# Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020

arXiv: https://arxiv.org/abs/2204.02625 · HTML: https://mlsanity.com/paper/2204.02625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 20 of 20)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Topology Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1710.10370/) (2017)
- [Auto-GNN: Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/1909.03184/) (2019)
- [Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching](https://mlsanity.com/paper/1911.04131/) (2019)
- [Policy-GNN: Aggregation Optimization for Graph Neural Networks](https://mlsanity.com/paper/2006.15097/) (2020)
- [Search to aggregate neighborhood for graph neural network](https://mlsanity.com/paper/2104.06608/) (2021)
- [Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells](https://mlsanity.com/paper/1810.10804/) (2018)
- [Pooling Architecture Search for Graph Classification](https://mlsanity.com/paper/2108.10587/) (2021)
- [DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2010.03250/) (2020)
- [AutoGraph: Automated Graph Neural Network](https://mlsanity.com/paper/2011.11288/) (2020)
- [Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective](https://mlsanity.com/paper/2112.14531/) (2021)
- [Autonomous Graph Mining Algorithm Search with Best Speed/Accuracy Trade-off](https://mlsanity.com/paper/2011.14925/) (2020)
- [Search For Deep Graph Neural Networks](https://mlsanity.com/paper/2109.10047/) (2021)

## Abstract (arXiv)

Graph structured data is ubiquitous in daily life and scientific areas and has attracted increasing attention. Graph Neural Networks (GNNs) have been proved to be effective in modeling graph structured data and many variants of GNN architectures have been proposed. However, much human effort is often needed to tune the architecture depending on different datasets. Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs, but their methods focus more on the architecture search. To understand GNN practitioners' automated solutions, we organized AutoGraph Challenge at KDD Cup 2020, emphasizing on automated graph neural networks for node classification. We received top solutions especially from industrial tech companies like Meituan, Alibaba and Twitter, which are already open sourced on Github. After detailed comparisons with solutions from academia, we quantify the gaps between academia and industry on modeling scope, effectiveness and efficiency, and show that (1) academia AutoML for Graph solutions focus on GNN architecture search while industrial solutions, especially the winning ones in the KDD Cup, tend to obtain an overall solution (2) by neural architecture search only, academia solutions achieve on average 97.3% accuracy of industrial solutions (3) academia solutions are cheap to obtain with several GPU hours while industrial solutions take a few months' labors. Academic solutions also contain much fewer parameters.