# Automated Graph Learning via Population Based Self-Tuning GCN

arXiv: https://arxiv.org/abs/2107.04713 · HTML: https://mlsanity.com/paper/2107.04713/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 9 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Forward and Reverse Gradient-Based Hyperparameter Optimization](https://mlsanity.com/paper/1703.01785/) (2017)
- [Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions](https://mlsanity.com/paper/1903.03088/) (2019)
- [Auto-GNN: Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/1909.03184/) (2019)
- [Policy-GNN: Aggregation Optimization for Graph Neural Networks](https://mlsanity.com/paper/2006.15097/) (2020)
- [Co-embedding of Nodes and Edges with Graph Neural Networks](https://mlsanity.com/paper/2010.13242/) (2020)
- [Graph Neural Network Architecture Search for Molecular Property Prediction](https://mlsanity.com/paper/2008.12187/) (2020)
- [Edge: Enriching Knowledge Graph Embeddings with External Text](https://mlsanity.com/paper/2104.04909/) (2021)
- [Evolutionary Architecture Search for Graph Neural Networks](https://mlsanity.com/paper/2009.10199/) (2020)

## Built on by (most cited first, 5 of 5)

- [Fair Attribute Completion on Graph with Missing Attributes](https://mlsanity.com/paper/2302.12977/) (2023)
- [Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions](https://mlsanity.com/paper/2201.01288/) (2022)
- [MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning](https://mlsanity.com/paper/2206.09280/) (2022)
- [Modeling Mask Uncertainty in Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2112.15362/) (2021)
- [GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection](https://mlsanity.com/paper/2404.01578/) (2024)

## Abstract (arXiv)

Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification. Traditional GCN models suffer from the issues of overfitting and oversmoothing, while some recent techniques like DropEdge could alleviate these issues and thus enable the development of deep GCN. However, training GCN models is non-trivial, as it is sensitive to the choice of hyperparameters such as dropout rate and learning weight decay, especially for deep GCN models. In this paper, we aim to automate the training of GCN models through hyperparameter optimization. To be specific, we propose a self-tuning GCN approach with an alternate training algorithm, and further extend our approach by incorporating the population based training scheme. Experimental results on three benchmark datasets demonstrate the effectiveness of our approaches on optimizing multi-layer GCN, compared with several representative baselines.