Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity
By Yunsheng Bai, Haoyang Ding, Yang Qiao, Agustin Marinovic, Ken Gu, Tingting Chen, Yizhou Sun, Wei Wang. 2019
10 citations recorded by the source corpus.
We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity. Our approach, UGRAPHEMB, is a general framework that provides a novel means to performing graph-level embedding in a completely unsupervised and inductive manner. The learned neural network can be considered as a function that receives any graph as input, either seen or unseen in the training set, and transforms it into an embedding. A novel graph-level embedding generation mechanism called Multi-Scale Node Attention (MSNA), is proposed. Experiments on five real graph datasets show that UGRAPHEMB achieves competitive accuracy in the tasks of graph classification, similarity ranking, and graph visualization.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, 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
- William L. Hamilton
- Weihua Hu
- Percy Liang
- Bowen Liu
- Vijay S. Pande
- Joseph Gomes
In Computer Vision and Pattern Recognition
- Jure Leskovec
- Marinka Zitnik
- Percy Liang
- Joseph Gomes
- Vijay S. Pande
- Bowen Liu
- Weihua Hu
- Mohit Bansal
In Statistical and Nonlinear Physics
- Marinka Zitnik
- Jure Leskovec
- Percy Liang
- Weihua Hu
- Bowen Liu
- Vijay S. Pande
- Joseph Gomes
- Jaewon Yang
In Graph Learning
- Marinka Zitnik
- Jure Leskovec
- Weihua Hu
- Percy Liang
- William L. Hamilton
- Bowen Liu
- Vijay S. Pande
- Joseph Gomes
Citations in the corpus
- Strategies for Pre-training Graph Neural Networks (2019, background): “Examples of such tasks include modeling the graph edit distance (Bai et al., 2019) or predicting graph structure similarity (Navarin et al.”
- Pre-training Graph Neural Networks (2019, background): “…two options possible for graph-level pre-training: learn composable embeddings either (1) by making predictions on domain-specific auxiliary supervised tasks, or, (2) by performing self-supervised prediction on graph-level structure, e.g. , graph edit distance [3] or graph structure similarity [33].”