Fast and Scalable Multi-Kernel Encoder Classifier

TL;DR

This paper presents a fast, scalable multi-kernel classifier that uses graph embedding techniques for efficient kernel matrix embedding, achieving comparable accuracy to traditional methods with improved speed.

Contribution

It introduces a novel kernel-based classifier that leverages graph embedding techniques for scalable multi-kernel learning, with theoretical analysis and empirical validation.

Findings

Faster runtime than SVMs and neural networks

Comparable classification accuracy across datasets

Effective integration of multiple kernels

Abstract

This paper introduces a new kernel-based classifier by viewing kernel matrices as generalized graphs and leveraging recent progress in graph embedding techniques. The proposed method facilitates fast and scalable kernel matrix embedding, and seamlessly integrates multiple kernels to enhance the learning process. Our theoretical analysis offers a population-level characterization of this approach using random variables. Empirically, our method demonstrates superior running time compared to standard approaches such as support vector machines and two-layer neural network, while achieving comparable classification accuracy across various simulated and real datasets.