ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
- URL: http://arxiv.org/abs/2408.12561v1
- Date: Thu, 22 Aug 2024 17:22:59 GMT
- Title: ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
- Authors: Lujia Zhong, Shuo Huang, Yonggang Shi,
- Abstract summary: Back-propagation (BP) is a major source of computational expense during training deep learning models.
We propose a general, energy-efficient convolution module that can be seamlessly integrated into any deep learning architecture.
- Score: 4.77407121905745
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, deep learning has made remarkable strides, especially with generative modeling, such as large language models and probabilistic diffusion models. However, training these models often involves significant computational resources, requiring billions of petaFLOPs. This high resource consumption results in substantial energy usage and a large carbon footprint, raising critical environmental concerns. Back-propagation (BP) is a major source of computational expense during training deep learning models. To advance research on energy-efficient training and allow for sparse learning on any machine and device, we propose a general, energy-efficient convolution module that can be seamlessly integrated into any deep learning architecture. Specifically, we introduce channel-wise sparsity with additional gradient selection schedulers during backward based on the assumption that BP is often dense and inefficient, which can lead to over-fitting and high computational consumption. Our experiments demonstrate that our approach reduces 40\% computations while potentially improving model performance, validated on image classification and generation tasks. This reduction can lead to significant energy savings and a lower carbon footprint during the research and development phases of large-scale AI systems. Additionally, our method mitigates over-fitting in a manner distinct from Dropout, allowing it to be combined with Dropout to further enhance model performance and reduce computational resource usage. Extensive experiments validate that our method generalizes to a variety of datasets and tasks and is compatible with a wide range of deep learning architectures and modules. Code is publicly available at https://github.com/lujiazho/ssProp.
Related papers
- Diffusion-Based Neural Network Weights Generation [80.89706112736353]
D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning.
Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation.
Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
arXiv Detail & Related papers (2024-02-28T08:34:23Z) - Uncovering Energy-Efficient Practices in Deep Learning Training:
Preliminary Steps Towards Green AI [8.025202812165412]
We consider energy consumption as a metric of equal importance to accuracy and to reduce any irrelevant tasks or energy usage.
We examine the training stage of the deep learning pipeline from a sustainability perspective.
We highlight innovative and promising energy-efficient practices for training deep learning models.
arXiv Detail & Related papers (2023-03-24T12:48:21Z) - Energy Efficiency of Training Neural Network Architectures: An Empirical
Study [11.325530936177493]
The evaluation of Deep Learning models has traditionally focused on criteria such as accuracy, F1 score, and related measures.
The computations needed to train such models entail a large carbon footprint.
We study the relations between DL model architectures and their environmental impact in terms of energy consumed and CO$$ emissions produced during training.
arXiv Detail & Related papers (2023-02-02T09:20:54Z) - RLFlow: Optimising Neural Network Subgraph Transformation with World
Models [0.0]
We propose a model-based agent which learns to optimise the architecture of neural networks by performing a sequence of subgraph transformations to reduce model runtime.
We show our approach can match the performance of state of the art on common convolutional networks and outperform those by up to 5% on transformer-style architectures.
arXiv Detail & Related papers (2022-05-03T11:52:54Z) - Benchmarking Resource Usage for Efficient Distributed Deep Learning [10.869092085691687]
We conduct over 3,400 experiments training an array of deep networks representing various domains/tasks.
We fit power law models that describe how training time scales with available compute resources and energy constraints.
arXiv Detail & Related papers (2022-01-28T21:24:15Z) - LCS: Learning Compressible Subspaces for Adaptive Network Compression at
Inference Time [57.52251547365967]
We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models.
We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity.
Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
arXiv Detail & Related papers (2021-10-08T17:03:34Z) - Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models.
Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely.
Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
arXiv Detail & Related papers (2021-10-01T10:03:57Z) - FG-Net: Fast Large-Scale LiDAR Point CloudsUnderstanding Network
Leveraging CorrelatedFeature Mining and Geometric-Aware Modelling [15.059508985699575]
FG-Net is a general deep learning framework for large-scale point clouds understanding without voxelizations.
We propose a deep convolutional neural network leveraging correlated feature mining and deformable convolution based geometric-aware modelling.
Our approaches outperform state-of-the-art approaches in terms of accuracy and efficiency.
arXiv Detail & Related papers (2020-12-17T08:20:09Z) - Learning Discrete Energy-based Models via Auxiliary-variable Local
Exploration [130.89746032163106]
We propose ALOE, a new algorithm for learning conditional and unconditional EBMs for discrete structured data.
We show that the energy function and sampler can be trained efficiently via a new variational form of power iteration.
We present an energy model guided fuzzer for software testing that achieves comparable performance to well engineered fuzzing engines like libfuzzer.
arXiv Detail & Related papers (2020-11-10T19:31:29Z) - Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model.
This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs)
The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
arXiv Detail & Related papers (2020-03-13T13:11:35Z) - Large-Scale Gradient-Free Deep Learning with Recursive Local
Representation Alignment [84.57874289554839]
Training deep neural networks on large-scale datasets requires significant hardware resources.
Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize.
We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
arXiv Detail & Related papers (2020-02-10T16:20:02Z)
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.