Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf Node

• URL: http://arxiv.org/abs/2405.16836v1
• Date: Mon, 27 May 2024 05:06:24 GMT
• Title: Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf Node
• Authors: Andreas Charalampopoulos, Nikolas Chatzis, Foivos Ntoulas-Panagiotopoulos, Charilaos Papaioannou, Alexandros Potamianos,
• Abstract summary: Fast feedforward networks (FFFs) exploit the observation that different regions of the input space activate distinct subsets of neurons in wide networks. We propose the incorporation of load balancing and Master Leaf techniques into the FFF architecture to improve performance and simplify the training process.
• Score: 49.08777822540483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fast feedforward networks (FFFs) are a class of neural networks that exploit the observation that different regions of the input space activate distinct subsets of neurons in wide networks. FFFs partition the input space into separate sections using a differentiable binary tree of neurons and during inference descend the binary tree in order to improve computational efficiency. Inspired by Mixture of Experts (MoE) research, we propose the incorporation of load balancing and Master Leaf techniques into the FFF architecture to improve performance and simplify the training process. We reproduce experiments found in literature and present results on FFF models enhanced using these techniques. The proposed architecture and training recipe achieves up to 16.3% and 3% absolute classification accuracy increase in training and test accuracy, respectively, compared to the original FFF architecture. Additionally, we observe a smaller variance in the results compared to those reported in prior research. These findings demonstrate the potential of integrating MoE-inspired techniques into FFFs for developing more accurate and efficient models.

Related papers

• LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation [64.34935748707673]
  Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. We propose a novel method of Learning Resampling (termed LeRF) which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption. LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the shapes of these resampling functions with a neural network.
  arXiv  Detail & Related papers  (2024-07-13T16:09:45Z)
• Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion [11.689517005768046]
  Out-of-distribution samples may exhibit shifts in local or global features compared to the training distribution. We propose a novel framework, Multitesting-based Layer-wise Out-of-Distribution (OOD) Detection. Our scheme effectively enhances the performance of out-of-distribution detection when compared to baseline methods.
  arXiv  Detail & Related papers  (2024-03-16T04:35:04Z)
• Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm [5.1246638322893245]
  Forward-Forward (FF) algorithm has been proposed to alleviate the issues of backpropagation (BP) commonly used to train deep neural networks. We take the main ideas of FF and improve them by leveraging channel-wise competitive learning in the context of convolutional neural networks for image classification tasks. Our method outperforms recent FF-based models on image classification tasks, achieving testing errors of 0.58%, 7.69%, 21.89%, and 48.77% on MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 respectively.
  arXiv  Detail & Related papers  (2023-12-19T23:48:43Z)
• FaFCNN: A General Disease Classification Framework Based on Feature Fusion Neural Networks [4.097623533226476]
  We propose the Feature-aware Fusion Correlation Neural Network (FaFCNN), which introduces a feature-aware interaction module and a feature alignment module based on domain adversarial learning. The experimental results show that training using augmented features obtained by pre-training gradient boosting decision tree yields more performance gains than random-forest based methods.
  arXiv  Detail & Related papers  (2023-07-24T04:23:08Z)
• Kernel function impact on convolutional neural networks [10.98068123467568]
  We study the usage of kernel functions at the different layers in a convolutional neural network. We show how one can effectively leverage kernel functions, by introducing a more distortion aware pooling layers. We propose Kernelized Dense Layers (KDL), which replace fully-connected layers.
  arXiv  Detail & Related papers  (2023-02-20T19:57:01Z)
• Deep Frequency Filtering for Domain Generalization [55.66498461438285]
  Deep Neural Networks (DNNs) have preferences for some frequency components in the learning process. We propose Deep Frequency Filtering (DFF) for learning domain-generalizable features. We show that applying our proposed DFF on a plain baseline outperforms the state-of-the-art methods on different domain generalization tasks.
  arXiv  Detail & Related papers  (2022-03-23T05:19:06Z)
• Optimization-Based Separations for Neural Networks [57.875347246373956]
  We show that gradient descent can efficiently learn ball indicator functions using a depth 2 neural network with two layers of sigmoidal activations. This is the first optimization-based separation result where the approximation benefits of the stronger architecture provably manifest in practice.
  arXiv  Detail & Related papers  (2021-12-04T18:07:47Z)
• Improving Sample Efficiency with Normalized RBF Kernels [0.0]
  This paper explores how neural networks with normalized Radial Basis Function (RBF) kernels can be trained to achieve better sample efficiency. We show how this kind of output layer can find embedding spaces where the classes are compact and well-separated. Experiments on CIFAR-10 and CIFAR-100 show that networks with normalized kernels as output layer can achieve higher sample efficiency, high compactness and well-separability.
  arXiv  Detail & Related papers  (2020-07-30T11:40:29Z)
• DrNAS: Dirichlet Neural Architecture Search [88.56953713817545]
  We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet distribution. With recently developed pathwise derivatives, the Dirichlet parameters can be easily optimized with gradient-based generalization. To alleviate the large memory consumption of differentiable NAS, we propose a simple yet effective progressive learning scheme.
  arXiv  Detail & Related papers  (2020-06-18T08:23:02Z)
• FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining [65.39532971991778]
  We present an accuracy predictor that scores architecture and training recipes jointly, guiding both sample selection and ranking. We run fast evolutionary searches in just CPU minutes to generate architecture-recipe pairs for a variety of resource constraints. FBNetV3 makes up a family of state-of-the-art compact neural networks that outperform both automatically and manually-designed competitors.
  arXiv  Detail & Related papers  (2020-06-03T05:20:21Z)

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.