Momentum Auxiliary Network for Supervised Local Learning

• URL: http://arxiv.org/abs/2407.05623v4
• Date: Mon, 12 Aug 2024 12:47:11 GMT
• Title: Momentum Auxiliary Network for Supervised Local Learning
• Authors: Junhao Su, Changpeng Cai, Feiyu Zhu, Chenghao He, Xiaojie Xu, Dongzhi Guan, Chenyang Si,
• Abstract summary: Supervised local learning segments the network into multiple local blocks updated by independent auxiliary networks. We propose a Momentum Auxiliary Network (MAN) that establishes a dynamic interaction mechanism. Our method can reduce GPU memory usage by more than 45% on the ImageNet dataset compared to end-to-end training.
• Score: 7.5717621206854275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network parameter updates, leading to significant GPU memory use. Supervised local learning, which segments the network into multiple local blocks updated by independent auxiliary networks. However, these methods cannot replace end-to-end training due to lower accuracy, as gradients only propagate within their local block, creating a lack of information exchange between blocks. To address this issue and establish information transfer across blocks, we propose a Momentum Auxiliary Network (MAN) that establishes a dynamic interaction mechanism. The MAN leverages an exponential moving average (EMA) of the parameters from adjacent local blocks to enhance information flow. This auxiliary network, updated through EMA, helps bridge the informational gap between blocks. Nevertheless, we observe that directly applying EMA parameters has certain limitations due to feature discrepancies among local blocks. To overcome this, we introduce learnable biases, further boosting performance. We have validated our method on four image classification datasets (CIFAR-10, STL-10, SVHN, ImageNet), attaining superior performance and substantial memory savings. Notably, our method can reduce GPU memory usage by more than 45\% on the ImageNet dataset compared to end-to-end training, while achieving higher performance. The Momentum Auxiliary Network thus offers a new perspective for supervised local learning. Our code is available at: https://github.com/JunhaoSu0/MAN.

Related papers

• Distributed Convolutional Neural Network Training on Mobile and Edge Clusters [0.9421843976231371]
  Recent efforts have emerged to localize machine learning tasks fully on the edge. This brings advantages in reduced latency and increased privacy, but necessitates working with resource-constrained devices. We describe an approach for distributed CNN training exclusively on mobile and edge devices.
  arXiv  Detail & Related papers  (2024-09-11T02:44:28Z)
• HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion [7.9514535887836795]
  We propose a novel model that performs hierarchical locally supervised learning and patch-level feature on auxiliary networks. We conduct experiments on CIFAR-10, STL-10, SVHN, and ImageNet datasets, and the results demonstrate that our proposed HPFF significantly outperforms previous approaches.
  arXiv  Detail & Related papers  (2024-07-08T06:05:19Z)
• Scaling Supervised Local Learning with Augmented Auxiliary Networks [29.79621064772869]
  We present an augmented local learning method dubbed AugLocal for deep neural networks. We show that AugLocal can effectively scale up to tens of local layers with a comparable accuracy to BP-trained networks. The proposed AugLocal method opens up a myriad of opportunities for training high-performance deep neural networks on resource-constrained platforms.
  arXiv  Detail & Related papers  (2024-02-27T08:50:45Z)
• Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks [9.718519843862937]
  We introduce a block-wise BP-free (BWBPF) neural network that leverages local error signals to optimize sub-neural networks separately. Our experimental results consistently show that this approach can identify transferable decoupled architectures for VGG and ResNet variations.
  arXiv  Detail & Related papers  (2023-12-20T08:02:33Z)
• CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning [52.72888626663642]
  Copy-move forgery detection aims at detecting duplicated regions in a suspected forged image. Deep learning based copy-move forgery detection methods are in the ascendant. We propose a Transformer-style copy-move forgery network named as CMFDFormer. We also provide a novel PCSD continual learning framework to help CMFDFormer handle new tasks.
  arXiv  Detail & Related papers  (2023-11-22T09:27:46Z)
• Block-local learning with probabilistic latent representations [2.839567756494814]
  Locking and weight transport are problems because they prevent efficient parallelization and horizontal scaling of the training process. We propose a new method to address both these problems and scale up the training of large models. We present results on a variety of tasks and architectures, demonstrating state-of-the-art performance using block-local learning.
  arXiv  Detail & Related papers  (2023-05-24T10:11:30Z)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Knowledge Distillation By Sparse Representation Matching [107.87219371697063]
  We propose Sparse Representation Matching (SRM) to transfer intermediate knowledge from one Convolutional Network (CNN) to another by utilizing sparse representation. We formulate as a neural processing block, which can be efficiently optimized using gradient descent and integrated into any CNN in a plug-and-play manner. Our experiments demonstrate that is robust to architectural differences between the teacher and student networks, and outperforms other KD techniques across several datasets.
  arXiv  Detail & Related papers  (2021-03-31T11:47:47Z)
• LoCo: Local Contrastive Representation Learning [93.98029899866866]
  We show that by overlapping local blocks stacking on top of each other, we effectively increase the decoder depth and allow upper blocks to implicitly send feedbacks to lower blocks. This simple design closes the performance gap between local learning and end-to-end contrastive learning algorithms for the first time.
  arXiv  Detail & Related papers  (2020-08-04T05:41:29Z)
• Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning [73.82875010696849]
  Machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models. This paper focuses on the novel joint design of parameter (computation load) allocation and bandwidth allocation.
  arXiv  Detail & Related papers  (2020-03-10T05:52:15Z)
• Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition [75.4027660840568]
  This paper explores how to enhance the local and global dense feature flow by exploiting hierarchical features fully from all the convolution layers. Technically, we propose an efficient and effective CNN framework, i.e., Fast Dense Residual Network (FDRN) for text recognition.
  arXiv  Detail & Related papers  (2020-01-23T06:55:08Z)

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.