paper-with-me

홈 › Papers

Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks

2025-06-19 · Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker, Galip Ümit Yolcu, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek, René P. Klausen

Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to both forward and inverse problems across various scientific domains, PINNs have recently emerged as a valuable tool in the field of scientific machine learning. A key aspect of their training is that the data -- spatio-temporal points sampled from the PDE's input domain -- are readily available. Influence functions, a tool from the field of explainable AI (XAI), approximate the effect of individual training points on the model, enhancing interpretability. In the present work, we explore the application of influence function-based sampling approaches for the training data. Our results indicate that such targeted resampling based on data attribution methods has the potential to enhance prediction accuracy in physics-informed neural networks, demonstrating a practical application of an XAI method in PINN training.

📄 PDF Abstract BibTeX arXiv:2506.16443

Code (1)

aleks-krasowski/pinnfluence_resampling 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Resolving Training Biases via Influence-based Data Relabeling

2021-09-29 · ICLR 2022 4 · Shuming Kong, Yanyan Shen, Linpeng Huang

The performance of supervised learning methods easily suffers from the training bias issue caused by train-test distribution mismatch or label noise. Influence function is a technique that estimates the impacts of a tra…

Differentiable Particle Filtering via Entropy-Regularized Optimal Transport

2021-02-15 · Adrien Corenflos, James Thornton, George Deligiannidis, Arnaud Doucet

Particle Filtering (PF) methods are an established class of procedures for performing inference in non-linear state-space models. Resampling is a key ingredient of PF, necessary to obtain low variance likelihood and stat…

State Space ModelsVariational Inference

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks

2023-10-18 · Yue Cao, Tianlin Li, Xiaofeng Cao, Ivor Tsang 외

We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified…

Adversarial Robustness

PINNfluence: Influence Functions for Physics-Informed Neural Networks

2024-09-13 · Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker, Thomas Wiegand 외

Recently, physics-informed neural networks (PINNs) have emerged as a flexible and promising application of deep learning to partial differential equations in the physical sciences. While offering strong performance and c…

Influence of Resampling on Accuracy of Imbalanced Classification

2017-07-12 · Evgeny Burnaev, Pavel Erofeev, Artem Papanov

In many real-world binary classification tasks (e.g. detection of certain objects from images), an available dataset is imbalanced, i.e., it has much less representatives of a one class (a minor class), than of another. …

Binary ClassificationClassificationGeneral Classificationimbalanced classification