# A Scalable and Efficient Iterative Method for Copying Machine Learning Classifiers

arXiv: https://arxiv.org/abs/2302.02667 · HTML: https://mlsanity.com/paper/2302.02667/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 6 Feb 2023.

## Builds on (most cited first, 18 of 18)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Challenges in Deploying Machine Learning: a Survey of Case Studies](https://mlsanity.com/paper/2011.09926/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Label Refinery: Improving ImageNet Classification through Label Progression](https://mlsanity.com/paper/1805.02641/) (2018)
- [Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students](https://mlsanity.com/paper/1805.05551/) (2018)
- [Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model](https://mlsanity.com/paper/2003.13960/) (2020)
- [Domain adaptation under structural causal models](https://mlsanity.com/paper/2010.15764/) (2020)
- [User Response Prediction in Online Advertising](https://mlsanity.com/paper/2101.02342/) (2021)
- [Teacher-Student Compression with Generative Adversarial Networks](https://mlsanity.com/paper/1812.02271/) (2018)
- [Copying Machine Learning Classifiers](https://mlsanity.com/paper/1903.01879/) (2019)
- [Scaling up Data Augmentation MCMC via Calibration](https://mlsanity.com/paper/1703.03123/) (2017)
- [Sampling Unknown Decision Functions to Build Classifier Copies](https://mlsanity.com/paper/1910.00237/) (2019)
- [Transfer Learning in Information Criteria-based Feature Selection](https://mlsanity.com/paper/2107.02847/) (2021)

## Built on by (most cited first, 1 of 1)

- [Smoothing the Black-Box: Signed-Distance Supervision for Black-Box Model Copying](https://mlsanity.com/paper/2601.20773/) (2026)

## Abstract (arXiv)

Differential replication through copying refers to the process of replicating the decision behavior of a machine learning model using another model that possesses enhanced features and attributes. This process is relevant when external constraints limit the performance of an industrial predictive system. Under such circumstances, copying enables the retention of original prediction capabilities while adapting to new demands. Previous research has focused on the single-pass implementation for copying. This paper introduces a novel sequential approach that significantly reduces the amount of computational resources needed to train or maintain a copy, leading to reduced maintenance costs for companies using machine learning models in production. The effectiveness of the sequential approach is demonstrated through experiments with synthetic and real-world datasets, showing significant reductions in time and resources, while maintaining or improving accuracy.