mlsanityData to 7 Oct 2026

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

arXiv 2204.02625 ↗First posted 6 Apr 2022cs.LG cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

20 of 31 references.

References · 20

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2017Topology Adaptive Graph Convolutional Networkscited by 112
  10. 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
  11. 2019Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searchingcited by 70
  12. 2020Policy-GNN: Aggregation Optimization for Graph Neural Networkscited by 48
8 more
  1. 2021Search to aggregate neighborhood for graph neural networkcited by 48
  2. 2018Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cellscited by 39
  3. 2021Pooling Architecture Search for Graph Classificationcited by 36
  4. 2020DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networkscited by 34
  5. 2020AutoGraph: Automated Graph Neural Networkcited by 21
  6. 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
  7. 2020Autonomous Graph Mining Algorithm Search with Best Speed/Accuracy Trade-offcited by 6
  8. 2021Search For Deep Graph Neural Networkscited by 6

Built on by

Not cited yet.