Prune significantly accelerates the training speed while maintaining or even improving the model performance, and it also has scalability and universality.

Related papers

• When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training [58.25341036646294]
  We analytically examine why learning recurrent poles does not provide tangible benefits in data and empirically offer real-time learning scenarios.<n>We show that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.
  arXiv  Detail & Related papers  (2026-02-25T00:15:13Z)
• Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data [89.96277093034547]
  We introduce EntroDrop, an entropy-guided token dropout method that functions as structured data regularization.<n>We show that EntroDrop consistently outperforms standard regularization baselines and maintains robust performance throughout extended multi-epoch training.
  arXiv  Detail & Related papers  (2025-12-29T12:35:51Z)
• A Deep Learning Approach for Spatio-Temporal Forecasting of InSAR Ground Deformation in Eastern Ireland [2.840858735842673]
  Monitoring ground displacement is crucial for urban infrastructure and mitigating geological hazards.<n>This paper introduces a novel deep learning framework that transforms sparse point measurements into a dense-temporal tensor.<n>Results demonstrate that the proposed architecture provides more accurate and spatially coherent forecasts.
  arXiv  Detail & Related papers  (2025-09-17T17:10:18Z)
• Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting [40.9030781267984]
  We propose a novel test-time computing paradigm, namely learning with calibration, ST-TTC, for S-temporal forecasting.<n>We aim to capture periodic structural biases arising from non-stationarity during the testing phase and perform real-time bias correction on predictions to improve accuracy.
  arXiv  Detail & Related papers  (2025-05-31T16:48:27Z)
• STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization [29.10084723132903]
  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.
  arXiv  Detail & Related papers  (2025-05-26T06:11:05Z)
• FlowDistill: Scalable Traffic Flow Prediction via Distillation from LLMs [5.6685153523382015]
  FlowDistill is a lightweight traffic prediction framework based on knowledge distillation from large language models (LLMs)<n>Despite its simplicity, FlowDistill consistently outperforms state-of-the-art models in prediction accuracy while requiring significantly less training data.
  arXiv  Detail & Related papers  (2025-04-02T19:54:54Z)
• EasyST: A Simple Framework for Spatio-Temporal Prediction [18.291117879544945]
  We propose a simple framework for spatial-temporal prediction - EasyST paradigm. It learns lightweight and robust Multi-Layer Perceptrons (MLPs) generalization by distilling knowledge from complex-temporal GNNs. EasyST surpasses state-of-the-art approaches in terms of efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-09-10T11:40:01Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• 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)
• SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning [61.419914155985886]
  We propose SimVPv2, a streamlined model that eliminates the need for Unet architectures for spatial and temporal modeling.<n>SimVPv2 not only simplifies the model architecture but also improves both performance and computational efficiency.<n>On the standard Moving MNIST benchmark, SimVPv2 achieves superior performance compared to SimVP, with fewer FLOPs, about half the training time and 60% faster inference efficiency.
  arXiv  Detail & Related papers  (2022-11-22T08:01:33Z)
• Towards Robust Dataset Learning [90.2590325441068]
  We propose a principled, tri-level optimization to formulate the robust dataset learning problem. Under an abstraction model that characterizes robust vs. non-robust features, the proposed method provably learns a robust dataset.
  arXiv  Detail & Related papers  (2022-11-19T17:06:10Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)

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.