ABSTRACT
Machine learning on graphs has been extensively studiedin 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 attentions from the research community. In this tutorial, we discuss AutoML on graphs, 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. To the best of our knowledge, this tutorial is the first to systematically and comprehensively review automated machine learning on graphs, possessing a great potential to draw a large amount of interests in the community.
- James Bergstra and Yoshua Bengio. Random search for hyper-parameter optimization. JMLR, 2012.Google ScholarDigital Library
- Michael M Bronstein et al. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 2017.Google Scholar
- Yuhui Ding, Quanming Yao, and Tong Zhang. Propagation model search for graph neural networks. arXiv:2010.03250, 2020.Google Scholar
- Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. Neural architecture search: A survey. JMLR, 2019.Google Scholar
- Yang Gao et al. Graph neural architecture search. In IJCAI, 2020.Google Scholar
- Chaoyu Guan et al. Autoattend: Automated attention representation search. In ICML, 2021.Google Scholar
- Chaoyu Guan et al. Autogl: A library for automated graph learning. arXiv:2104.04987, 2021.Google Scholar
- Mengying Guo et al. Jitune: Just-in-time hyperparameter tuning for network embedding algorithms. arXiv:2101.06427, 2021.Google Scholar
- Weihua Hu et al. Open graph benchmark: Datasets for machine learning on graphs. NeurIPS, 2020.Google Scholar
- Shengli Jiang and Prasanna Balaprakash. Graph neural network architecture search for molecular property prediction. In IEEE Big Data, 2020.Google ScholarCross Ref
- Guohao Li et al. Sgas: Sequential greedy architecture search. In CVPR, 2020.Google Scholar
- Yaoman Li and Irwin King. Autograph: Automated graph neural network. In ICONIP, 2020.Google Scholar
- Matheus Nunes et al. Neural architecture search in graph neural networks. In Brazilian Conference on Intelligent Systems, 2020.Google Scholar
- Wei Peng et al. Learning graph convolutional network for skeleton-based human action recognition by neural searching. AAAI, 2020.Google Scholar
- Pourchot and Sigaud. CEM-RL: Combining evolutionary and gradient-based methods for policy search. In ICLR, 2019.Google Scholar
- Min Shi et al. Evolutionary architecture search for graph neural networks. arXiv:2009.10199, 2020.Google Scholar
- Ke Tu et al. Autone: Hyperparameter optimization for massive network embedding. In KDD, 2019.Google Scholar
- Xin Wang et al. Explainable automated graph representation learning with hyperparameter importance. In ICML, 2021.Google Scholar
- Minji Yoon et al. Autonomous graph mining algorithm search with best speed/accuracy trade-off. In IEEE ICDM, 2020.Google Scholar
- Jiaxuan You et al. Design space for graph neural networks. NeurIPS, 2020.Google Scholar
- Yingfang Yuan et al. A novel genetic algorithm with hierarchical evaluation strategy for hyperparameter optimisation of graph neural networks. arXiv:2101.09300, 2021.Google Scholar
- Huan Zhao et al. Efficient graph neural architecture search, 2021.Google Scholar
- Huan Zhao, Lanning Wei, and Quanming Yao. Simplifying architecture search for graph neural network. arXiv:2008.11652, 2020.Google Scholar
- Yiren Zhao et al. Learned low precision graph neural networks. arXiv:2009.09232, 2020.Google Scholar
- Yiren Zhao et al. Probabilistic dual network architecture search on graphs. arXiv:2003.09676, 2020.Google Scholar
- Kaixiong Zhou et al. Auto-gnn: Neural architecture search of graph neural networks. arXiv:1909.03184, 2019.Google Scholar
Index Terms
- Automated Machine Learning on Graph
Recommendations
Graph Representation Learning: Foundations, Methods, Applications and Systems
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningGraphs such as social networks and molecular graphs are ubiquitous data structures in the real world. Due to their prevalence, it is of great research importance to extract meaningful patterns from graph structured data so that downstream tasks can be ...
From Zero to AI Hero with Automated Machine Learning
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAutomated ML is an emerging field in Machine Learning that helps developers and new data scientists with little data science knowledge build Machine Learning models and solutions without understanding the complexity of Learning Algorithm selection, and ...
A General Recipe for Automated Machine Learning in Practice
Advances in Artificial Intelligence – IBERAMIA 2022AbstractAutomated Machine Learning (AutoML) is an area of research that focuses on developing methods to generate machine learning models automatically. The idea of being able to build machine learning models with very little human intervention represents ...
Comments