Association Pattern-enhanced Molecular Representation Learning

Authors: Lingxiang Jia, Yuchen Ying, Tian Qiu, Shaolun Yao, Liang Xue, Jie Lei, Jie Song, Mingli Song, Zunlei Feng

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on 11 benchmark molecular property prediction tasks across 8 advanced molecular foundation models demonstrate significant superiority of the proposed method, with performance improvements of up to approximately 20%.
Researcher Affiliation Academia Lingxiang Jia1,2, Yuchen Ying1,2, Tian Qiu1,2, Shaolun Yao1,2, Liang Xue3*, Jie Lei4, Jie Song1,2, Mingli Song1,2, Zunlei Feng1,2* 1State Key Laboratory of Blockchain and Data Security, Zhejiang University 2Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security 3Computing Science and Artificial Intelligence College, Suzhou City University 4College of Computer Science, Zhejiang University of Technology
Pseudocode Yes Algorithm 1: Pattern-Enhanced Finetuning for MFMs
Open Source Code Yes Code & Appendix https://github.com/hry98kki/APMP
Open Datasets Yes To comprehensively evaluate the proposed method on downstream tasks, we conduct experiments on 11 benchmark datasets from Molecule Net (Wu et al. 2018)
Dataset Splits Yes Moreover, we randomly split all the datasets with a ratio for train/validation/test as 8:1:1, and use the best of validation results to select the best model evaluated on the test set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments in the main text.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9) needed to replicate the experiment in the main text.
Experiment Setup No The paper mentions using three different seeds for evaluation and an 8:1:1 train/validation/test split, but it lacks specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) in the main text. It refers to Appendix C.2 for more finetuning details, but these are not provided in the main text.