Fast Graph Learning with Unique Optimal Solutions

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

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

page 1

page 2

page 3

page 4

10/05/2020

Accurate, Efficient and Scalable Training of Graph Neural Networks

Graph Neural Networks (GNNs) are powerful deep learning models to genera...
09/14/2018

Revisiting Random Binning Features: Fast Convergence and Strong Parallelizability

Kernel method has been developed as one of the standard approaches for n...
07/20/2020

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

In this paper, we propose an efficient NAS algorithm for generating task...
11/25/2014

Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data

We propose an efficient family of algorithms to learn the parameters of ...
05/27/2021

Towards a Better Understanding of Linear Models for Recommendation

Recently, linear regression models, such as EASE and SLIM, have shown to...
02/20/2020

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning

We introduce a parameterization method called Neural Bayes which allows ...
02/18/2018

Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation

We propose an efficient stochastic variational approach to GP classifica...

Code Repositories

tf-fsvd

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


view repo