MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: graph kernel, graph metric learning, maximum mean discrepancy
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: This paper presents MMD-based graph kernels for improved graph metric learning with proven effectiveness in clustering and classification tasks.
Abstract: This paper focuses on graph metric learning. First, we present a class of maximum mean discrepancy (MMD) based graph kernels, called MMD-GK. These kernels are computed by applying MMD to the node representations of two graphs with message-passing propagation.
Secondly, we provide a class of deep MMD-GKs that are able to learn graph kernels and implicit graph features adaptively in an unsupervised manner. Thirdly, we propose a class of supervised deep MMD-GKs that are able to utilize label information of graphs and hence yield more discriminative metrics. Besides the algorithms, we provide theoretical analysis for the proposed methods. The proposed methods are evaluated in comparison to many baselines such as graph kernels and graph neural networks in the tasks of graph clustering and graph classification. The numerical results demonstrate the effectiveness and superiority of our methods.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: metric learning, kernel learning, and sparse coding
Submission Number: 3490
Loading