Graph-level Neural Networks: Current Progress and Future Directions

TL;DR

This survey reviews the current state and future directions of Graph-level Neural Networks (GLNNs), covering models, benchmarks, datasets, and challenges in the field of graph-structured data analysis.

Contribution

It provides a systematic taxonomy of GLNNs, analyzes recent models, and discusses reproducibility, benchmarks, and future research directions.

Findings

Comprehensive taxonomy of GLNNs categories.

Analysis of state-of-the-art models and datasets.

Identification of challenges and future research directions.

Abstract

Graph-structured data consisting of objects (i.e., nodes) and relationships among objects (i.e., edges) are ubiquitous. Graph-level learning is a matter of studying a collection of graphs instead of a single graph. Traditional graph-level learning methods used to be the mainstream. However, with the increasing scale and complexity of graphs, Graph-level Neural Networks (GLNNs, deep learning-based graph-level learning methods) have been attractive due to their superiority in modeling high-dimensional data. Thus, a survey on GLNNs is necessary. To frame this survey, we propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling. The representative and state-of-the-art models in each category are focused on this survey. We also investigate the reproducibility, benchmarks, and new graph datasets of GLNNs. Finally, we conclude future directions to further push forward GLNNs. The repository of this survey is available at https://github.com/GeZhangMQ/Awesome-Graph-level-Neural-Networks.