Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks

• URL: http://arxiv.org/abs/2412.00884v1
• Date: Sun, 01 Dec 2024 16:44:55 GMT
• Title: Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks
• Authors: Emily Liu,
• Abstract summary: We show that constraining the final layer of a neural network to a simplex ETF can reduce the number of trainable parameters without sacrificing model accuracy. We propose two novel training approaches: Adaptive-ETF, a generalized framework that enforces simplex ETF constraints on all layers beyond the effective depth, and ETF-Transformer, which applies simplex ETF constraints to the feedforward layers within transformer blocks.
• Score: 0.0
• License:
• Abstract: Neural collapse is a phenomenon observed during the terminal phase of neural network training, characterized by the convergence of network activations, class means, and linear classifier weights to a simplex equiangular tight frame (ETF), a configuration of vectors that maximizes mutual distance within a subspace. This phenomenon has been linked to improved interpretability, robustness, and generalization in neural networks. However, its potential to guide neural network training and regularization remains underexplored. Previous research has demonstrated that constraining the final layer of a neural network to a simplex ETF can reduce the number of trainable parameters without sacrificing model accuracy. Furthermore, deep fully connected networks exhibit neural collapse not only in the final layer but across all layers beyond a specific effective depth. Using these insights, we propose two novel training approaches: Adaptive-ETF, a generalized framework that enforces simplex ETF constraints on all layers beyond the effective depth, and ETF-Transformer, which applies simplex ETF constraints to the feedforward layers within transformer blocks. We show that these approaches achieve training and testing performance comparable to those of their baseline counterparts while significantly reducing the number of learnable parameters.

Related papers

• Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
  We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
  arXiv  Detail & Related papers  (2023-07-20T13:34:11Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization [1.3999481573773072]
  We introduce and evaluate the batch-entropy which quantifies the flow of information through each layer of a neural network. We show that we can train a "vanilla" fully connected network and convolutional neural network with 500 layers by simply adding the batch-entropy regularization term to the loss function.
  arXiv  Detail & Related papers  (2022-08-01T20:31:58Z)
• Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network [32.575847142016585]
  Top-Down Credit Assignment Network (TDCA-network) is designed to train a bottom-up network using a Top-Down Credit Assignment Network (TDCA-network) TDCA-network serves as a substitute for the conventional loss function and the back-propagation algorithm, widely used in neural network training. The results indicate TDCA-network holds promising potential to train neural networks across diverse datasets.
  arXiv  Detail & Related papers  (2022-08-01T07:14:37Z)
• On Feature Learning in Neural Networks with Global Convergence Guarantees [49.870593940818715]
  We study the optimization of wide neural networks (NNs) via gradient flow (GF) We show that when the input dimension is no less than the size of the training set, the training loss converges to zero at a linear rate under GF. We also show empirically that, unlike in the Neural Tangent Kernel (NTK) regime, our multi-layer model exhibits feature learning and can achieve better generalization performance than its NTK counterpart.
  arXiv  Detail & Related papers  (2022-04-22T15:56:43Z)
• LocalDrop: A Hybrid Regularization for Deep Neural Networks [98.30782118441158]
  We propose a new approach for the regularization of neural networks by the local Rademacher complexity called LocalDrop. A new regularization function for both fully-connected networks (FCNs) and convolutional neural networks (CNNs) has been developed based on the proposed upper bound of the local Rademacher complexity.
  arXiv  Detail & Related papers  (2021-03-01T03:10:11Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth [19.866928507243617]
  Training deep neural networks with gradient descent (SGD) can often achieve zero training loss on real-world landscapes. We propose a new limit of infinity deep residual networks, which enjoys a good training in the sense that everyr is global.
  arXiv  Detail & Related papers  (2020-03-11T20:14:47Z)

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.