LaCoOT: Layer Collapse through Optimal Transport

• URL: http://arxiv.org/abs/2406.08933v3
• Date: Tue, 15 Jul 2025 08:40:26 GMT
• Title: LaCoOT: Layer Collapse through Optimal Transport
• Authors: Victor Quétu, Zhu Liao, Nour Hezbri, Fabio Pizzati, Enzo Tartaglione,
• Abstract summary: We present an optimal transport-based method to reduce the depth of over-parametrized deep neural networks.<n>We show that our method achieves better performance/depth trade-off compared to existing techniques.
• Score: 9.715121047425262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although deep neural networks are well-known for their outstanding performance in tackling complex tasks, their hunger for computational resources remains a significant hurdle, posing energy-consumption issues and restricting their deployment on resource-constrained devices, preventing their widespread adoption. In this paper, we present an optimal transport-based method to reduce the depth of over-parametrized deep neural networks, alleviating their computational burden. More specifically, we propose a new regularization strategy based on the Max-Sliced Wasserstein distance to minimize the distance between the intermediate feature distributions in the neural network. We show that minimizing this distance enables the complete removal of intermediate layers in the network, achieving better performance/depth trade-off compared to existing techniques. We assess the effectiveness of our method on traditional image classification setups and extend it to generative image models. Our code is available at https://github.com/VGCQ/LaCoOT.

Related papers

• Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers [5.008189006630566]
  We introduce a method called textbfTill the textbfLayers textbfCollapse (TLC), which compresses deep neural networks through the lenses of batch normalization layers.<n>We validate our method on popular models such as Swin-T, MobileNet-V2, and RoBERTa, across both image classification and natural language processing (NLP) tasks.
  arXiv  Detail & Related papers  (2024-12-19T17:26:07Z)
• Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning [69.00997996453842]
  We propose a deep Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for virtual network embedding. We show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue.
  arXiv  Detail & Related papers  (2024-06-25T07:42:30Z)
• DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach [49.56404236394601]
  We formulate the problem of joint DNN partitioning, task offloading, and resource allocation in Vehicular Edge Computing. Our objective is to minimize the DNN-based task completion time while guaranteeing the system stability over time. We propose a Multi-Agent Diffusion-based Deep Reinforcement Learning (MAD2RL) algorithm, incorporating the innovative use of diffusion models.
  arXiv  Detail & Related papers  (2024-06-11T06:31:03Z)
• The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth [5.869633234882029]
  We propose an efficiency strategy that leverages prior knowledge transferred by large models. Simple but effective, we propose a method relying on an Entropy-bASed Importance mEtRic (EASIER) to reduce the depth of over-parametrized deep neural networks.
  arXiv  Detail & Related papers  (2024-04-27T08:28:25Z)
• NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer [5.373015313199385]
  We propose an eNtropy-basEd Pruning as a nEural Network depTH's rEducer to alleviate deep neural networks' computational burden. We validate our approach on popular architectures such as MobileNet and Swin-T.
  arXiv  Detail & Related papers  (2024-04-24T09:12:04Z)
• Towards Meta-Pruning via Optimal Transport [64.6060250923073]
  This paper introduces a novel approach named Intra-Fusion, challenging the prevailing pruning paradigm. We leverage the concepts of model fusion and Optimal Transport to arrive at a more effective sparse model representation. We benchmark our results for various networks on commonly used datasets such as CIFAR-10, CIFAR-100, and ImageNet.
  arXiv  Detail & Related papers  (2024-02-12T17:50:56Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Universal Neural Optimal Transport [0.0]
  UNOT (Universal Neural Optimal Transport) is a novel framework capable of accurately predicting (entropic) OT distances and plans. We show that our network not only accurately predicts optimal transport distances and plans across a wide range of datasets, but also captures the geometry of the Wasserstein space correctly.
  arXiv  Detail & Related papers  (2022-11-30T21:56:09Z)
• RDRN: Recursively Defined Residual Network for Image Super-Resolution [58.64907136562178]
  Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution. We propose a novel network architecture which utilizes attention blocks efficiently.
  arXiv  Detail & Related papers  (2022-11-17T11:06:29Z)
• Image Superresolution using Scale-Recurrent Dense Network [30.75380029218373]
  Recent advances in the design of convolutional neural network (CNN) have yielded significant improvements in the performance of image super-resolution (SR) We propose a scale recurrent SR architecture built upon units containing series of dense connections within a residual block (Residual Dense Blocks (RDBs)) Our scale recurrent design delivers competitive performance for higher scale factors while being parametrically more efficient as compared to current state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-28T09:18:43Z)
• DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction [0.0]
  A receptive field (ERF) and a higher resolution of spatial features within a network are essential for providing higher-resolution dense estimates. We present a systemic approach to design network architectures that can provide a larger receptive field while maintaining a higher spatial feature resolution.
  arXiv  Detail & Related papers  (2021-07-09T23:15:34Z)
• Layer Folding: Neural Network Depth Reduction using Activation Linearization [0.0]
  Modern devices exhibit a high level of parallelism, but real-time latency is still highly dependent on networks' depth. We propose a method that learns whether non-linear activations can be removed, allowing to fold consecutive linear layers into one. We apply our method to networks pre-trained on CIFAR-10 and CIFAR-100 and find that they can all be transformed into shallower forms that share a similar depth.
  arXiv  Detail & Related papers  (2021-06-17T08:22:46Z)
• DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting [70.62923754433461]
  Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non- optimization problem. We propose a novel method that can directly solve a convex relaxation of the problem to high accuracy, by splitting it into smaller subproblems that often have analytical solutions.
  arXiv  Detail & Related papers  (2021-06-16T20:43:49Z)
• Weight Pruning via Adaptive Sparsity Loss [31.978830843036658]
  Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks. We propose a robust learning framework that efficiently prunes network parameters during training with minimal computational overhead.
  arXiv  Detail & Related papers  (2020-06-04T10:55:16Z)
• Compact Neural Representation Using Attentive Network Pruning [1.0152838128195465]
  We describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers. Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation.
  arXiv  Detail & Related papers  (2020-05-10T03:20:01Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)
• 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.