Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks

• URL: http://arxiv.org/abs/2604.24313v1
• Date: Mon, 27 Apr 2026 11:04:18 GMT
• Title: Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
• Abstract summary: Training large-scale deep neural networks effectively and stably is essential for applying deep learning across various fields.<n>To overcome these limitations, we introduce Self-Abstraction Learning (SAL), a hierarchical framework.<n>In SAL, networks are arranged by structural complexity, where the simplest topmost network is trained first and its hidden and output layers serve as guidance for the successively more complex networks below.
• Score: 1.787702109751332
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training large-scale deep neural networks effectively and stably is essential for applying deep learning across various fields. However, conventional methods, which rely on training a single large network, often encounter challenges such as gradient vanishing, overfitting and unstable learning. To overcome these limitations, we introduce Self-Abstraction Learning (SAL), a hierarchical framework. In SAL, networks are arranged by structural complexity, where the simplest topmost network is trained first and its hidden and output layers serve as guidance for the successively more complex networks below. This top-down sequential guidance effectively mitigates optimization issues, enabling stable training of deep architectures. Various experiments across MLP, CNN, and RNN architectures demonstrate that SAL consistently outperforms conventional methods, ensuring robust generalization even in data-scarce and complex network regimes.

Related papers

• Efficient and provably convergent end-to-end training of deep neural networks with linear constraints [12.559930224041544]
  We introduce an efficiently computable HS-Jacobian to the projection layer.<n>We prove that the HS-Jacobian is a conservative mapping for the projection operator onto the polyhedral set.<n>We establish convergence guarantees of the HS-Jacobian based Adam algorithm for training linearly constrained deep neural networks.
  arXiv  Detail & Related papers  (2026-05-12T04:51:55Z)
• Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining [58.69016084278948]
  We consider a hierarchical context-free grammar introduced by arXiv:2307.02129 and conjectured to separate deep and shallow networks.<n>We prove that, under mild conditions, a deep convolutional network can be efficiently trained to learn this function class.
  arXiv  Detail & Related papers  (2026-01-27T16:19:54Z)
• Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition [0.5024983453990065]
  layer-wise training eliminates the need for cross-entropy loss and backpropagation.<n>Most existing layer-wise training approaches have been evaluated only on relatively small datasets.<n>We propose a novel layer-wise training approach based on the recently developed deterministic information bottleneck (DIB) and the matrix-based R'enyi's $alpha$-order entropy functional.
  arXiv  Detail & Related papers  (2025-10-31T17:24:58Z)
• Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning [57.3885832382455]
  We show that introducing static network sparsity alone can unlock further scaling potential beyond dense counterparts with state-of-the-art architectures.<n>Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity.
  arXiv  Detail & Related papers  (2025-06-20T17:54:24Z)
• Lattice-Based Pruning in Recurrent Neural Networks via Poset Modeling [0.0]
  Recurrent neural networks (RNNs) are central to sequence modeling tasks, yet their high computational complexity poses challenges for scalability and real-time deployment.<n>We introduce a novel framework that models RNNs as partially ordered sets (posets) and constructs corresponding dependency lattices.<n>By identifying meet irreducible neurons, our lattice-based pruning algorithm selectively retains critical connections while eliminating redundant ones.
  arXiv  Detail & Related papers  (2025-02-23T10:11:38Z)
• Residual Kolmogorov-Arnold Network for Enhanced Deep Learning [0.9399249626168465]
  Deep convolutional neural networks (CNNs) can be difficult to optimize and costly to train due to hundreds of layers within the network depth.<n>We introduce a "plug-in" module, called Residual Kolmogorov-Arnold Network (RKAN)<n>RKAN offers consistent improvements over baseline models in different vision tasks.
  arXiv  Detail & Related papers  (2024-10-07T21:12:32Z)
• Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks [44.31729147722701]
  We show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks.<n>This work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.
  arXiv  Detail & Related papers  (2023-05-11T17:19:30Z)
• 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)
• SIRe-Networks: Skip Connections over Interlaced Multi-Task Learning and Residual Connections for Structure Preserving Object Classification [28.02302915971059]
  In this paper, we introduce an interlaced multi-task learning strategy, defined SIRe, to reduce the vanishing gradient in relation to the object classification task. The presented methodology directly improves a convolutional neural network (CNN) by enforcing the input image structure preservation through auto-encoders. To validate the presented methodology, a simple CNN and various implementations of famous networks are extended via the SIRe strategy and extensively tested on the CIFAR100 dataset.
  arXiv  Detail & Related papers  (2021-10-06T13:54:49Z)
• Learning Structures for Deep Neural Networks [99.8331363309895]
  We propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience. We show that sparse coding can effectively maximize the entropy of the output signals. Our experiments on a public image classification dataset demonstrate that using the structure learned from scratch by our proposed algorithm, one can achieve a classification accuracy comparable to the best expert-designed structure.
  arXiv  Detail & Related papers  (2021-05-27T12:27:24Z)
• Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning [88.17413955380262]
  Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy. We introduce a novel method called Multi-Exit Curriculum Learning that utilizes curriculum learning. Our method consistently improves the accuracy of early exits compared to the standard training approach.
  arXiv  Detail & Related papers  (2021-04-21T11:12:35Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• 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.