SCGG: A Deep Structure-Conditioned Graph Generative Model

Abstract

Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their effectiveness by empowering them to generate new graph samples that meet the desired criteria. This paper presents a conditional deep graph generation method called SCGG that considers a particular type of structural conditions. Specifically, our proposed SCGG model takes an initial subgraph and autoregressively generates new nodes and their corresponding edges on top of the given conditioning substructure. The architecture of SCGG consists of a graph representation learning network and an autoregressive generative model, which is trained end-to-end. Using this model, we can address graph completion, a rampant and inherently difficult problem of recovering missing nodes and their associated edges of partially observed graphs. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our method compared with state-of-the-art baselines.

References in corpus (29)

• Statistical mechanics of complex networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Predicting Missing Links via Local Information
• Kronecker Graphs: An Approach to Modeling Networks
• Link Prediction Based on Local Random Walk
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• Efficient Graph Generation with Graph Recurrent Attention Networks
• Scaffold-based molecular design using graph generative model
• Hierarchical Generation of Molecular Graphs using Structural Motifs
• BRP-NAS: Prediction-based NAS using GCNs
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Trans4E: Link Prediction on Scholarly Knowledge Graphs
• GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generation
• Structure-Aware Transformer for Graph Representation Learning
• Graphite: Iterative Generative Modeling of Graphs
• Guiding Deep Molecular Optimization with Genetic Exploration
• Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition
• Edge-based sequential graph generation with recurrent neural networks
• GraphDF: A Discrete Flow Model for Molecular Graph Generation
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
• Goal-directed graph construction using reinforcement learning
• Dirichlet Graph Variational Autoencoder
• GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference
• EPG2S: Speech Generation and Speech Enhancement based on Electropalatography and Audio Signals using Multimodal Learning
• CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
• DeepNC: Deep Generative Network Completion