Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation

Kartik Sharma, Srijan Kumar, Rakshit Trivedi
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44545-44564, 2024.

Abstract

Diffusion models lend transformative capabilities to the graph generation task, yet controlling the properties of the generated graphs remains challenging. Recent approaches augment support for controlling soft, differentiable properties but they fail to handle user-specified hard constraints that are non-differentiable. This often results in vague control, unsuitable for applications like drug discovery that demand satisfaction of precise constraints, e.g., the maximum number of bonds. To address this, we formalize the problem of controlled graph generation and introduce PRODIGY (PROjected DIffusion for controlled Graph Generation), an innovative plug-and-play approach enabling the generation of graphs with precise control, from any pre-trained diffusion model. PRODIGY employs a novel operator to project the samples at each diffusion step onto the specified constrained space. For a large class of practical constraints and a variety of graphs, our extensive experiments demonstrate that PRODIGY empowers state-of-the-art continuous and discrete diffusion models to produce graphs meeting specific, hard constraints. Our approach achieves up to 100% constraint satisfaction for non-attributed and molecular graphs, under a variety of constraints, marking a significant step forward in precise, interpretable graph generation. Code is provided on the project webpage: https://prodigy-diffusion.github.io/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-sharma24b, title = {Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation}, author = {Sharma, Kartik and Kumar, Srijan and Trivedi, Rakshit}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {44545--44564}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/sharma24b/sharma24b.pdf}, url = {https://proceedings.mlr.press/v235/sharma24b.html}, abstract = {Diffusion models lend transformative capabilities to the graph generation task, yet controlling the properties of the generated graphs remains challenging. Recent approaches augment support for controlling soft, differentiable properties but they fail to handle user-specified hard constraints that are non-differentiable. This often results in vague control, unsuitable for applications like drug discovery that demand satisfaction of precise constraints, e.g., the maximum number of bonds. To address this, we formalize the problem of controlled graph generation and introduce PRODIGY (PROjected DIffusion for controlled Graph Generation), an innovative plug-and-play approach enabling the generation of graphs with precise control, from any pre-trained diffusion model. PRODIGY employs a novel operator to project the samples at each diffusion step onto the specified constrained space. For a large class of practical constraints and a variety of graphs, our extensive experiments demonstrate that PRODIGY empowers state-of-the-art continuous and discrete diffusion models to produce graphs meeting specific, hard constraints. Our approach achieves up to 100% constraint satisfaction for non-attributed and molecular graphs, under a variety of constraints, marking a significant step forward in precise, interpretable graph generation. Code is provided on the project webpage: https://prodigy-diffusion.github.io/.} }
Endnote
%0 Conference Paper %T Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation %A Kartik Sharma %A Srijan Kumar %A Rakshit Trivedi %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-sharma24b %I PMLR %P 44545--44564 %U https://proceedings.mlr.press/v235/sharma24b.html %V 235 %X Diffusion models lend transformative capabilities to the graph generation task, yet controlling the properties of the generated graphs remains challenging. Recent approaches augment support for controlling soft, differentiable properties but they fail to handle user-specified hard constraints that are non-differentiable. This often results in vague control, unsuitable for applications like drug discovery that demand satisfaction of precise constraints, e.g., the maximum number of bonds. To address this, we formalize the problem of controlled graph generation and introduce PRODIGY (PROjected DIffusion for controlled Graph Generation), an innovative plug-and-play approach enabling the generation of graphs with precise control, from any pre-trained diffusion model. PRODIGY employs a novel operator to project the samples at each diffusion step onto the specified constrained space. For a large class of practical constraints and a variety of graphs, our extensive experiments demonstrate that PRODIGY empowers state-of-the-art continuous and discrete diffusion models to produce graphs meeting specific, hard constraints. Our approach achieves up to 100% constraint satisfaction for non-attributed and molecular graphs, under a variety of constraints, marking a significant step forward in precise, interpretable graph generation. Code is provided on the project webpage: https://prodigy-diffusion.github.io/.
APA
Sharma, K., Kumar, S. & Trivedi, R.. (2024). Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:44545-44564 Available from https://proceedings.mlr.press/v235/sharma24b.html.

Related Material