# Behavior of k-NN as an Instance-Based Explanation Method

arXiv: https://arxiv.org/abs/2109.06999 · HTML: https://mlsanity.com/paper/2109.06999/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Model-Agnostic Counterfactual Explanations for Consequential Decisions](https://mlsanity.com/paper/1905.11190/) (2019)
- [On the Accuracy of Influence Functions for Measuring Group Effects](https://mlsanity.com/paper/1905.13289/) (2019)
- [RelatIF: Identifying Explanatory Training Examples via Relative Influence](https://mlsanity.com/paper/2003.11630/) (2020)
- [Explaining and Improving Model Behavior with k Nearest Neighbor Representations](https://mlsanity.com/paper/2010.09030/) (2020)

## Built on by (most cited first, 2 of 2)

- [Local MDI+: Local Feature Importances for Tree-Based Models](https://mlsanity.com/paper/2506.08928/) (2025)
- [WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles](https://mlsanity.com/paper/2411.01357/) (2024)

## Abstract (arXiv)

Adoption of DL models in critical areas has led to an escalating demand for sound explanation methods. Instance-based explanation methods are a popular type that return selective instances from the training set to explain the predictions for a test sample. One way to connect these explanations with prediction is to ask the following counterfactual question - how does the loss and prediction for a test sample change when explanations are removed from the training set? Our paper answers this question for k-NNs which are natural contenders for an instance-based explanation method. We first demonstrate empirically that the representation space induced by last layer of a neural network is the best to perform k-NN in. Using this layer, we conduct our experiments and compare them to influence functions (IFs) ~citekoh2017understanding which try to answer a similar question. Our evaluations do indicate change in loss and predictions when explanations are removed but we do not find a trend between k and loss or prediction change. We find significant stability in the predictions and loss of MNIST vs. CIFAR-10. Surprisingly, we do not observe much difference in the behavior of k-NNs vs. IFs on this question. We attribute this to training set subsampling for IFs.