Automated Machine Learning on Graphs: A Survey
arXiv:2103.00742 · doi:10.24963/ijcai.2021/637
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.
arXiv commentIJCAI 2021 Survey Track. Change bib style for better retrieval and add paper collection URL
References in corpus (41)
- Practical Bayesian Optimization of Machine Learning Algorithms
- Neural Architecture Search with Reinforcement Learning
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Categorical Reparameterization with Gumbel-Softmax
- Graph Embedding Techniques, Applications, and Performance: A Survey
- Neural Architecture Search: A Survey
- AutoML: A Survey of the State-of-the-Art
- Graph Neural Networks: A Review of Methods and Applications
- DARTS: Differentiable Architecture Search
- Fast Graph Representation Learning with PyTorch Geometric
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Representation Learning on Graphs with Jumping Knowledge Networks
- ParamILS: An Automatic Algorithm Configuration Framework
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- Pitfalls of Graph Neural Network Evaluation
- Predicting multicellular function through multi-layer tissue networks
- Large-Scale Evolution of Image Classifiers
- Adversarial Attack and Defense on Graph Data: A Survey
- NAS-Bench-101: Towards Reproducible Neural Architecture Search
- PyTorch-BigGraph: A Large-scale Graph Embedding System
- Benchmarking Graph Neural Networks
- Design Space for Graph Neural Networks
- AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
- Automated Machine Learning: State-of-The-Art and Open Challenges
- Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks
- Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19
- Learning Disentangled Representations for Recommendation
- CEM-RL: Combining evolutionary and gradient-based methods for policy search
- Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
- Auto-GNN: Neural Architecture Search of Graph Neural Networks
- DIG: A Turnkey Library for Diving into Graph Deep Learning Research
- Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
- Graph Structure of Neural Networks
- Probabilistic Dual Network Architecture Search on Graphs
- Learned Low Precision Graph Neural Networks
- Evolutionary Architecture Search for Graph Neural Networks
- A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks
- Simplifying Architecture Search for Graph Neural Network
- CogDL: A Comprehensive Library for Graph Deep Learning
- JITuNE: Just-In-Time Hyperparameter Tuning for Network Embedding Algorithms