Saved in:
Bibliographic Details
Main Authors: Nguyen, Van Khoa, Falkiewicz, Maciej, Mercatali, Giangiacomo, Kalousis, Alexandros
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.12522
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916616342601728
author Nguyen, Van Khoa
Falkiewicz, Maciej
Mercatali, Giangiacomo
Kalousis, Alexandros
author_facet Nguyen, Van Khoa
Falkiewicz, Maciej
Mercatali, Giangiacomo
Kalousis, Alexandros
contents 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 https://github.com/v18nguye/MING.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12522
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MING: A Functional Approach to Learning Molecular Generative Models
Nguyen, Van Khoa
Falkiewicz, Maciej
Mercatali, Giangiacomo
Kalousis, Alexandros
Machine Learning
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 https://github.com/v18nguye/MING.
title MING: A Functional Approach to Learning Molecular Generative Models
topic Machine Learning
url https://arxiv.org/abs/2410.12522