Molecular Representations in Implicit Functional Space via Hyper-Networks

TL;DR

This paper proposes a novel approach to molecular representation by modeling molecules as continuous functions in 3D space using hyper-networks, enabling more generalizable and physically consistent molecular learning.

Contribution

It introduces MolField, a hyper-network framework that learns distributions over molecular fields, shifting from discrete to continuous function-based molecular representations.

Findings

Improved generalization across molecular tasks.

Stable representations regardless of discretization or querying methods.

Enhanced physical consistency in molecular modeling.

Abstract

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.