# neuralRank: Searching and ranking ANN-based model repositories

## TL;DR

This paper introduces neuralRank, a novel method for searching and ranking pre-trained neural network models based on their suitability for specific datasets, demonstrating its effectiveness across multiple datasets.

## Contribution

The paper proposes neuralRank, a new ranking algorithm that assesses model suitability based on discriminating power, independent of domain, training set, or architecture.

## Key findings

- neuralRank effectively ranks models with higher accuracy in practice
- The ranking is independent of domain, training set, or architecture
- Models ranked highly by neuralRank tend to perform better

## Abstract

Widespread applications of deep learning have led to a plethora of pre-trained neural network models for common tasks. Such models are often adapted from other models via transfer learning. The models may have varying training sets, training algorithms, network architectures, and hyper-parameters. For a given application, what isthe most suitable model in a model repository? This is a critical question for practical deployments but it has not received much attention. This paper introduces the novel problem of searching and ranking models based on suitability relative to a target dataset and proposes a ranking algorithm called \textit{neuralRank}. The key idea behind this algorithm is to base model suitability on the discriminating power of a model, using a novel metric to measure it. With experimental results on the MNIST, Fashion, and CIFAR10 datasets, we demonstrate that (1) neuralRank is independent of the domain, the training set, or the network architecture and (2) that the models ranked highly by neuralRank ranking tend to have higher model accuracy in practice.