MING: A Functional Approach to Learning Molecular Generative Models

Van Khoa Nguyen, Maciej Falkiewicz, Giangiacomo Mercatali, Alexandros Kalousis
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:1279-1287, 2025.

Abstract

Traditional molecule generation methods often rely on sequence- or graph-based representations, which can limit their expressive power or require complex permutation-equivariant architectures. This paper introduces a novel paradigm for learning molecule generative models based on functional representations. Specifically, we propose Molecular Implicit Neural Generation (MING), a diffusion-based model that learns molecular distributions in the function space. Unlike standard diffusion processes in the data space, MING employs a novel functional denoising probabilistic process, which jointly denoises information in both the function’s input and output spaces by leveraging an expectation-maximization procedure for latent implicit neural representations of data. This approach enables a simple yet effective model design that accurately captures underlying function distributions. Experimental results on molecule-related datasets demonstrate MING’s superior performance and ability to generate plausible molecular samples, surpassing state-of-the-art data-space methods while offering a more streamlined architecture and significantly faster generation times. The code is available at \url{https://github.com/v18nguye/MING.}

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-nguyen25c, title = {MING: A Functional Approach to Learning Molecular Generative Models}, author = {Nguyen, Van Khoa and Falkiewicz, Maciej and Mercatali, Giangiacomo and Kalousis, Alexandros}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {1279--1287}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/nguyen25c/nguyen25c.pdf}, url = {https://proceedings.mlr.press/v258/nguyen25c.html}, abstract = {Traditional molecule generation methods often rely on sequence- or graph-based representations, which can limit their expressive power or require complex permutation-equivariant architectures. This paper introduces a novel paradigm for learning molecule generative models based on functional representations. Specifically, we propose Molecular Implicit Neural Generation (MING), a diffusion-based model that learns molecular distributions in the function space. Unlike standard diffusion processes in the data space, MING employs a novel functional denoising probabilistic process, which jointly denoises information in both the function’s input and output spaces by leveraging an expectation-maximization procedure for latent implicit neural representations of data. This approach enables a simple yet effective model design that accurately captures underlying function distributions. Experimental results on molecule-related datasets demonstrate MING’s superior performance and ability to generate plausible molecular samples, surpassing state-of-the-art data-space methods while offering a more streamlined architecture and significantly faster generation times. The code is available at \url{https://github.com/v18nguye/MING.}} }
Endnote
%0 Conference Paper %T MING: A Functional Approach to Learning Molecular Generative Models %A Van Khoa Nguyen %A Maciej Falkiewicz %A Giangiacomo Mercatali %A Alexandros Kalousis %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-nguyen25c %I PMLR %P 1279--1287 %U https://proceedings.mlr.press/v258/nguyen25c.html %V 258 %X Traditional molecule generation methods often rely on sequence- or graph-based representations, which can limit their expressive power or require complex permutation-equivariant architectures. This paper introduces a novel paradigm for learning molecule generative models based on functional representations. Specifically, we propose Molecular Implicit Neural Generation (MING), a diffusion-based model that learns molecular distributions in the function space. Unlike standard diffusion processes in the data space, MING employs a novel functional denoising probabilistic process, which jointly denoises information in both the function’s input and output spaces by leveraging an expectation-maximization procedure for latent implicit neural representations of data. This approach enables a simple yet effective model design that accurately captures underlying function distributions. Experimental results on molecule-related datasets demonstrate MING’s superior performance and ability to generate plausible molecular samples, surpassing state-of-the-art data-space methods while offering a more streamlined architecture and significantly faster generation times. The code is available at \url{https://github.com/v18nguye/MING.}
APA
Nguyen, V.K., Falkiewicz, M., Mercatali, G. & Kalousis, A.. (2025). MING: A Functional Approach to Learning Molecular Generative Models. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:1279-1287 Available from https://proceedings.mlr.press/v258/nguyen25c.html.

Related Material