# Deep Weighted Averaging Classifiers

arXiv: https://arxiv.org/abs/1811.02579 · HTML: https://mlsanity.com/paper/1811.02579/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers](https://mlsanity.com/paper/2103.12279/) (2021)
- [Unsupervised Out-of-Domain Detection via Pre-trained Transformers](https://mlsanity.com/paper/2106.00948/) (2021)
- [Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates](https://mlsanity.com/paper/2110.03212/) (2021)
- [Removing biased data to improve fairness and accuracy](https://mlsanity.com/paper/2102.03054/) (2021)
- [Designing Interpretable ML System to Enhance Trust in Healthcare: A Systematic Review to Proposed Responsible Clinician-AI-Collaboration Framework](https://mlsanity.com/paper/2311.11055/) (2023)
- [Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps](https://mlsanity.com/paper/2104.12294/) (2021)
- [StyLEx: Explaining Style Using Human Lexical Annotations](https://mlsanity.com/paper/2210.07469/) (2022)
- [Harnessing value from data science in business: ensuring explainability and fairness of solutions](https://mlsanity.com/paper/2108.07714/) (2021)

## Abstract (arXiv)

Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness, and interpretability of these models. In this paper we propose a simple way to modify any conventional deep architecture to automatically provide more transparent explanations for classification decisions, as well as an intuitive notion of the credibility of each prediction. Specifically, we draw on ideas from nonparametric kernel regression, and propose to predict labels based on a weighted sum of training instances, where the weights are determined by distance in a learned instance-embedding space. Working within the framework of conformal methods, we propose a new measure of nonconformity suggested by our model, and experimentally validate the accompanying theoretical expectations, demonstrating improved transparency, controlled error rates, and robustness to out-of-domain data, without compromising on accuracy or calibration.