g-Inspector: Recurrent Attention Model on Graph

• Published in: IEEE transactions on knowledge and data engineering 2022-02, Vol.34 (2), p.680-690
• Main Authors: Luo, Zhiling, Cui, Yinghua, Zhao, Sha, Yin, Jianwei
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Bioinformatics; Biological system modeling; Classification; Computational modeling; Data models; Feature extraction; Graph classification; graph mining; Kernel; recurrent neural network; reinforcement learning; Social networking (online); Social networks; Task analysis
• ISSN: 1041-4347; 1558-2191
• DOI: 10.1109/TKDE.2020.2983689

Graph classification problem is becoming one of research hotspots in the realm of graph mining, which has been widely used in cheminformatics, bioinformatics and social network analytics. Existing approaches, such as graph kernel methods and graph Convolutional Neural Network, are facing the challenges of non-interpretability and high dimensionality. To address the problems, we propose a novel recurrent attention model, called g-Inspector, which applies the attention mechanism to investigate the significance of each region to make the results interpretable. It also takes a shift operation to guide the inspector agent to discover the next relevant region, so that the model sequentially loads small regions instead of the entire large graph, to solve the high dimensionality problem. The experiments conducted on standard graph datasets show the effectiveness of our g-Inspector in graph classification problems.