Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Zehong, Han, Xiaolong, Yang, Qi, Tang, Xiangru, Wu, Fang, Guo, Xiaoguang, Sun, Weixiang, Ma, Tianyi, Lio, Pietro, Cong, Le, Wang, Sheng, Zhang, Chuxu, Ye, Yanfang
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.22327
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911408606674944
author Wang, Zehong
Han, Xiaolong
Yang, Qi
Tang, Xiangru
Wu, Fang
Guo, Xiaoguang
Sun, Weixiang
Ma, Tianyi
Lio, Pietro
Cong, Le
Wang, Sheng
Zhang, Chuxu
Ye, Yanfang
author_facet Wang, Zehong
Han, Xiaolong
Yang, Qi
Tang, Xiangru
Wu, Fang
Guo, Xiaoguang
Sun, Weixiang
Ma, Tianyi
Lio, Pietro
Cong, Le
Wang, Sheng
Zhang, Chuxu
Ye, Yanfang
contents Molecular representations fundamentally shape how machine learning systems reason about molecular structure and physical properties. Most existing approaches adopt a discrete pipeline: molecules are encoded as sequences, graphs, or point clouds, mapped to fixed-dimensional embeddings, and then used for task-specific prediction. This paradigm treats molecules as discrete objects, despite their intrinsically continuous and field-like physical nature. We argue that molecular learning can instead be formulated as learning in function space. Specifically, we model each molecule as a continuous function over three-dimensional (3D) space and treat this molecular field as the primary object of representation. From this perspective, conventional molecular representations arise as particular sampling schemes of an underlying continuous object. We instantiate this formulation with MolField, a hyper-network-based framework that learns distributions over molecular fields. To ensure physical consistency, these functions are defined over canonicalized coordinates, yielding invariance to global SE(3) transformations. To enable learning directly over functions, we introduce a structured weight tokenization and train a sequence-based hyper-network to model a shared prior over molecular fields. We evaluate MolField on molecular dynamics and property prediction. Our results show that treating molecules as continuous functions fundamentally changes how molecular representations generalize across tasks and yields downstream behavior that is stable to how molecules are discretized or queried.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22327
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Molecular Representations in Implicit Functional Space via Hyper-Networks
Wang, Zehong
Han, Xiaolong
Yang, Qi
Tang, Xiangru
Wu, Fang
Guo, Xiaoguang
Sun, Weixiang
Ma, Tianyi
Lio, Pietro
Cong, Le
Wang, Sheng
Zhang, Chuxu
Ye, Yanfang
Machine Learning
Molecular representations fundamentally shape how machine learning systems reason about molecular structure and physical properties. Most existing approaches adopt a discrete pipeline: molecules are encoded as sequences, graphs, or point clouds, mapped to fixed-dimensional embeddings, and then used for task-specific prediction. This paradigm treats molecules as discrete objects, despite their intrinsically continuous and field-like physical nature. We argue that molecular learning can instead be formulated as learning in function space. Specifically, we model each molecule as a continuous function over three-dimensional (3D) space and treat this molecular field as the primary object of representation. From this perspective, conventional molecular representations arise as particular sampling schemes of an underlying continuous object. We instantiate this formulation with MolField, a hyper-network-based framework that learns distributions over molecular fields. To ensure physical consistency, these functions are defined over canonicalized coordinates, yielding invariance to global SE(3) transformations. To enable learning directly over functions, we introduce a structured weight tokenization and train a sequence-based hyper-network to model a shared prior over molecular fields. We evaluate MolField on molecular dynamics and property prediction. Our results show that treating molecules as continuous functions fundamentally changes how molecular representations generalize across tasks and yields downstream behavior that is stable to how molecules are discretized or queried.
title Molecular Representations in Implicit Functional Space via Hyper-Networks
topic Machine Learning
url https://arxiv.org/abs/2601.22327