VALSE 论文速览 第127期：Fractional Denoising for Molecular Pre-training

论文题目：Fractional Denoising for 3D Molecular Pre-training

作者列表：

Shikun Feng (清华大学)，Yuyan Ni (中国科学院)，Yanyan Lan (清华大学)，Zhi-Ming Ma (中国科学院)，Weiying Ma (清华大学)

B站观看网址：

https://www.bilibili.com/video/BV1rh4y1v7Q8/

论文摘要：

Coordinate denoising is a promising 3D molecular pre-training method, which has achieved remarkable performance in various downstream drug discovery tasks. Theoretically, the objective is equivalent to learning the force field, which is revealed helpful for downstream tasks. Nevertheless, there are two challenges for coordinate denoising to learn an effective force field, i.e. low coverage samples and isotropic force field. The underlying reason is that molecular distributions assumed by existing denoising methods fail to capture the anisotropic characteristic of molecules. To tackle these challenges, we propose a novel hybrid noise strategy, including noises on both dihedral angel and coordinate. However, denoising such hybrid noise in a traditional way is no more equivalent to learning the force field. Through theoretical deductions, we find that the problem is caused by the dependency of the input conformation for covariance. To this end, we propose to decouple the two types of noise and design a novel fractional denoising method (Frad), which only denoises the latter coordinate part. In this way, Frad enjoys both the merits of sampling more low-energy structures and the force field equivalence. Extensive experiments show the effectiveness of Frad in molecular representation, with a new state-of-the-art on 9 out of 12 tasks of QM9 and on 7 out of 8 targets of MD17.

论文信息：

[1] Shikun Feng, Yuyan Ni, Yanyan Lan, Zhi-Ming Ma, Weiying Ma, “Fractional Denoising for 3D Molecular Pre-training”. International Conference on Machine Learning (ICML), Hawaii, USA, July 2023.

论文链接：

[https://openreview.net/forum?id=vH6cWEqceA]

代码链接：

[https://github.com/fengshikun/Frad]

视频讲者简介：

Yuyan Ni is currently a Ph.D. student in Academy of Mathematics and Systems Science, Chinese Academy of Sciences and an intern student in Institute for AI Industry Research, Tsinghua University. Before that, she received her bachelor degree at School of Mathematical Sciences, University of Chinese Academy of Sciences in 2021. Her research interests include deep learning theory and AI for sciences.

特别鸣谢本次论文速览主要组织者：

月度轮值AC：王啸 (北京航空航天大学)