# Is network fragmentation a useful complexity measure?

Source: [Is network fragmentation a useful complexity measure?](<https://www.sota2.com/research/paper/68fa759f1e209131cea69043>)

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

Data updated: 2025-10-26T03:38:44.922Z

Authors: Coenraad Mouton, Randle Rabe, Dani\\"el G. Haasbroek, Marthinus W. Theunissen, Hermanus L. Potgieter, Marelie H. Davel

Published: 2024-11-07T13:27:37.000Z

## Abstract

It has been observed that the input space of deep neural network classifiers can exhibit \`fragmentation', where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the double descent curve, achieving a maximum at the interpolation regime. We study this phenomenon in the context of image classification and ask whether fragmentation could be predictive of generalization performance. Using a fragmentation-based complexity measure, we show this to be possible by achieving good performance on the PGDL (Predicting Generalization in Deep Learning) benchmark. In addition, we report on new observations related to fragmentation, namely (i) fragmentation is not limited to the input space but occurs in the hidden representations as well, (ii) fragmentation follows the trends in the validation error throughout training, and (iii) fragmentation is not a direct result of increased weight norms. Together, this indicates that fragmentation is a phenomenon worth investigating further when studying the generalization ability of deep neural networks.

## 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/2411.04695>)

[PDF](<https://arxiv.org/pdf/2411.04695.pdf>)
