# Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction

arXiv: https://arxiv.org/abs/1712.02734 · HTML: https://mlsanity.com/paper/1712.02734/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2017.

## Built on by (most cited first, 12 of 12)

- [Property-Aware Relation Networks for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2107.07994/) (2021)
- [End-to-End Weak Supervision](https://mlsanity.com/paper/2107.02233/) (2021)
- [Assigning Confidence to Molecular Property Prediction](https://mlsanity.com/paper/2102.11439/) (2021)
- [DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling](https://mlsanity.com/paper/2305.19395/) (2023)
- [Self-Training with Differentiable Teacher](https://mlsanity.com/paper/2109.07049/) (2021)
- [Interactive Molecular Discovery with Natural Language](https://mlsanity.com/paper/2306.11976/) (2023)
- [Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement](https://mlsanity.com/paper/2505.19675/) (2025)
- [Improving VAE based molecular representations for compound property prediction](https://mlsanity.com/paper/2201.04929/) (2022)
- [Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?](https://mlsanity.com/paper/2506.10912/) (2025)
- [Improving Compound Activity Classification via Deep Transfer and Representation Learning](https://mlsanity.com/paper/2111.07439/) (2021)
- [Integrated Weak Learning](https://mlsanity.com/paper/2206.09496/) (2022)
- [Exploring the Role of Artificial Intelligence and Machine Learning in Process Optimization for Chemical Industry](https://mlsanity.com/paper/2502.15768/) (2025)

## Abstract (arXiv)

With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks. However, in chemistry, data is inherently small and fragmented. In this work, we develop an approach of using rule-based knowledge for training ChemNet, a transferable and generalizable deep neural network for chemical property prediction that learns in a weak-supervised manner from large unlabeled chemical databases. When coupled with transfer learning approaches to predict other smaller datasets for chemical properties that it was not originally trained on, we show that ChemNet's accuracy outperforms contemporary DNN models that were trained using conventional supervised learning. Furthermore, we demonstrate that the ChemNet pre-training approach is equally effective on both CNN (Chemception) and RNN (SMILES2vec) models, indicating that this approach is network architecture agnostic and is effective across multiple data modalities. Our results indicate a pre-trained ChemNet that incorporates chemistry domain knowledge, enables the development of generalizable neural networks for more accurate prediction of novel chemical properties.