Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints

TL;DR

This paper presents NSGGM, a neuro-symbolic framework for molecule and graph generation that combines neural scaffold proposals with symbolic constraints, ensuring validity, interpretability, and control.

Contribution

The paper introduces a novel neuro-symbolic approach that integrates neural scaffold learning with symbolic constraint solving for graph generation, providing formal guarantees and controllability.

Findings

NSGGM achieves state-of-the-art performance in molecule generation.

It enforces chemical validity and user constraints through symbolic reasoning.

The framework offers interpretable control over generated graphs.

Abstract

We challenge black-box purely deep neural approaches for molecules and graph generation, which are limited in controllability and lack formal guarantees. We introduce Neuro-Symbolic Graph Generative Modeling (NSGGM), a neurosymbolic framework that reapproaches molecule generation as a scaffold and interaction learning task with symbolic assembly. An autoregressive neural model proposes scaffolds and refines interaction signals, and a CPU-efficient SMT solver constructs full graphs while enforcing chemical validity, structural rules, and user-specific constraints, yielding molecules that are correct by construction and interpretable control that pure neural methods cannot provide. NSGGM delivers strong performance on both unconstrained generation and constrained generation tasks, demonstrating that neuro-symbolic modeling can match state-of-the-art generative performance while offering explicit controllability and guarantees. To evaluate more nuanced controllability, we also introduce a Logical-Constraint Molecular Benchmark, designed to test strict hard-rule satisfaction in workflows that require explicit, interpretable specifications together with verifiable compliance.