The Resistance to Label Noise in K-NN and DNN Depends on its Concentration
This work addresses the problem of understanding label noise resistance in machine learning models for researchers, providing insights into DNN robustness but is incremental as it builds on prior observations.
The paper investigates how label noise affects classification performance in K-NN and DNNs, showing that DNN predictions depend on local training labels and deriving an analytic expression for K-NN error that approximates DNN error, with empirical validation indicating greater performance degradation with more concentrated noise.
We investigate the classification performance of K-nearest neighbors (K-NN) and deep neural networks (DNNs) in the presence of label noise. We first show empirically that a DNN's prediction for a given test example depends on the labels of the training examples in its local neighborhood. This motivates us to derive a realizable analytic expression that approximates the multi-class K-NN classification error in the presence of label noise, which is of independent importance. We then suggest that the expression for K-NN may serve as a first-order approximation for the DNN error. Finally, we demonstrate empirically the proximity of the developed expression to the observed performance of K-NN and DNN classifiers. Our result may explain the already observed surprising resistance of DNN to some types of label noise. It also characterizes an important factor of it showing that the more concentrated the noise the greater is the degradation in performance.