SE-VGAE: Unsupervised Disentangled Representation Learning for Interpretable Architectural Layout Design Graph Generation
This work addresses the lack of interpretable graph generation methods for architectural design, which could aid architects and designers in exploring layout spaces, though it appears incremental as it builds on existing graph auto-encoder techniques.
The authors tackled the problem of generating architectural layout designs using graph-based representation learning by introducing SE-VGAE, an unsupervised framework that generates attributed adjacency multi-graphs, achieving enhanced fidelity and diversity in layout generation as demonstrated through extensive experiments. They also contributed a new large-scale dataset from real-world floor plans to support this research.
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.