Dynamic Sparse Training with Structured Sparsity

• URL: http://arxiv.org/abs/2305.02299v4
• Date: Wed, 21 Feb 2024 23:31:49 GMT
• Title: Dynamic Sparse Training with Structured Sparsity
• Authors: Mike Lasby, Anna Golubeva, Utku Evci, Mihai Nica, Yani Ioannou
• Abstract summary: Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training. We propose a sparse-to-sparse DST method, Structured RigL (SRigL), to learn a variant of fine-grained structured N:M sparsity. We demonstrate a real-world acceleration of 3.4x/2.5x on CPU for online inference and 1.7x/13.0x on GPU for inference with a batch size of 256.
• Score: 11.778353786208765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference. Although the resulting models are highly sparse and theoretically less computationally expensive, achieving speedups with unstructured sparsity on real-world hardware is challenging. In this work, we propose a sparse-to-sparse DST method, Structured RigL (SRigL), to learn a variant of fine-grained structured N:M sparsity by imposing a constant fan-in constraint. Using our empirical analysis of existing DST methods at high sparsity, we additionally employ a neuron ablation method which enables SRigL to achieve state-of-the-art sparse-to-sparse structured DST performance on a variety of Neural Network (NN) architectures. Using a 90% sparse linear layer, we demonstrate a real-world acceleration of 3.4x/2.5x on CPU for online inference and 1.7x/13.0x on GPU for inference with a batch size of 256 when compared to equivalent dense/unstructured (CSR) sparse layers, respectively.

Related papers

• Dynamic Sparsity Is Channel-Level Sparsity Learner [91.31071026340746]
  Dynamic sparse training (DST) is a leading sparse training approach. Channel-aware dynamic sparse (Chase) seamlessly translates the promise of unstructured dynamic sparsity to channel-level sparsity. Our approach translates unstructured sparsity to channel-wise sparsity.
  arXiv  Detail & Related papers  (2023-05-30T23:33:45Z)
• FSCNN: A Fast Sparse Convolution Neural Network Inference System [31.474696818171953]
  Convolution neural networks (CNNs) have achieved remarkable success, but typically accompany high computation cost and numerous redundant weight parameters. To reduce the FLOPs, structure pruning is a popular approach to remove the entire hidden structures via introducing coarse-grained sparsity. We present an efficient convolution neural network inference system to accelerate its forward pass by utilizing the fine-grained sparsity of compressed CNNs.
  arXiv  Detail & Related papers  (2022-12-17T06:44:58Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation [70.75043144299168]
  Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. It is a challenge to efficiently train SNNs due to their non-differentiability. We propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance.
  arXiv  Detail & Related papers  (2022-05-01T12:44:49Z)
• Scaling Structured Inference with Randomization [64.18063627155128]
  We propose a family of dynamic programming (RDP) randomized for scaling structured models to tens of thousands of latent states. Our method is widely applicable to classical DP-based inference. It is also compatible with automatic differentiation so can be integrated with neural networks seamlessly.
  arXiv  Detail & Related papers  (2021-12-07T11:26:41Z)
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch [75.69506249886622]
  Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network.
  arXiv  Detail & Related papers  (2021-02-08T05:55:47Z)
• Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training [16.81321230135317]
  We propose the concept of In-Time Over- Resibilityization (ITOP) in sparse training. ITOP closes the gap in the express between sparse training and dense training. We present a series of experiments to support our conjecture and achieve the state-of-the-art sparse training performance.
  arXiv  Detail & Related papers  (2021-02-04T20:59:31Z)
• Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training [0.5219568203653523]
  We develop a sparse DNN training accelerator that produces pruned models with the same accuracy as dense models without first training, then pruning, and finally retraining, a dense model. Compared to training the equivalent unpruned models using a state-of-the-art DNN accelerator without sparse training support, Procrustes consumes up to 3.26$times$ less energy and offers up to 4$times$ speedup across a range of models, while pruning weights by an order of magnitude and maintaining unpruned accuracy.
  arXiv  Detail & Related papers  (2020-09-23T07:39:55Z)
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes [98.65457534223539]
  We propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes. The proposed method achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps.
  arXiv  Detail & Related papers  (2020-03-11T08:45:53Z)

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.