Using predefined vector systems to speed up neural network multimillion class classification

• URL: http://arxiv.org/abs/2604.00779v2
• Date: Mon, 06 Apr 2026 06:55:28 GMT
• Title: Using predefined vector systems to speed up neural network multimillion class classification
• Abstract summary: We show that if NN latent space geometry is known and possesses specific properties, label prediction complexity can be significantly reduced.<n>The proposed method only requires finding indexes of several largest and lowest values in the embedding vector.<n>Experiments show that the proposed method allows to achieve up to 11.6 times overall acceleration over conventional methods.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label prediction in neural networks (NNs) has O(n) complexity proportional to the number of classes. This holds true for classification using fully connected layers and cosine similarity with some set of class prototypes. In this paper we show that if NN latent space (LS) geometry is known and possesses specific properties, label prediction complexity can be significantly reduced. This is achieved by associating label prediction with the O(1) complexity closest cluster center search in a vector system used as target for latent space configuration (LSC). The proposed method only requires finding indexes of several largest and lowest values in the embedding vector making it extremely computationally efficient. We show that the proposed method does not change NN training accuracy computational results. We also measure the time required by different computational stages of NN inference and label prediction on multiple datasets. The experiments show that the proposed method allows to achieve up to 11.6 times overall acceleration over conventional methods. Furthermore, the proposed method has unique properties which allow to predict the existence of new classes.

Related papers

• Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes [0.0]
  Supervised learning (SL) methods are indispensable for neural network (NN) training used to perform classification tasks.<n>We propose a methodology that allows one to train the same NN architecture regardless of the number of classes.
  arXiv  Detail & Related papers  (2025-10-05T08:28:37Z)
• Categorical Data Clustering via Value Order Estimated Distance Metric Learning [53.28598689867732]
  This paper introduces a novel order distance metric learning approach to intuitively represent categorical attribute values.<n>A new joint learning paradigm is developed to alternatively perform clustering and order distance metric learning.<n>The proposed method achieves superior clustering accuracy on categorical and mixed datasets.
  arXiv  Detail & Related papers  (2024-11-19T08:23:25Z)
• Factorizers for Distributed Sparse Block Codes [45.29870215671697]
  We propose a fast and highly accurate method for factorizing distributed block codes (SBCs) Our iterative factorizer introduces a threshold-based nonlinear activation, conditional random sampling, and an $ell_infty$-based similarity metric. We demonstrate the feasibility of our method on four deep CNN architectures over CIFAR-100, ImageNet-1K, and RAVEN datasets.
  arXiv  Detail & Related papers  (2023-03-24T12:31:48Z)
• The Cascaded Forward Algorithm for Neural Network Training [61.06444586991505]
  We propose a new learning framework for neural networks, namely Cascaded Forward (CaFo) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, our framework directly outputs label distributions at each cascaded block, which does not require generation of additional negative samples. In our framework each block can be trained independently, so it can be easily deployed into parallel acceleration systems.
  arXiv  Detail & Related papers  (2023-03-17T02:01:11Z)
• Sparse tree-based initialization for neural networks [0.0]
  We show that dedicated neural network (NN) architectures can handle specific data types such as CNN for images or RNN for text. In this work, we propose a new technique for (potentially deep) multilayer perceptrons (MLP) We show that our new initializer operates an implicit regularization during the NN training, and emphasizes that the first layers act as a sparse feature extractor.
  arXiv  Detail & Related papers  (2022-09-30T07:44:03Z)
• Large-Margin Representation Learning for Texture Classification [67.94823375350433]
  This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The experimental results on texture and histopathologic image datasets have shown that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence when compared to equivalent CNNs.
  arXiv  Detail & Related papers  (2022-06-17T04:07:45Z)
• Rethinking Nearest Neighbors for Visual Classification [56.00783095670361]
  k-NN is a lazy learning method that aggregates the distance between the test image and top-k neighbors in a training set. We adopt k-NN with pre-trained visual representations produced by either supervised or self-supervised methods in two steps. Via extensive experiments on a wide range of classification tasks, our study reveals the generality and flexibility of k-NN integration.
  arXiv  Detail & Related papers  (2021-12-15T20:15:01Z)
• Cluster Representatives Selection in Non-Metric Spaces for Nearest Prototype Classification [4.176752121302988]
  In this paper, we present CRS, a novel method for selecting a small yet representative subset of objects as a cluster prototype. Memory and computationally efficient selection of representatives is enabled by leveraging the similarity graph representation of each cluster created by the NN-Descent algorithm. CRS can be used in an arbitrary metric or non-metric space because of the graph-based approach, which requires only a pairwise similarity measure.
  arXiv  Detail & Related papers  (2021-07-03T04:51:07Z)
• Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing [4.4886210896619945]
  We propose a modified RVFL network that avoids computationally expensive matrix operations during training. The proposed approach achieved state-of-the-art accuracy on a collection of datasets from the UCI Machine Learning Repository.
  arXiv  Detail & Related papers  (2021-06-17T21:17:17Z)
• Expectation propagation on the diluted Bayesian classifier [0.0]
  We introduce a statistical mechanics inspired strategy that addresses the problem of sparse feature selection in the context of binary classification. A computational scheme known as expectation propagation (EP) is used to train a continuous-weights perceptron learning a classification rule. EP is a robust and competitive algorithm in terms of variable selection properties, estimation accuracy and computational complexity.
  arXiv  Detail & Related papers  (2020-09-20T23:59:44Z)
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer [77.90012156266324]
  This paper aims to find a subspace of neural networks that can facilitate a large decision margin. We propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain during both the training and test processes. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets.
  arXiv  Detail & Related papers  (2020-04-20T02:41:01Z)
• Learning Class Regularized Features for Action Recognition [68.90994813947405]
  We introduce a novel method named Class Regularization that performs class-based regularization of layer activations. We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1.8%, 1.2% and 1.4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
  arXiv  Detail & Related papers  (2020-02-07T07:27:49Z)

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.