添加小编微信GNN4AI: 加入会议的讨论群，目前已经满200人 报告嘉宾：付襄 @ MIT CSAIL 报告题目Simulate
Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine
Learning 报告摘要Molecular
dynamics (MD) simulation is the workhorse of various scientific domains but is
limited by high computational cost. Learning-based force fields have made major
progress in accelerating ab-initio MD simulation but are still not fast enough
for many real-world applications that require long-time MD simulation. In this
paper, we adopt a different machine learning approach where we coarse-grain a
physical system using graph clustering, and model the system evolution with a
very large time-integration step using graph neural networks. A novel
score-based GNN refinement module resolves the long-standing challenge of
long-time simulation instability. Despite only trained with short MD trajectory
data, our learned simulator can generalize to unseen novel systems and simulate
for much longer than the training trajectories. Properties requiring 10-100 ns
level long-time dynamics can be accurately recovered at
several-orders-of-magnitude higher speed than classical force fields. We
demonstrate the effectiveness of our method on two realistic complex systems:
(1) single-chain coarse-grained polymers in implicit solvent; (2)
multi-component Li-ion polymer electrolyte systems. 报告人简介 Xiang Fu is a third-year PhD student
in computer science at MIT, working with Tommi Jaakkola and Pulkit Agrawal. His
is interested in learning dynamical models and generative models. His past
projects include learning to simulate coarse-grained molecular dynamics,
crystal generative models, molecule design, and reinforcement learning. His
research aims to develop principled and novel methodology for ML
simulator/generative models, with application in inverse design of materials
and drugs. 参考文献1.Simulate Time-integrated
Coarse-grained Molecular Dynamics with Geometric Machine Learning. arXiv
preprint (2022).2.Accelerating amorphous polymer
electrolyte screening by learning to reduce errors in molecular dynamics
simulated properties. Nature communications (2022).3.Targeted sequence design within the
coarse-grained polymer genome. Science advances (2022).
