CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
arXiv:2110.03800 · doi:10.1145/3487553.3524721
Abstract
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.
References in corpus (13)
- Categorical Reparameterization with Gumbel-Softmax
- Hierarchical Graph Representation Learning with Differentiable Pooling
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Constrained Graph Variational Autoencoders for Molecule Design
- NetGAN: Generating Graphs via Random Walks
- Efficient Graph Generation with Graph Recurrent Attention Networks
- Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
- GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
- ContraGAN: Contrastive Learning for Conditional Image Generation
- Topic-Guided Variational Autoencoders for Text Generation
- DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation
- Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
- Text as Neural Operator: Image Manipulation by Text Instruction