arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.09161cs.LG
收藏

基于约束的图网络模拟器

Constraint-based graph network simulator

DeepMind

Yulia Rubanova, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Peter Battaglia

摘要:

在物理模拟领域,几乎所有基于神经网络的方法都直接从输入状态预测未来状态。然而,许多传统的仿真引擎,而不是模拟系统的约束条件,并选择满足它们的状态。在这里,我们提出了一个框架,基于约束的学习模拟,其中一个标量约束函数实现为图神经网络,未来的预测计算通过解决的优化问题所定义的学习约束。我们的模型在各种具有挑战性的物理领域上达到了与顶级学习模拟器相当或更好的准确性,并提供了几个独特的优势。我们可以通过在测试时应用更多的求解器迭代来提高更大系统的模拟精度。我们还可以在测试时加入新的手工设计的约束,并模拟训练数据中不存在的新动力学。我们的基于约束的框架显示了如何从传统的模拟和数值方法的关键技术,可以利用作为归纳偏见的机器学习模拟器。

英文摘要:

In the area of physical simulations, nearly all neural-network-based methods directly predict future states from the input states. However, many traditional simulation engines instead model the constraints of the system and select the state which satisfies them. Here we present a framework for constraint-based learned simulation, where a scalar constraint function is implemented as a graph neural network, and future predictions are computed by solving the optimization problem defined by the learned constraint. Our model achieves comparable or better accuracy to top learned simulators on a variety of challenging physical domains, and offers several unique advantages. We can improve the simulation accuracy on a larger system by applying more solver iterations at test time. We also can incorporate novel hand-designed constraints at test time and simulate new dynamics which were not present in the training data. Our constraint-based framework shows how key techniques from traditional simulation and numerical methods can be leveraged as inductive biases in machine learning simulators.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑