Research map / Learning theory and algorithms / Combinatorial and search optimization
Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add a neural-network discriminator to the GA fitness | GA · Penalized logP optimization | Max. Penalized logP: 12.61± 0.81 -> 13.31±0.63 | Helped |
| Add a time-dependent adaptive discriminator penalty during saturation (ablation) | GA + D · Penalized logP optimization | Max. Penalized logP: 13.31±0.63 -> 20.72\pm3.14 | Helped |
| Remove the discriminator (β=0) (ablation) | GA + D · Penalized logP optimization | Max. Penalized logP: 13.31±0.63 -> 12.61± 0.81 | Hurt |
| Use the GA for similarity-constrained optimization | Molecular optimization · Constrained penalized logP improvement (δ=0.4) | Improvement: 3.55 \pm 1.67 -> 5.93 \pm 1.41 | Helped |
| Use the GA for similarity-constrained optimization | Molecular optimization · Constrained penalized logP improvement (δ=0.6) | Improvement: 2.33 \pm 1.17 -> 3.44 \pm 1.09 | Helped |
| Increase β to favor resemblance to the reference data distribution (ablation) | GA + D · Penalized logP optimization | Average J(m) | Hurt |
| Vary β to intermediate values around 18–20 (ablation) | GA + D · Penalized logP optimization | J(m) distribution: approximately 12-13 | Mixed |
Closest papers by meaning
- Neural Genetic Search in Discrete Spaces (ICML 2025 · similarity 0.85)
- Molecule Design by Latent Prompt Transformer (NeurIPS 2024 · similarity 0.85)
- Efficient Evolutionary Search Over Chemical Space with Large Language Models (ICLR 2025 · similarity 0.85)
- Molecular Optimization Model with Patentability Constraint (AAAI 2024 · similarity 0.85)
- Navigating Chemical Space with Latent Flows (NeurIPS 2024 · similarity 0.84)
- Genetic-guided GFlowNets for Sample Efficient Molecular Optimization (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.