SAMN: A Sample Attention Memory Network Combining SVM and NN in One Architecture

TL;DR

SAMN is a novel neural network architecture that effectively integrates SVM and NN components through a sample attention mechanism, class prototypes, and memory, leading to improved classification performance.

Contribution

This paper introduces SAMN, a new architecture that truly combines SVM and NN by incorporating sample attention, class prototypes, and memory, enhancing multi-class classification.

Findings

SAMN outperforms single SVM and NN models with similar parameters.

SAMN achieves state-of-the-art results among combined SVM-NN models.

The sample attention module is flexible and easily integrable into neural networks.

Abstract

Support vector machine (SVM) and neural networks (NN) have strong complementarity. SVM focuses on the inner operation among samples while NN focuses on the operation among the features within samples. Thus, it is promising and attractive to combine SVM and NN, as it may provide a more powerful function than SVM or NN alone. However, current work on combining them lacks true integration. To address this, we propose a sample attention memory network (SAMN) that effectively combines SVM and NN by incorporating sample attention module, class prototypes, and memory block to NN. SVM can be viewed as a sample attention machine. It allows us to add a sample attention module to NN to implement the main function of SVM. Class prototypes are representatives of all classes, which can be viewed as alternatives to support vectors. The memory block is used for the storage and update of class prototypes. Class prototypes and memory block effectively reduce the computational cost of sample attention and make SAMN suitable for multi-classification tasks. Extensive experiments show that SAMN achieves better classification performance than single SVM or single NN with similar parameter sizes, as well as the previous best model for combining SVM and NN. The sample attention mechanism is a flexible module that can be easily deepened and incorporated into neural networks that require it.