LCS Graph Kernel Based on Wasserstein Distance in Longest Common Subsequence Metric Space

TL;DR

This paper introduces a novel graph kernel leveraging LCS similarity and Wasserstein distance in a new metric space, improving graph comparison by focusing on similar paths and reducing computational costs.

Contribution

It proposes a new LCS-based graph kernel and a Wasserstein distance in a specialized metric space, addressing limitations of existing path-based and message-passing methods.

Findings

The proposed kernel effectively captures path similarities.

The Wasserstein distance emphasizes similar path comparisons.

The adjacency merging reduces computational complexity.

Abstract

For graph learning tasks, many existing methods utilize a message-passing mechanism where vertex features are updated iteratively by aggregation of neighbor information. This strategy provides an efficient means for graph features extraction, but obtained features after many iterations might contain too much information from other vertices, and tend to be similar to each other. This makes their representations less expressive. Learning graphs using paths, on the other hand, can be less adversely affected by this problem because it does not involve all vertex neighbors. However, most of them can only compare paths with the same length, which might engender information loss. To resolve this difficulty, we propose a new Graph Kernel based on a Longest Common Subsequence (LCS) similarity. Moreover, we found that the widely-used R-convolution framework is unsuitable for path-based Graph Kernel because a huge number of comparisons between dissimilar paths might deteriorate graph distances calculation. Therefore, we propose a novel metric space by exploiting the proposed LCS-based similarity, and compute a new Wasserstein-based graph distance in this metric space, which emphasizes more the comparison between similar paths. Furthermore, to reduce the computational cost, we propose an adjacent point merging operation to sparsify point clouds in the metric space.