On a Family of Decomposable Kernels on Sequences

TL;DR

This paper introduces a new family of decomposable Mercer kernels for sequence data, enabling efficient similarity computation and improved classification performance over existing sequence kernels.

Contribution

It proposes a novel family of kernels combining symbol and structure similarities, with an efficient computation method for sequential data.

Findings

The kernels outperform the Global Alignment kernel in classification tasks.

The proposed kernels are computationally efficient.

Experimental results demonstrate improved accuracy on sequence classification.

Abstract

In many applications data is naturally presented in terms of orderings of some basic elements or symbols. Reasoning about such data requires a notion of similarity capable of handling sequences of different lengths. In this paper we describe a family of Mercer kernel functions for such sequentially structured data. The family is characterized by a decomposable structure in terms of symbol-level and structure-level similarities, representing a specific combination of kernels which allows for efficient computation. We provide an experimental evaluation on sequential classification tasks comparing kernels from our family of kernels to a state of the art sequence kernel called the Global Alignment kernel which has been shown to outperform Dynamic Time Warping