CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
It addresses conditional graph generation for applications needing graphs with specific features, but it is incremental as it builds on existing graph generation methods.
The paper tackles class-conditional graph generation by introducing CCGG, which injects class information into a graph generator with a classification loss and gradient trick, and it outperforms existing methods on various datasets while maintaining graph quality.
Graph data structures are fundamental for studying connected entities. With an increase in the number of applications where data is represented as graphs, the problem of graph generation has recently become a hot topic. However, despite its significance, conditional graph generation that creates graphs with desired features is relatively less explored in previous studies. This paper addresses the problem of class-conditional graph generation that uses class labels as generation constraints by introducing the Class Conditioned Graph Generator (CCGG). We built CCGG by injecting the class information as an additional input into a graph generator model and including a classification loss in its total loss along with a gradient passing trick. Our experiments show that CCGG outperforms existing conditional graph generation methods on various datasets. It also manages to maintain the quality of the generated graphs in terms of distribution-based evaluation metrics.