Adaptive Loss Weighting

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning
Apr 17, 2026Reza PirayeshshirazinezhadSelf-Supervised Learning Adaptive Loss Weighting
Texas A&M University College Station, TX, USA
Training Flow Matching: The Role of Weighting and Parameterization
Mar 6, 2026Anne Gagneux, Ségolène Martin, Rémi Gribonval +1Flow Matching Adaptive Loss Weighting
ENS de Lyon, CNRS, Universit´e Claude Bernard Lyon 1, Inria, LIP, UMR 5668, France · Technische Universität Berlin, Germany · Inria, ENS de Lyon, CNRS, Universit´e Claude Bernard Lyon 1, LIP, UMR 5668, France
LAW & ORDER: Adaptive Spatial Weighting for Medical Diffusion and Segmentation
Mar 5, 2026Anugunj Naman, Ayushman Singh, Gaibo Zhang +1Image Segmentation Healthcare
Elmore Family School of Electrical and Computer Engineering Purdue University, West Lafayette, USA · Sesame AI, New York, USA · Department of Computer Science Purdue University, West Lafayette, USA +1
Uncovering Cross-Objective Interference in Multi-Objective Alignment
Feb 6, 2026Yining Lu, Meng JiangAdaptive Loss Weighting Multi-Objective Language Model Alignment
University of Notre Dame
Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
Oct 28, 2025Hao Wang, Licheng Pan, Yuan Lu +7Time Series Forecasting Adaptive Loss Weighting
Xiaohongshu Inc. · State Key Lab of General AI, School of Intelligence Science and Technology, Peking University · College of Engineering, Purdue University +6
iCost: A Novel Instance-Complexity-Based Cost-Sensitive Learning Framework
Sep 19, 2024Asif Newaz, Asif Ur Rahman Adib, Taskeed JabidClass-Imbalanced Learning Cost-Sensitive Learning
Department of Electrical and Electronic Engineering, Islamic University of Technology (IUT), Gazipur, Bangladesh · Department of Electrical and Electronic Engineering, Ahsanullah University of Science and Technology (AUST), Dhaka, Bangladesh · Department of Computer Science and Engineering, East West University, Dhaka, Bangladesh

Apr 17, 2026, cs.LGJ/K move · Enter open · S save

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning

Reza Pirayeshshirazinezhad

Texas A&M University College Station, TX, USA

Self-Supervised Learning Adaptive Loss Weighting Scientific ML Physics-Informed ML

Open paper AskPDF arXiv

We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine learning under data scarcity. Unlike prior PINNs that rely on fixed or heuristic weighting of physics residuals and data loss, our approach introduces a learnable blending neuron that dynamically adjusts the relative contribution of each term based on their uncertainties. This mechanism enables stable training and improved generalization without manual tuning. To further enhance efficiency, we integrate a transfer learning strategy that reuses representations from related domains and adapts them to new physical systems with limited data. We validate the framework for the prediction of heat transfer in liquid-metal miniature heat sinks using only 87 CFD datapoints, where the adaptive PINN achieves an error <8%, outperforming shallow neural networks, kernel methods, and physics-only baselines. Our framework provides a general recipe for embedding physics adaptively into neural networks, offering a robust and reproducible approach for data-scarce problems across various scientific domains, including fluid dynamics and material modeling.

Momentum

Related topics

Latest papers 66

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning

Training Flow Matching: The Role of Weighting and Parameterization

LAW & ORDER: Adaptive Spatial Weighting for Medical Diffusion and Segmentation

Uncovering Cross-Objective Interference in Multi-Objective Alignment

Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

iCost: A Novel Instance-Complexity-Based Cost-Sensitive Learning Framework