mlsanityData to 14 Oct 2026

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

arXiv 2406.17418 ↗First posted 25 Jun 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 25 Jun 2024.

Builds on

32 of 52 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016Layer Normalizationcited by 5,669
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2013Auto-Encoding Variational Bayescited by 4,053
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  10. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  11. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  12. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
20 more
  1. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  2. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  3. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  4. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  5. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  6. 2020Can Graph Neural Networks Count Substructures?cited by 236
  7. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
  8. 2019Position-aware Graph Neural Networkscited by 203
  9. 2020Random Features Strengthen Graph Neural Networkscited by 186
  10. 2019Relational Pooling for Graph Representationscited by 150
  11. 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 114
  12. 2022Disentangled Representation Learningcited by 112
  13. 2020A Systematic Survey on Deep Generative Models for Graph Generationcited by 94
  14. 2018An empirical study on evaluation metrics of generative adversarial networkscited by 81
  15. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  16. 2022On Evaluation Metrics for Graph Generative Modelscited by 46
  17. 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
  18. 2020Interpretable Deep Graph Generation with Node-Edge Co-Disentanglementcited by 24
  19. 2022Disentangled Spatiotemporal Graph Generative Modelscited by 12
  20. 2019Disentangling Interpretable Generative Parameters of Random and Real-World Graphscited by 5

Built on by

Not cited yet.