# Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics

Source: [Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics](<https://www.sota2.com/research/paper/68fa6b971e209131cea2f1b0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:52:06.013Z

Authors: Chunheng Jiang, Tejaswini Pedapati, Pin-Yu Chen, Yizhou Sun, Jianxi Gao

Published: 2022-01-11T20:53:15.000Z

## Abstract

Efficient model selection for identifying a suitable pre-trained neural network to a downstream task is a fundamental yet challenging task in deep learning. Current practice requires expensive computational costs in model training for performance prediction. In this paper, we propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training. Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections. Therefore, a converged neural network is associated with an equilibrium state of a networked system composed of those edges. To this end, we construct a network mapping $\\phi$, converting a neural network $G\_A$ to a directed line graph $G\_B$ that is defined on those edges in $G\_A$. Next, we derive a neural capacitance metric $\\beta\_{\\rm eff}$ as a predictive measure universally capturing the generalization capability of $G\_A$ on the downstream task using only a handful of early training results. We carried out extensive experiments using 17 popular pre-trained ImageNet models and five benchmark datasets, including CIFAR10, CIFAR100, SVHN, Fashion MNIST and Birds, to evaluate the fine-tuning performance of our framework. Our neural capacitance metric is shown to be a powerful indicator for model selection based only on early training results and is more efficient than state-of-the-art methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2201.04194>)

[PDF](<https://arxiv.org/pdf/2201.04194.pdf>)
