Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks
By Katsuhiko Ishiguro, Shin-ichi Maeda, Masanori Koyama. 2019
32 citations recorded by the source corpus.
Recently, Graph Neural Networks (GNNs) are trending in the machine learning community as a family of architectures that specializes in capturing the features of graph-related datasets, such as those pertaining to social networks and chemical structures. Unlike for other families of the networks, the representation power of GNNs has much room for improvement, and many graph networks to date suffer from the problem of underfitting. In this paper we will introduce a Graph Warp Module, a supernode-based auxiliary network module that can be attached to a wide variety of existing GNNs in order to improve the representation power of the original networks. Through extensive experiments on molecular graph datasets, we will show that our GWM indeed alleviates the underfitting problem for various existing networks, and that it can even help create a network with the state-of-the-art generalization performance.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Materials Chemistry, Graph Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jure Leskovec
- Marinka Zitnik
- Yuxiao Dong
- Hongyu Ren
- Weihua Hu
- Percy Liang
- Matthias Fey
- William L. Hamilton
In Computational Theory and Mathematics
- Marinka Zitnik
- Jure Leskovec
- Bowen Liu
- Weihua Hu
- Joseph Gomes
- Percy Liang
- Vijay S. Pande
- Yuxiao Dong
In Materials Chemistry
- Jure Leskovec
- Marinka Zitnik
- Bowen Liu
- Weihua Hu
- Joseph Gomes
- Percy Liang
- Vijay S. Pande
- Yuxiao Dong
In Graph Learning
- Jure Leskovec
- Marinka Zitnik
- Yuxiao Dong
- Weihua Hu
- Matthias Fey
- William L. Hamilton
- Percy Liang
- Bowen Liu
Citations in the corpus
- Strategies for Pre-training Graph Neural Networks (2019, methodology): “On the HIV dataset, where a number of recent works (Wu et al., 2018; Li et al., 2017; Ishiguro et al., 2019) have reported performance on the same scaffold split and using the same protocol, our best pre-trained model (ContextPred + Supervised) achieves state-of-the-art performance.”
- Open Graph Benchmark: Datasets for Machine Learning on Graphs (2020, methodology): “Recent work in graph ML (Hu et al., 2020a; Ishiguro et al., 2019) has started to adopt M OLECULE N ET (Wu et al., 2018) that contains a set of realistic and large-scale molecular property prediction datasets.”