物理集成生成建模：基于注意力平面归一化流变分自编码器
Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder
AI总结：
本研究提出一种物理集成变分自编码器，利用平面归一化流学习后验分布，并在编码器中引入缩放点积注意力以增强对噪声的鲁棒性，实验表明其提升了重建质量与抗噪能力。
摘要：
物理集成生成建模是一类混合或灰盒建模方法，其中我们用控制数据分布的物理知识来增强数据驱动模型。使用物理知识使得生成模型能够以受控方式产生输出，从而保证输出在构造上符合物理定律。这赋予了模型超越训练分布进行外推的改进泛化能力，同时由于模型部分基于坚实的领域知识，其可解释性也得到提升。在本工作中，我们旨在提高物理集成生成模型中重建的保真度以及对噪声的鲁棒性。为此，我们使用变分自编码器作为生成模型。为了改进解码器的重建结果，我们提出使用平面归一化流来学习物理组件和可训练数据驱动组件的潜在后验分布。基于归一化流的后验分布利用了数据分布固有的动态结构，因此学习到的模型更接近真实潜在数据分布。为了提高生成模型对注入噪声的鲁棒性，我们提出了对基于归一化流的VAE编码器部分的修改。我们设计编码器将基于缩放点积注意力的上下文信息纳入含噪潜在向量中，这将减轻噪声对潜在向量的不利影响，使模型更加鲁棒。我们在人体运动数据集[33]上进行了实证评估，结果验证了我们提出的模型在重建质量改进和对注入噪声鲁棒性方面的有效性。
英文摘要：
Physics-integrated generative modeling is a class of hybrid or grey-box modeling in which we augment the the data-driven model with the physics knowledge governing the data distribution. The use of physics knowledge allows the generative model to produce output in a controlled way, so that the output, by construction, complies with the physical laws. It imparts improved generalization ability to extrapolate beyond the training distribution as well as improved interpretability because the model is partly grounded in firm domain knowledge. In this work, we aim to improve the fidelity of reconstruction and robustness to noise in the physics integrated generative model. To this end, we use variational-autoencoder as a generative model. To improve the reconstruction results of the decoder, we propose to learn the latent posterior distribution of both the physics as well as the trainable data-driven components using planar normalizng flow. Normalizng flow based posterior distribution harnesses the inherent dynamical structure of the data distribution, hence the learned model gets closer to the true underlying data distribution. To improve the robustness of generative model against noise injected in the model, we propose a modification in the encoder part of the normalizing flow based VAE. We designed the encoder to incorporate scaled dot product attention based contextual information in the noisy latent vector which will mitigate the adverse effect of noise in the latent vector and make the model more robust. We empirically evaluated our models on human locomotion dataset [33] and the results validate the efficacy of our proposed models in terms of improvement in reconstruction quality as well as robustness against noise injected in the model.
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。
