Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees

Abstract

Nearest neighbor (kNN) methods have been gaining popularity in recent years in light of advances in hardware and efficiency of algorithms. There is a plethora of methods to choose from today, each with their own advantages and disadvantages. One requirement shared between all kNN based methods is the need for a good representation and distance measure between samples. We introduce a new method called differentiable boundary tree which allows for learning deep kNN representations. We build on the recently proposed boundary tree algorithm which allows for efficient nearest neighbor classification, regression and retrieval. By modelling traversals in the tree as stochastic events, we are able to form a differentiable cost function which is associated with the tree's predictions. Using a deep neural network to transform the data and back-propagating through the tree allows us to learn good representations for kNN methods. We demonstrate that our method is able to learn suitable represe

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzoran2017learning

Related papers

• Efficient Learning Of Neighbor Representations For Boundary Trees And Forests (2018)0.00
• Adaptive Nearest Neighbor: A General Framework For Distance Metric Learning (2019)0.00
• Knet: A Deep Knn Network To Handle Label Noise (2021)0.00
• Neural Nearest Neighbors Networks (2018)0.00
• Explaining The Success Of Nearest Neighbor Methods In Prediction (2025)18.63
• Exploiting Pre-trained Models For Drug Target Affinity Prediction With Nearest Neighbors (2024)3.58
• A Two-stage Active Learning Algorithm For \(k\)-nearest Neighbors (2022)0.00
• On Convergence Of Nearest Neighbor Classifiers Over Feature Transformations (2020)0.00