A Deep Generative Model for Graph Layout

Abstract

Different layouts can characterize different aspects of the same graph. Finding a "good" layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-and-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.

arXiv commentTo appear in IEEE Transactions on Visualization and Computer Graphics. In Proc. IEEE VIS 2019 (InfoVis)

References in corpus (19)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Community structure in social and biological networks
• Auto-Encoding Variational Bayes
• Finding community structure in networks using the eigenvectors of matrices
• Inductive Representation Learning on Large Graphs
• Automatic chemical design using a data-driven continuous representation of molecules
• On the Convergence of Adam and Beyond
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Community Structure in Jazz
• Representation Learning on Graphs with Jumping Knowledge Networks
• Hierarchical Graph Representation Learning with Differentiable Pooling
• A Neural Representation of Sketch Drawings
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
• Hierarchical Block Structures and High-resolution Model Selection in Large Networks
• What Would a Graph Look Like in This Layout? A Machine Learning Approach to Large Graph Visualization
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
• Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach

Cited by in corpus (16)

• A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization
• Graph Neural Networks for Graph Drawing
• A Study of Mental Maps in Immersive Network Visualization
• Quantivine: A Visualization Approach for Large-scale Quantum Circuit Representation and Analysis
• Interactive Visual Pattern Search on Graph Data via Graph Representation Learning
• A Deep Generative Model for Reordering Adjacency Matrices
• Revisiting 2D Convolutional Neural Networks for Graph-based Applications
• A contribution to Optimal Transport on incomparable spaces
• Adversarial Attacks on Machine Learning-Aided Visualizations
• Auditing the Sensitivity of Graph-based Ranking with Visual Analytics
• Deep Neural Network for DrawiNg Networks, (DNN)^2
• DRGraph: An Efficient Graph Layout Algorithm for Large-scale Graphs by Dimensionality Reduction
• PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning
• DeepGD: A Deep Learning Framework for Graph Drawing Using GNN
• Interpreting Graph Drawing with Multi-Agent Reinforcement Learning
• Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs