# Improving Simple Models with Confidence Profiles

arXiv: https://arxiv.org/abs/1807.07506 · HTML: https://mlsanity.com/paper/1807.07506/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 12 of 12)

- [Human-Centered Explainable AI (XAI): From Algorithms to User Experiences](https://mlsanity.com/paper/2110.10790/) (2021)
- [Gradient based Feature Attribution in Explainable AI: A Technical Review](https://mlsanity.com/paper/2403.10415/) (2024)
- [AI Explainability 360: Impact and Design](https://mlsanity.com/paper/2109.12151/) (2021)
- [On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach](https://mlsanity.com/paper/2211.01498/) (2022)
- [Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges](https://mlsanity.com/paper/2112.04698/) (2021)
- [Auto-Transfer: Learning to Route Transferrable Representations](https://mlsanity.com/paper/2202.01011/) (2022)
- [Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners](https://mlsanity.com/paper/2202.01153/) (2022)
- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning](https://mlsanity.com/paper/2201.12143/) (2022)
- [Using Knowledge Distillation to improve interpretable models in a retail banking context](https://mlsanity.com/paper/2209.15496/) (2022)
- [Multihop: Leveraging Complex Models to Learn Accurate Simple Models](https://mlsanity.com/paper/2109.06961/) (2021)
- [PainPoints: A Framework for Language-based Detection of Chronic Pain and Expert-Collaborative Text-Summarization](https://mlsanity.com/paper/2209.09814/) (2022)

## Abstract (arXiv)

In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretable model or a very shallow network of low complexity and a priori low test accuracy. We are motivated by applications in interpretability and model deployment in severely memory constrained environments (like sensors). Our method uses linear probes to generate confidence scores through flattened intermediate representations. Our transfer method involves a theoretically justified weighting of samples during the training of the simple model using confidence scores of these intermediate layers. The value of our method is first demonstrated on CIFAR-10, where our weighting method significantly improves (3-4%) networks with only a fraction of the number of Resnet blocks of a complex Resnet model. We further demonstrate operationally significant results on a real manufacturing problem, where we dramatically increase the test accuracy of a CART model (the domain standard) by roughly 13%.