Data to 7 Oct 2026

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation

arXiv 1806.02473 ↗First posted 7 Jun 2018cs.LG cs.AI stat.MLcited by 363

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generating novel graph structures that optimize given objectives while obeying some given underlying rules is fundamental for chemistry, biology and social science research. This is especially important in the task of molecular graph generation, whose goal is to discover novel molecules with desired properties such as drug-likeness and synthetic accessibility, while obeying physical laws such as chemical valency. However, designing models to find molecules that optimize desired properties while incorporating highly complex and non-differentiable rules remains to be a challenging task. Here we propose Graph Convolutional Policy Network (GCPN), a general graph convolutional network based model for goal-directed graph generation through reinforcement learning. The model is trained to optimize domain-specific rewards and adversarial loss through policy gradient, and acts in an environment that incorporates domain-specific rules. Experimental results show that GCPN can achieve 61% improvement on chemical property optimization over state-of-the-art baselines while resembling known molecules, and achieve 184% improvement on the constrained property optimization task.

Key facts. Cited by 363 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 72; 2022: 82; 2023: 71; 2024: 54; 2025: 41; 2026: 42.

363 papers.

Sort:

By area:

2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
2021Identity-aware Graph Neural Networkscited by 197
2022Graph neural networks for materials science and chemistrycited by 181
2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
2022A 3D Generative Model for Structure-Based Drug Designcited by 148

38 more

2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
2021Geometric Deep Learning on Molecular Representationscited by 113
2021Deep Generative Models in Engineering Design: A Reviewcited by 103
2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
2022SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generatorscited by 96
2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
2022Physics-Informed Machine Learning: A Survey on Problems, Methods and Applicationscited by 88
2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
2023Autoregressive Diffusion Model for Graph Generationcited by 82
2021Graph Representation Learning in Biomedicinecited by 79
2022Local Latent Space Bayesian Optimization over Structured Inputscited by 78
2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 70
2023GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learningcited by 70
2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
2021Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generationcited by 68
2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 65
2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
2021Few-shot Network Anomaly Detection via Cross-network Meta-learningcited by 64
2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 63
2021A Review of Graph Neural Networks and Their Applications in Power Systemscited by 62
2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB filescited by 59
2021Graph Coarsening with Neural Networkscited by 55
2022Boosting the Cycle Counting Power of Graph Neural Networks with I2-GNNscited by 55
2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 53
2022Regression Transformer: Concurrent sequence regression and generation for molecular language modelingcited by 49
2023Sample-efficient Multi-objective Molecular Optimization with GFlowNetscited by 48
2023Demystifying Oversmoothing in Attention-Based Graph Neural Networkscited by 47
2022Reinforced Genetic Algorithm for Structure-based Drug Designcited by 46

50 most cited of 363 All 363 (JSON)