SE-VGAE: Unsupervised Disentangled Representation Learning for Interpretable Architectural Layout Design Graph Generation

TL;DR

This study introduces an unsupervised disentangled representation learning framework, Style-based Edge-augmented Variational Graph Auto-Encoder (SE-VGAE), aiming to generate architectural layout in the form of attributed adjacency multi-graphs while prioritizing representation disentanglement.

Abstract

Despite the suitability of graphs for capturing the relational structures inherent in architectural layout designs, there is a notable dearth of research on interpreting architectural design space using graph-based representation learning and exploring architectural design graph generation. Concurrently, disentangled representation learning in graph generation faces challenges such as node permutation invariance and representation expressiveness. To address these challenges, we introduce an unsupervised disentangled representation learning framework, Style-based Edge-augmented Variational Graph Auto-Encoder (SE-VGAE), aiming to generate architectural layout in the form of attributed adjacency multi-graphs while prioritizing representation disentanglement. The framework is designed with three alternative pipelines, each integrating a transformer-based edge-augmented encoder, a latent space disentanglement module, and a style-based decoder. These components collectively facilitate the decomposition of latent factors influencing architectural layout graph generation, enhancing generation fidelity and diversity. We also provide insights into optimizing the framework by systematically exploring graph feature augmentation schemes and evaluating their effectiveness for disentangling architectural layout representation through extensive experiments. Additionally, we contribute a new benchmark large-scale architectural layout graph dataset extracted from real-world floor plan images to facilitate the exploration of graph data-based architectural design representation space interpretation. This study pioneered disentangled representation learning for the architectural layout graph generation. The code and dataset of this study will be open-sourced.

Figures (39)

• Figure 1: Overview of the proposed Style-based Edge-augmented Variational Graph Auto-Encoder (SE-VGAE) framework, together with three alternative pipelines, for the latent embedding space disentanglement of architectural layout design representation space
• Figure 2: Distribution of attributed adjacency graphs per architectural category (159 categories in total). The vertical axis is scaled according to the logarithm of image numbers
• Figure 3: Comparison of different graph representation model design choices and their corresponding metric values, including FID(FD), MMD Linear, MMD RBF, F1 PR, and F1 DC; the sweet spots for each metric measure are highlighted in dashed box
• Figure 4: Comparison of different graph representation model design choices and their corresponding metric values, including precision, density, recall, and coverage; the sweet spots for each metric measure are highlighted in dashed box
• Figure 5: Generated graph samples and their corresponding locations in the learned latent space using a trained framework with edge-augmented encoder, vanilla VAE disentanglement module, MLP-based decoder, SVD embeddings and 25 categories of architectural elements