Knet: A Deep Knn Network To Handle Label Noise

Abstract

Deep Neural Networks require large amounts of labeled data for their training. Collecting this data at scale inevitably causes label noise.Hence,the need to develop learning algorithms that are robust to label noise. In recent years, k Nearest Neighbors (kNN) emerged as a viable solution to this problem. Despite its success, kNN is not without its problems. Mainly, it requires a huge memory footprint to store all the training samples and it needs an advanced data structure to allow for fast retrieval of the relevant examples, given a query sample. We propose a neural network, termed kNet, that learns to perform kNN. Once trained, we no longer need to store the training data, and processing a query sample is a simple matter of inference. To use kNet, we first train a preliminary network on the data set, and then train kNet on the penultimate layer of the preliminary network.We find that kNet gives a smooth approximation of kNN,and cannot handle the sharp label changes between samples th

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymizrahi2021knet

Related papers

• On The Resistance Of Nearest Neighbor To Random Noisy Labels (2016)0.00
• An Embedding Is Worth A Thousand Noisy Labels (2024)2.16
• A Fast And Easy Regression Technique For K-nn Classification Without Using Negative Pairs (2018)0.00
• Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees (2017)0.00
• Revisiting A Knn-based Image Classification System With High-capacity Storage (2022)9.59
• A New Hashing Based Nearest Neighbors Selection Technique For Big Datasets (2020)3.58
• Adaptive Nearest Neighbor: A General Framework For Distance Metric Learning (2019)0.00
• Distributionally Robust Weighted \(k\)-nearest Neighbors (2020)0.00