Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation

Authors: Can Xu, Haosen Wang, Weigang Wang, Pengfei Zheng, Hongyang Chen

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments on current benchmarks demonstrate the superiority of GFMDiff.
Researcher Affiliation Collaboration Can Xu1,2* , Haosen Wang3,2*, Weigang Wang1 , Pengfei Zheng2, Hongyang Chen2 1Zhejiang Gongshang University 2Zhejiang Lab 3Southeast University leoxc1571@163.com, haosenwang@seu.edu.cn, wangweigang@zjgsu.edu.cn, zpf2021@zhejianglab.com, dr.h.chen@ieee.org
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not explicitly state that source code for the methodology is provided or include a link to a repository.
Open Datasets Yes we conduct experiments on two benchmark datasets in molecule generation: GEOM-QM9 (Ramakrishnan et al. 2014) and GEOM-Drugs (Axelrod and Gomez-Bombarelli 2022).
Dataset Splits No The paper mentions 'train', 'validation', and 'test' in general terms for experimental phases but does not provide specific percentages, sample counts, or explicit details about how the datasets were split for training, validation, and testing to enable reproduction.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers required to replicate the experiments.
Experiment Setup Yes On QM9, GFMDiff is trained for around 1000 epochs, with a five layer DTN and the embedding size of 256. ... The weight for GFLoss λ is set 0.01.