Reducing ReLU Count for Privacy-Preserving CNN Speedup

• URL: http://arxiv.org/abs/2101.11835v1
• Date: Thu, 28 Jan 2021 06:49:31 GMT
• Title: Reducing ReLU Count for Privacy-Preserving CNN Speedup
• Authors: Inbar Helbitz, Shai Avidan
• Abstract summary: Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. CNNs typically consist of two types of operations: a convolutional or linear layer, followed by a non-linear function such as ReLU. Recent research suggests that ReLU is responsible for most of the communication bandwidth. We propose to share ReLU operations. Specifically, the ReLU decision of one activation can be used by others, and we explore different ways to determine the ReLU for such a group of activations.
• Score: 25.86435513157795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Networks (CNN). CNNs typically consist of two types of operations: a convolutional or linear layer, followed by a non-linear function such as ReLU. Each of these types can be implemented efficiently using a different cryptographic tool. But these tools require different representations and switching between them is time-consuming and expensive. Recent research suggests that ReLU is responsible for most of the communication bandwidth. ReLU is usually applied at each pixel (or activation) location, which is quite expensive. We propose to share ReLU operations. Specifically, the ReLU decision of one activation can be used by others, and we explore different ways to group activations and different ways to determine the ReLU for such a group of activations. Experiments on several datasets reveal that we can cut the number of ReLU operations by up to three orders of magnitude and, as a result, cut the communication bandwidth by more than 50%.

Related papers

• SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performance [1.2724528787590168]
  ReLU, a commonly used activation function in deep neural networks, is prone to the issue of "Dying ReLU" Several enhanced versions, such as ELU, SeLU, and Swish, have been introduced and are considered to be less commonly utilized. This paper proposes SwishReLU, a novel activation function combining elements of ReLU and Swish.
  arXiv  Detail & Related papers  (2024-07-11T07:14:34Z)
• ReLUs Are Sufficient for Learning Implicit Neural Representations [17.786058035763254]
  We revisit the use of ReLU activation functions for learning implicit neural representations. Inspired by second order B-spline wavelets, we incorporate a set of simple constraints to the ReLU neurons in each layer of a deep neural network (DNN) We demonstrate that, contrary to popular belief, one can learn state-of-the-art INRs based on a DNN composed of only ReLU neurons.
  arXiv  Detail & Related papers  (2024-06-04T17:51:08Z)
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks [64.92221119723048]
  Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. We propose Graph-adaptive Rectified Linear Unit (GReLU) which is a new parametric activation function incorporating the neighborhood information in a novel and efficient way. We conduct comprehensive experiments to show that our plug-and-play GReLU method is efficient and effective given different GNN backbones and various downstream tasks.
  arXiv  Detail & Related papers  (2022-02-13T10:54:59Z)
• Deep ensembles in bioimage segmentation [74.01883650587321]
  In this work, we propose an ensemble of convolutional neural networks (CNNs) In ensemble methods, many different models are trained and then used for classification, the ensemble aggregates the outputs of the single classifiers. The proposed ensemble is implemented by combining different backbone networks using the DeepLabV3+ and HarDNet environment.
  arXiv  Detail & Related papers  (2021-12-24T05:54:21Z)
• An Exact Poly-Time Membership-Queries Algorithm for Extraction a three-Layer ReLU Network [38.91075212630913]
  As machine learning increasingly becomes more prevalent in our everyday life, many organizations offer neural-networks based services as a black-box. The reasons for hiding a learning model may vary: e.g., preventing copying of its behavior or keeping back an adversarial from reverse-engineering its mechanism. In this work, we show a neural-network algorithm that uses a number of queries to mimic precisely the behavior of a three-layer network that uses ReLU activation.
  arXiv  Detail & Related papers  (2021-05-20T11:24:08Z)
• Solving Mixed Integer Programs Using Neural Networks [57.683491412480635]
  This paper applies learning to the two key sub-tasks of a MIP solver, generating a high-quality joint variable assignment, and bounding the gap in objective value between that assignment and an optimal one. Our approach constructs two corresponding neural network-based components, Neural Diving and Neural Branching, to use in a base MIP solver such as SCIP. We evaluate our approach on six diverse real-world datasets, including two Google production datasets and MIPLIB, by training separate neural networks on each.
  arXiv  Detail & Related papers  (2020-12-23T09:33:11Z)
• Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare [77.99636165307996]
  We classify biomedical images using ensembles of neural networks. We select our activations among the following ones: ReLU, leaky ReLU, Parametric ReLU, ELU, Adaptive Piecewice Linear Unit, S-Shaped ReLU, Swish, Mish, Mexican Linear Unit, Parametric Deformable Linear Unit, Soft Root Sign.
  arXiv  Detail & Related papers  (2020-11-24T01:53:39Z)
• Efficient Integer-Arithmetic-Only Convolutional Neural Networks [87.01739569518513]
  We replace conventional ReLU with Bounded ReLU and find that the decline is due to activation quantization. Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPU.
  arXiv  Detail & Related papers  (2020-06-21T08:23:03Z)
• Self-Organized Operational Neural Networks with Generative Neurons [87.32169414230822]
  ONNs are heterogenous networks with a generalized neuron model that can encapsulate any set of non-linear operators. We propose Self-organized ONNs (Self-ONNs) with generative neurons that have the ability to adapt (optimize) the nodal operator of each connection.
  arXiv  Detail & Related papers  (2020-04-24T14:37:56Z)

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.