Graph Classification via Deep Learning with Virtual Nodes

By Trang Pham, Truyen Tran, Khanh Hoa Dam, Svetha Venkatesh. 2017

57 citations recorded by the source corpus.

Learning representation for graph classification turns a variable-size graph into a fixed-size vector (or matrix). Such a representation works nicely with algebraic manipulations. Here we introduce a simple method to augment an attributed graph with a virtual node that is bidirectionally connected to all existing nodes. The virtual node represents the latent aspects of the graph, which are not immediately available from the attributes and local connectivity structures. The expanded graph is then put through any node representation method. The representation of the virtual node is then the representation of the entire graph. In this paper, we use the recently introduced Column Network for the expanded graph, resulting in a new end-to-end graph classification model dubbed Virtual Column Network (VCN). The model is validated on two tasks: (i) predicting bio-activity of chemical compounds, and (ii) finding software vulnerability from source code. Results demonstrate that VCN is competitive against well-established rivals.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Materials Chemistry

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

1. Masanori Koyama
2. Bernd Malle
3. Anna Saranti
4. Andreas Holzinger
5. Katsuhiko Ishiguro
6. Bastian Pfeifer
7. Shin-ichi Maeda
8. Quoc V. Le

In Computational Theory and Mathematics

1. Andreas Holzinger
2. Katsuhiko Ishiguro
3. Masanori Koyama
4. Shin-ichi Maeda

In Materials Chemistry

1. Andreas Holzinger
2. Katsuhiko Ishiguro
3. Masanori Koyama
4. Shin-ichi Maeda

Citations in the corpus

• Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks (2019, background): “[18] propose similar ideas to learn a graph level representation on a simple GNN.”
• Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI (2021, background): “The literature contains several approaches to achieve uch coarsened embeddings: while (i) simple aggregation of node feaures can already suffice [41], (ii) introducing virtual nodes and learning their embeddings together with the rest of the subgraph [42] promises a very flexible clustering strategy”
• Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis (2019, methodology): “In this study, we use supernode [8, 15, 20] to promote the global propagation of the information in molecular graphs.”