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

2026-02-18

AI Summary

This work addresses the challenge that purely deep neural approaches to molecular graph generation often fail to guarantee chemical validity and hard user-specified constraints. To overcome this limitation, the authors propose the Neural-Symbolic Graph Generation Model (NSGGM), which decouples the generation process into two stages: a neural network autoregressively proposes candidate structures, and an SMT solver symbolically assembles them under explicit logical constraints. This framework achieves the first deep integration of neural proposal mechanisms with symbolic reasoning, ensuring that chemical rules and complex logical constraints are strictly satisfied during construction—realizing “correct-by-construction” verifiable generation. Experiments demonstrate that NSGGM achieves state-of-the-art performance in both unconstrained and constrained settings. Furthermore, the authors introduce the first benchmark dataset for logic-constrained molecular generation, empirically validating the model’s controllability and compliance with domain-specific constraints.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• molecule generation
• graph generation
• controllability
• formal guarantees
• hard constraints

Innovation

• Neuro-Symbolic
• Graph Generation
• Hard Constraints
• SMT Solver
• Molecular Design