paper-with-me

홈 › Papers

Network scaling and scale-driven loss balancing for intelligent poroelastography

2024-10-27 · Yang Xu, Fatemeh Pourahmadian

A deep learning framework is developed for multiscale characterization of poroelastic media from full waveform data which is known as poroelastography. Special attention is paid to heterogeneous environments whose multiphase properties may drastically change across several scales. Described in space-frequency, the data takes the form of focal solid displacement and pore pressure fields in various neighborhoods furnished either by reconstruction from remote data or direct measurements depending on the application. The objective is to simultaneously recover the six hydromechanical properties germane to Biot equations and their spatial distribution in a robust and efficient manner. Two major challenges impede direct application of existing state-of-the-art techniques for this purpose: (i) the sought-for properties belong to vastly different and potentially uncertain scales, and~(ii) the loss function is multi-objective and multi-scale (both in terms of its individual components and the total loss). To help bridge the gap, we propose the idea of \emph{network scaling} where the neural property maps are constructed by unit shape functions composed into a scaling layer. In this model, the unknown network parameters (weights and biases) remain of O(1) during training. This forms the basis for explicit scaling of the loss components and their derivatives with respect to the network parameters. Thereby, we propose the physics-based \emph{dynamic scaling} approach for adaptive loss balancing. The idea is first presented in a generic form for multi-physics and multi-scale PDE systems, and then applied through a set of numerical experiments to poroelastography. The results are presented along with reconstructions by way of gradient normalization (GradNorm) and Softmax adaptive weights (SoftAdapt) for loss balancing. A comparative analysis of the methods and corresponding results is provided.

📄 PDF Abstract BibTeX arXiv:2411.08886

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Gradient Normalization 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adaptive Loss 설명 없음

Similar Papers 제목 키워드 기반

Multi-Objective Loss Balancing for Physics-Informed Deep Learning

2021-10-19 · Rafael Bischof, Michael Kraus

Physics-Informed Neural Networks (PINN) are algorithms from deep learning leveraging physical laws by including partial differential equations together with a respective set of boundary and initial conditions as penalty …

Deep LearningPhysics-informed machine learning

A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models

2025-12-03 · X. Y. Han, Yuan Zhong arxiv

In large-scale AI training, Sparse Mixture-of-Experts (s-MoE) layers enable scaling by activating only a small subset of experts per token. An operational challenge in this design is load balancing: routing tokens to min…

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks

2026-05-29 · Tianyu Pang, Vignesh Kothapalli, Shenyang Deng, Haohui Wang 외 arxiv

We study optimal learning-rate selection in two-layer and three-layer linear neural networks trained to learn linear target functions. In particular, we derive the exact closed-form expressions for the gradients and test…

Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies

2022-11-22 · Anish Lakkapragada, Essam Sleiman, Saimourya Surabhi, Dennis P. Wall

Multi-Task Learning (MTL) is a growing subject of interest in deep learning, due to its ability to train models more efficiently on multiple tasks compared to using a group of conventional single-task models. However, MT…

Multi-Task Learning

The Race to Efficiency: A New Perspective on AI Scaling Laws

2025-01-04 · Chien-Ping Lu

As large-scale AI models expand, training becomes costlier and sustaining progress grows harder. Classical scaling laws (e.g., Kaplan et al. (2020), Hoffmann et al. (2022)) predict training loss from a static compute bud…

GPU