LGMLOct 6, 2021

A Regularized Wasserstein Framework for Graph Kernels

arXiv:2110.02554v24 citations
Originality Highly original
AI Analysis

This work addresses the challenge of graph kernel learning for researchers in machine learning and graph analysis, offering a novel method with strong empirical gains.

The authors tackled the problem of learning graph kernels by proposing a regularized Wasserstein framework, which consistently outperformed 16 state-of-the-art baselines across 12 benchmark datasets for graphs with both discrete and continuous attributes.

We propose a learning framework for graph kernels, which is theoretically grounded on regularizing optimal transport. This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which can preserve both features and structure of graphs via Wasserstein distances on features and their local variations, local barycenters and global connectivity. Two strongly convex regularization terms are introduced to improve the learning ability. One is to relax an optimal alignment between graphs to be a cluster-to-cluster mapping between their locally connected vertices, thereby preserving the local clustering structure of graphs. The other is to take into account node degree distributions in order to better preserve the global structure of graphs. We also design an efficient algorithm to enable a fast approximation for solving the optimization problem. Theoretically, our framework is robust and can guarantee the convergence and numerical stability in optimization. We have empirically validated our method using 12 datasets against 16 state-of-the-art baselines. The experimental results show that our method consistently outperforms all state-of-the-art methods on all benchmark databases for both graphs with discrete attributes and graphs with continuous attributes.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes