Neural networks, especially the recent proposed neural operator models, are increasingly being used to find the solution operator of differential equations. Compared to traditional numerical solvers, they are much faster and more efficient in practical applications. However, one critical issue is that training neural operator models require large amount of ground truth data, which usually comes from the slow numerical solvers. In this paper, we propose a physics-guided data augmentation (PGDA) method to improve the accuracy and generalization of neural operator models. Training data is augmented naturally through the physical properties of differential equations such as linearity and translation. We demonstrate the advantage of PGDA on a variety of linear differential equations, showing that PGDA can improve the sample complexity and is robust to distributional shift.
Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation
University of Science and Technology of China(科学技术大学);Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学);Beijing Jiaotong University(北京交通大学);Tencent(腾讯)
Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning
Department of Mechanical and Process Engineering, ETH Zurich, Switzerland(瑞士苏黎世联邦理工学院机械与过程工程系);ETH AI Center, ETH Zurich, Switzerland(瑞士苏黎世联邦理工学院人工智能中心);Department of Computer Science, ETH Zurich, Switzerland(瑞士苏黎世联邦理工学院计算机科学系)
Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering
College of Information Science and Technology, Beijing University of Chemical Technology(北京化工大学信息科学与技术学院);Beijing University of Technology(北京工业大学);The University of Sydney Business School, The University of Sydney(悉尼大学商学院)
Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection
School of Internet, Anhui University(安徽大学互联网学院);School of Computer Science and Technology, Hefei University of Technology(合肥工业大学计算机科学与技术学院);School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机科学与信息工程学院)
ToxiGAN: Toxic Data Augmentation via LLM-Guided Directional Adversarial Generation
Freie Universität Berlin(弗里德里希-莱布尼茨柏林大学);Fraunhofer-Institut für Offene Kommunikationssysteme(弗劳恩霍夫开放通信系统研究所);Institut für Angewandte Informatik(应用信息研究所);Stanford University(斯坦福大学)
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
University of Science Technology of China(中国科学技术大学);University of Maryland College Park(马里兰大学帕克分校);JD Explore Academy(京东探索研究院);The University of Sydney(悉尼大学)
Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models
XITASO GmbH(XITASO 有限公司);Zuse School of Excellence in Reliable AI(Zuse 卓越可靠人工智能学院);Technische Hochschule Ingolstadt(因戈尔施塔特应用技术大学);Technische Hochschule Augsburg(奥格斯堡应用技术大学)
MS-Mix: Sentiment-Guided Adaptive Augmentation for Multimodal Sentiment Analysis
Chongqing Institute of Green Intelligent Technology, Chinese Academy of Sciences(中国科学院重庆绿色智能技术研究院);Chongqing School, University of Chinese Academy of Sciences(中国科学院大学重庆学院);School of Engineering, Westlake University(西湖大学工学院)
Prior-Guided Frequency-Calibrated Virtual EEG Channel Inference from Four Frontal Electrodes for Wearable EEG Augmentation
School of Biomedical Science and Engineering, South China University of Technology(生物医学工程学院,华南理工大学);School of Automation Science and Engineering, South China University of Technology(自动化科学与工程学院,华南理工大学)
Outlier-aware Tensor Robust Principal Component Analysis with Self-guided Data Augmentation
School of Mathematics and Statistics, Hunan Normal University(湖南师范大学数学与统计学学院);School of Statistics and Mathematics, Yunnan University of Finance and Economics(云南财经大学统计与数学学院)
The University of Sydney(悉尼大学);SenseTime Research(商汤科技研究院);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学)
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
Beihang University(北京航空航天大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Leicester(莱斯特大学);Nanyang Technological University(南洋理工大学)
Mask-guided Data Augmentation for Multiparametric MRI Generation with a Rare Hepatocellular Carcinoma
Universidad Industrial de Santander(桑坦德工业大学);University of Toulouse(图卢兹大学);Université Paul Sabatier Toulouse 3(图卢兹第三大学(保罗·萨巴蒂埃大学));Bicêtre University Hospital(比塞特尔大学医院);Assistance publique des hôpitaux de Paris(巴黎公共援助医院);Université Claude Bernard Lyon 1(里昂第一大学(克洛德·贝尔纳里昂第一大学))
Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction
Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University(湖南生物信息省重点实验室,计算机科学与工程学院,中南大学);Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University(新疆大数据与智能软件工程研究中心,软件学院,新疆大学);School of Science and Engineering, University of Dundee(科学与工程学院,邓迪大学);Department of Neurology, Xiangya Hospital, Central South University(神经内科,湘雅医院,中南大学)
On the Impact of Interpretability Methods in Active Image Augmentation Method
Centro de Informática(信息中心);Universidade Federal de Pernambuco(伯南布哥联邦大学);Departamento de Ciência da Computação(计算机科学系);Universidade Federal de Sergipe(塞尔希培联邦大学);Informatics Department(信息学系);University of Minho(米尼奥大学)