Metric Learning for Ordered Labeled Trees with pq-grams

TL;DR

This paper introduces a new, computationally efficient metric learning method for ordered labeled trees using pq-grams, outperforming traditional edit distance approaches in speed while maintaining competitive accuracy.

Contribution

The paper proposes a differentiable, weighted pq-gram distance and a metric learning framework based on LMNN for tree-structured data, reducing computation time significantly.

Findings

Achieves competitive classification accuracy with state-of-the-art methods.

Reduces computation time compared to tree edit distance methods.

Demonstrates effectiveness on various classification tasks.

Abstract

Computing the similarity between two data points plays a vital role in many machine learning algorithms. Metric learning has the aim of learning a good metric automatically from data. Most existing studies on metric learning for tree-structured data have adopted the approach of learning the tree edit distance. However, the edit distance is not amenable for big data analysis because it incurs high computation cost. In this paper, we propose a new metric learning approach for tree-structured data with pq-grams. The pq-gram distance is a distance for ordered labeled trees, and has much lower computation cost than the tree edit distance. In order to perform metric learning based on pq-grams, we propose a new differentiable parameterized distance, weighted pq-gram distance. We also propose a way to learn the proposed distance based on Large Margin Nearest Neighbors (LMNN), which is a well-studied and practical metric learning scheme. We formulate the metric learning problem as an optimization problem and use the gradient descent technique to perform metric learning. We empirically show that the proposed approach not only achieves competitive results with the state-of-the-art edit distance-based methods in various classification problems, but also solves the classification problems much more rapidly than the edit distance-based methods.