Multiple Kernel Representation Learning on Networks

TL;DR

This paper introduces a novel multiple kernel matrix factorization approach that combines random walk information and kernel learning to improve node representations in networks, outperforming existing methods.

Contribution

It proposes a weighted matrix factorization model with multiple kernel learning, enhancing expressiveness and computational efficiency for network node embedding.

Findings

Outperforms baseline node embedding algorithms in real-world network tasks.

Utilizes multiple kernels to adaptively learn better node representations.

Enhances matrix factorization with kernel functions for improved expressiveness.

Abstract

Learning representations of nodes in a low dimensional space is a crucial task with numerous interesting applications in network analysis, including link prediction, node classification, and visualization. Two popular approaches for this problem are matrix factorization and random walk-based models. In this paper, we aim to bring together the best of both worlds, towards learning node representations. In particular, we propose a weighted matrix factorization model that encodes random walk-based information about nodes of the network. The benefit of this novel formulation is that it enables us to utilize kernel functions without realizing the exact proximity matrix so that it enhances the expressiveness of existing matrix decomposition methods with kernels and alleviates their computational complexities. We extend the approach with a multiple kernel learning formulation that provides the flexibility of learning the kernel as the linear combination of a dictionary of kernels in data-driven fashion. We perform an empirical evaluation on real-world networks, showing that the proposed model outperforms baseline node embedding algorithms in downstream machine learning tasks.