DeInfoReg: A Decoupled Learning Framework for Better Training Throughput

• URL: http://arxiv.org/abs/2506.18193v2
• Date: Tue, 15 Jul 2025 14:29:38 GMT
• Title: DeInfoReg: A Decoupled Learning Framework for Better Training Throughput
• Authors: Zih-Hao Huang, You-Teng Lin, Hung-Hsuan Chen,
• Abstract summary: This paper introduces Decoupled Supervised Learning with Information Regularization (DeInfoReg)<n>It transforms a long gradient flow into multiple shorter ones, thereby mitigating the vanishing gradient problem.<n>We compare our proposed method with standard backpropagation and other gradient flow decomposition techniques.
• Score: 1.8434042562191815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces Decoupled Supervised Learning with Information Regularization (DeInfoReg), a novel approach that transforms a long gradient flow into multiple shorter ones, thereby mitigating the vanishing gradient problem. Integrating a pipeline strategy, DeInfoReg enables model parallelization across multiple GPUs, significantly improving training throughput. We compare our proposed method with standard backpropagation and other gradient flow decomposition techniques. Extensive experiments on diverse tasks and datasets demonstrate that DeInfoReg achieves superior performance and better noise resistance than traditional BP models and efficiently utilizes parallel computing resources. The code for reproducibility is available at: https://github.com/ianzih/Decoupled-Supervised-Learning-for-Information-Regularization/.

Related papers

• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Multiscale Stochastic Gradient Descent: Efficiently Training Convolutional Neural Networks [6.805997961535213]
  Multiscale Gradient Descent (Multiscale-SGD) is a novel optimization approach that exploits coarse-to-fine training strategies to estimate the gradient at a fraction of the cost.<n>We introduce a new class of learnable, scale-independent Mesh-Free Convolutions (MFCs) that ensure consistent gradient behavior across resolutions.<n>Our results establish a new paradigm for the efficient training of deep networks, enabling practical scalability in high-resolution and multiscale learning tasks.
  arXiv  Detail & Related papers  (2025-01-22T09:13:47Z)
• Linearly Convergent Mixup Learning [0.0]
  We present two novel algorithms that extend to a broader range of binary classification models.<n>Unlike gradient-based approaches, our algorithms do not require hyper parameters like learning rates, simplifying their implementation and optimization.<n>Our algorithms achieve faster convergence to the optimal solution compared to descent gradient approaches, and that mixup data augmentation consistently improves the predictive performance across various loss functions.
  arXiv  Detail & Related papers  (2025-01-14T02:33:40Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• DTL: Disentangled Transfer Learning for Visual Recognition [21.549234013998255]
  We introduce Disentangled Transfer Learning (DTL), which disentangles the trainable parameters from the backbone using a lightweight Compact Side Network (CSN) The proposed method not only reduces a large amount of GPU memory usage and trainable parameters, but also outperforms existing PETL methods by a significant margin in accuracy.
  arXiv  Detail & Related papers  (2023-12-13T02:51:26Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging [104.41634756395545]
  Federated learning (FL) is an emerging learning paradigm to tackle massively distributed data. We propose textbfFedDA, a novel framework for local adaptive gradient methods. We show that textbfFedDA-MVR is the first adaptive FL algorithm that achieves this rate.
  arXiv  Detail & Related papers  (2023-02-13T05:10:30Z)
• GuideBP: Guiding Backpropagation Through Weaker Pathways of Parallel Logits [6.764324841419295]
  The proposed approach guides the gradients of backpropagation along weakest concept representations. A weakness scores defines the class specific performance of individual pathways which is then used to create a logit. The proposed approach has been shown to perform better than traditional column merging techniques.
  arXiv  Detail & Related papers  (2021-04-23T14:14:00Z)
• Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization [16.02377434191239]
  We propose an accumulated decoupled learning (ADL) which incorporates the gradient accumulation technique to mitigate the stale gradient effect. We prove that the proposed method can converge to critical points, i.e., the gradients converge to 0, in spite of its asynchronous nature. The ADL is shown to outperform several state-of-the-arts in the classification tasks, and is the fastest among the compared methods.
  arXiv  Detail & Related papers  (2020-12-03T11:52:55Z)
• DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion Framework [29.58965424136611]
  This work proposes an unsupervised fusion framework based on deep convolutional transform learning. We apply the proposed technique, named DeConFuse, on the problem of stock forecasting and trading.
  arXiv  Detail & Related papers  (2020-11-09T11:04:09Z)
• Scaling Distributed Deep Learning Workloads beyond the Memory Capacity with KARMA [58.040931661693925]
  We propose a strategy that combines redundant recomputing and out-of-core methods. We achieve an average of 1.52x speedup in six different models over the state-of-the-art out-of-core methods. Our data parallel out-of-core solution can outperform complex hybrid model parallelism in training large models, e.g. Megatron-LM and Turning-NLG.
  arXiv  Detail & Related papers  (2020-08-26T07:24:34Z)
• Dynamic Scale Training for Object Detection [111.33112051962514]
  We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Experimental results demonstrate the efficacy of our proposed DST towards scale variation handling. It does not introduce inference overhead and could serve as a free lunch for general detection configurations.
  arXiv  Detail & Related papers  (2020-04-26T16:48:17Z)

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.