DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction

• URL: http://arxiv.org/abs/2606.15346v1
• Date: Sat, 13 Jun 2026 15:14:05 GMT
• Title: DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction
• Abstract summary: Dyna-Pruner is an end-to-end framework for input-dependent co-pruning of data and model structure.<n>A shared-importance synchronization mechanism generates coupled masks that prune redundant regions.<n>Experiments on WeatherBench, SEVIR, and TaxiBJ show seamless integration with CNN, RNN, and Transformer backbones.
• Score: 24.16400471463046
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Spatio-temporal prediction supports radar/satellite nowcasting and city-scale traffic monitoring, but modern models are often too expensive for real-time deployment. This stems from a mismatch between dense computation and strong input-dependent redundancy (e.g., calm seas or clear skies). To enable automated, resource-aware architecture optimization in scalable media analysis, we propose Dyna-Pruner, an end-to-end framework for input-dependent co-pruning of data and model structure. A shared-importance synchronization mechanism generates coupled masks that prune redundant regions and their corresponding computational units (e.g., convolutional filters), yielding per-sample sparse sub-networks at inference time. Experiments on WeatherBench, SEVIR, and TaxiBJ show seamless integration with CNN, RNN, and Transformer backbones, reducing FLOPs by up to $70\%$ and achieving a $2.5\times$ speedup on NVIDIA Jetson AGX Orin with negligible accuracy loss ($<1\%$).

Related papers

• AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting [14.101995007248997]
  AsyncCouple-Flow supports weathercasting, traffic prediction, and earth-system modeling by combining heterogeneous sources such as physical fields, satellite sensors, and insitu sensors.<n>AsyncCouple-Flow outperforms state-of-the-art baselines and remains robust with up to two missing modalities.
  arXiv  Detail & Related papers  (2026-09-15T03:15:14Z)
• CNN-based Multi-In-Multi-Out Model for Efficient Spatiotemporal Prediction [0.0]
  CNN based models have difficulty considering global information due to the local properties of the kernel.<n>Models based on Transformer architecture have high complexity due to the self-attention calcuation.
  arXiv  Detail & Related papers  (2026-05-02T06:22:56Z)
• RepSFNet : A Single Fusion Network with Structural Reparameterization for Crowd Counting [6.895355763564631]
  RepSFNet is a lightweight architecture designed for accurate and real-time crowd estimation.<n>RepSFNet achieves competitive accuracy while reducing inference latency by up to 34 percent compared to recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-01-28T08:33:36Z)
• LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G [85.58816960936069]
  Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Time (Near-RT) latency and computational constraints.<n>This paper investigates a post-Transformer paradigm for efficient radio telemetry forecasting.<n>We propose a quantum-inspired state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels.
  arXiv  Detail & Related papers  (2026-01-18T12:08:38Z)
• Compression and Inference of Spiking Neural Networks on Resource-Constrained Hardware [0.2226043394835212]
  Spiking neural networks (SNNs) communicate via discrete spikes in time rather than continuous activations.<n>We present a lightweight C-based runtime for SNN inference on edge devices.<n>We exploit sparse spiking activity to prune inactive neurons and synapses, shrinking computation in upstream convolutional layers.
  arXiv  Detail & Related papers  (2025-11-15T10:02:23Z)
• Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous Racing [0.0]
  Traditional sequential network approaches may struggle to meet the real-time knowledge and decision-making demands of an autonomous agent.<n>This paper proposes a novel baseline architecture for developing sophisticated models capable of true hardware-enabled parallelism.<n>The proposed model takes raw 3D point cloud data from the LiDAR sensor as input and converts it into a 2D Bird's Eye View Map on both devices.
  arXiv  Detail & Related papers  (2024-12-24T04:56:32Z)
• Data-Free Dynamic Compression of CNNs for Tractable Efficiency [46.498278084317704]
  structured pruning approaches have shown promise in lowering floating-point operations without substantial drops in accuracy.<n>We propose HASTE (Hashing for Tractable Efficiency), a data-free, plug-and-play convolution module that instantly reduces a network's test-time inference cost without training or fine-tuning.<n>We demonstrate our approach on the popular vision benchmarks CIFAR-10 and ImageNet, where we achieve a 46.72% reduction in FLOPs with only a 1.25% loss in accuracy.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing [85.74517957717363]
  HALP accelerates inference by designing a seamless collaboration among edge devices (EDs) in Edge Computing. Experiments show that the distributed inference HALP achieves 1.7x inference acceleration for VGG-16. It is shown that the model selection with distributed inference HALP can significantly improve service reliability.
  arXiv  Detail & Related papers  (2022-11-24T19:48:30Z)
• Attention-based Feature Compression for CNN Inference Offloading in Edge Computing [93.67044879636093]
  This paper studies the computational offloading of CNN inference in device-edge co-inference systems. We propose a novel autoencoder-based CNN architecture (AECNN) for effective feature extraction at end-device. Experiments show that AECNN can compress the intermediate data by more than 256x with only about 4% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-24T18:10:01Z)
• SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication [11.763368822546468]
  We show that SWIFT converges faster with respect to run-time due to its wait-free structure. SWIFT produces loss levels for image classification, over IID and non-IID data settings, upwards 50% faster than existing SOTA algorithms.
  arXiv  Detail & Related papers  (2022-10-25T14:01:21Z)
• Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing [93.67044879636093]
  We study inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing network. We propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers.
  arXiv  Detail & Related papers  (2022-07-22T18:38:11Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels [52.60092598312894]
  We propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. Our proposed solution results in minimal energy consumption and $CO$ emission compared to the considered baselines.
  arXiv  Detail & Related papers  (2021-06-02T07:36:27Z)

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.