Automated Machine Learning on Graphs: A Survey (2021-03-01T00:00:00.000000Z)

TL;DR

This paper comprehensively survey AutoML on graphs, primarily focusing on hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning.

Abstract

Machine learning on graphs has been extensively studied in both academic and industry. However, as the literature on graph learning booms with a vast number of emerging methods and techniques, it becomes increasingly difficult to manually design the optimal machine learning algorithm for different graph-related tasks. To solve this critical challenge, automated machine learning (AutoML) on graphs which combines the strength of graph machine learning and AutoML together, is gaining attention from the research community. Therefore, we comprehensively survey AutoML on graphs in this paper, primarily focusing on hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning. We further overview libraries related to automated graph machine learning and in-depth discuss AutoGL, the first dedicated open-source library for AutoML on graphs. In the end, we share our insights on future research directions for automated graph machine learning. This paper is the first systematic and comprehensive review of automated machine learning on graphs to the best of our knowledge.

Authors

Ziwei Zhang

2 papers

Xin Wang

2 papers

Wenwu Zhu

6 papers

TL;DR

Abstract

Authors

References112 items

One-shot Graph Neural Architecture Search with Dynamic Search Space

AutoSTG: Neural Architecture Search for Predictions of Spatio-Temporal Graph✱

AutoGL: A Library for Automated Graph Learning

Search to aggregate neighborhood for graph neural network

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks

JITuNE: Just-In-Time Hyperparameter Tuning for Network Embedding Algorithms

Explainability in Graph Neural Networks: A Taxonomic Survey

AutoGraph: Automated Graph Neural Network

Design Space for Graph Neural Networks

Autonomous Graph Mining Algorithm Search with Best Speed/Accuracy Trade-off

Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS

Propagation Model Search for Graph Neural Networks

Evolutionary Architecture Search for Graph Neural Networks

Learned Low Precision Graph Neural Networks

Graph Neural Network Architecture Search for Molecular Property Prediction

Simplifying Architecture Search for Graph Neural Network

Neural Architecture Search in Graph Neural Networks

Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

BRP-NAS: Prediction-based NAS using GCNs

Graph Structure of Neural Networks

Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks

Graph Neural Architecture Search

Hardware-Aware Transformable Architecture Search with Efficient Search Space

Hardware Acceleration of Graph Neural Networks

Graph Neural Networks in TensorFlow and Keras with Spektral

Open Graph Benchmark: Datasets for Machine Learning on Graphs

Network medicine framework for identifying drug-repurposing opportunities for COVID-19

Probabilistic Dual Network Architecture Search on Graphs

AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data

Karate Club: An API Oriented Open-Source Python Framework for Unsupervised Learning on Graphs

SGAS: Sequential Greedy Architecture Search

Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching

Learning Disentangled Representations for Recommendation

Auto-GNN: Neural architecture search of graph neural networks

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks.

AutoML: A Survey of the State-of-the-Art

AutoNE: Hyperparameter Optimization for Massive Network Embedding

Automated Machine Learning: State-of-The-Art and Open Challenges

DeepGCNs: Can GCNs Go As Deep As CNNs?

Exploring Randomly Wired Neural Networks for Image Recognition

Single Path One-Shot Neural Architecture Search with Uniform Sampling

PyTorch-BigGraph: A Large-scale Graph Embedding System

Fast Graph Representation Learning with PyTorch Geometric

NAS-Bench-101: Towards Reproducible Neural Architecture Search

AliGraph: A Comprehensive Graph Neural Network Platform

Adversarial Attack and Defense on Graph Data: A Survey

Graph Neural Networks: A Review of Methods and Applications

Deep Learning on Graphs: A Survey

Network embedding in biomedical data science

Pitfalls of Graph Neural Network Evaluation

Taking Human out of Learning Applications: A Survey on Automated Machine Learning

CEM-RL: Combining evolutionary and gradient-based methods for policy search

Graph HyperNetworks for Neural Architecture Search

SNAS: Stochastic Neural Architecture Search

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

On Power Law Growth of Social Networks

GEM: A Python package for graph embedding methods

MnasNet: Platform-Aware Neural Architecture Search for Mobile

Auto-Keras: An Efficient Neural Architecture Search System

DARTS: Differentiable Architecture Search

Hierarchical Graph Representation Learning with Differentiable Pooling

Representation Learning on Graphs with Jumping Knowledge Networks

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

Relational inductive biases, deep learning, and graph networks

Efficient Neural Architecture Search via Parameter Sharing

Regularized Evolution for Image Classifier Architecture Search

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Knowledge Graph Embedding: A Survey of Approaches and Applications

A Survey on Network Embedding

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications

Representation Learning on Graphs: Methods and Applications

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Learning Transferable Architectures for Scalable Image Recognition

Predicting multicellular function through multi-layer tissue networks

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting