Fast Graph Learning with Unique Optimal Solutions

02/17/2021 βˆ™ by Sami Abu-El-Haija, et al. βˆ™ 23 βˆ™

Graph Representation Learning (GRL) has been advancing at an unprecedented rate. However, many results rely on careful design and tuning of architectures, objectives, and training schemes. We propose efficient GRL methods that optimize convexified objectives with known closed form solutions. Guaranteed convergence to a global optimum releases practitioners from hyper-parameter and architecture tuning. Nevertheless, our proposed method achieves competitive or state-of-the-art performance on popular GRL tasks while providing orders of magnitude speedup. Although the design matrix (𝐌) of our objective is expensive to compute, we exploit results from random matrix theory to approximate solutions in linear time while avoiding an explicit calculation of 𝐌. Our code is online: http://github.com/samihaija/tf-fsvd

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

Code Repositories

tf-fsvd

Functional TensorFlow Implementation of Singular Value Decomposition for paper Fast Graph Learning


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.