arXiv Open Access 2025

Semantically Consistent Discrete Diffusion for 3D Biological Graph Modeling

Chinmay Prabhakar Suprosanna Shit Tamaz Amiranashvili Hongwei Bran Li Bjoern Menze
Lihat Sumber

Abstrak

3D spatial graphs play a crucial role in biological and clinical research by modeling anatomical networks such as blood vessels,neurons, and airways. However, generating 3D biological graphs while maintaining anatomical validity remains challenging, a key limitation of existing diffusion-based methods. In this work, we propose a novel 3D biological graph generation method that adheres to structural and semantic plausibility conditions. We achieve this by using a novel projection operator during sampling that stochastically fixes inconsistencies. Further, we adopt a superior edge-deletion-based noising procedure suitable for sparse biological graphs. Our method demonstrates superior performance on two real-world datasets, human circle of Willis and lung airways, compared to previous approaches. Importantly, we demonstrate that the generated samples significantly enhance downstream graph labeling performance. Furthermore, we show that our generative model is a reasonable out-of-the-box link predictior.

Topik & Kata Kunci

Penulis (5)

C

Chinmay Prabhakar

S

Suprosanna Shit

T

Tamaz Amiranashvili

H

Hongwei Bran Li

B

Bjoern Menze

Format Sitasi

Prabhakar, C., Shit, S., Amiranashvili, T., Li, H.B., Menze, B. (2025). Semantically Consistent Discrete Diffusion for 3D Biological Graph Modeling. https://arxiv.org/abs/2507.04856

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓