Neighbourhood Components Analysis

By Jacob Goldberger, Sam T. Roweis, Geoffrey E. Hinton, Ruslan Salakhutdinov. 2004

2,168 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

Grafit: Learning fine-grained image representations with coarse labels (2020, methodology): “Therefore, inspired by the neighborhood component analysis [23, 39, 47], Wu et al.”
Prototypical Networks for Few-shot Learning (2017, background): “A key distinction between our approach and non-linear NCA is that we form a softmax directly over classes, rather than individual points, computed from distances to each class’s prototype representation.”
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “Since learning a projection for the data is equivalent to learning a Mahalanobis metric in the original feature space, our work is related to metric learning (Globerson and Roweis 2005; Goldberger et al. 2004; Weinberger et al. 2005).”
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models (2017, background): “However, sampling with dependencies may be necessary for tasks such as for metric learning [4, 11].”
Few-Shot Learning Through an Information Retrieval Lens (2017, background): “Neighborhood Component Analysis (NCA) [6] learns a metric aiming at high performance in nearest neirhbour classification.”
Improving Generalization via Scalable Neighborhood Component Analysis (2018, methodology): “The core of our approach is a metric learning model based on Neighborhood Component Analysis (NCA) [8].”
A Survey on Metric Learning for Feature Vectors and Structured Data (2013, methodology): “NCA (Goldberger et al.) The idea of Neighbourhood Component Analysis17 (NCA), introduced by Goldberger et al. (2004), is to optimize the expected leave-one-out error of a stochastic nearest neighbor classifier in the projection space induced by dM .”
Metric Learning with Adaptive Density Discrimination (2015, background): “…loss for a pair of triplets “symmetrized” for the two positive examples: Neighbourhood Components Analysis Neighbourhood Components Analysis (NCA) and its extensions (Goldberger et al., 2004; Salakhutdinov & Hinton, 2007; Min et al., 2010) have been designed in a similar spirit to Magnet Loss.”
Unsupervised Deep Learning by Neighbourhood Discovery (2019, background): “This takes the spirit of stochastic nearest neighbour (Goldberger et al., 2005), as it considers the entire training set.”
Hamming Distance Metric Learning (2012, background): “The goal of metric learning techniques is to improve matters by incorporating side information, and optimizing parametric distance functions such as the Mahalanobis distance [7, 12, 30, 34, 36].”
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning (2020, background): “A simple cross-entropy loss would work, but we found empirically that the NCA loss [10,28] converged faster.”
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training (2019, background): “Manifold and neighborhood structure have been proven to be effective in capturing the inter-sample relationships [51, 22].”
Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning (2013, methodology): “Our first set of experiments mimics those found in Goldberger et al. (2004).”
Learning Distance Metrics with Contextual Constraints for Image Retrieval (2006, methodology): “Most recently, Goldberger et al. [3] proposed the Neighborhood Component Analysis to learn a distance measure for kNN classiﬁcation by directly maximizing a stochastic variant of the leave-one-out kNN score on the training set.”
On Deep Multi-View Representation Learning (2015, methodology): “On these tasks, we compare the following methods in the multi-view learning setting: • DNN-based models , including SplitAE, CorrAE, DCCA, DCCAE, and DistAE.”
Self-Alignment Pretraining for Biomedical Entity Representations (2020, background): “, 2018), NCA loss (Goldberger et al., 2005), simple cosine loss (Phan et al.”