TLDR: Twin Learning For Dimensionality Reduction

Abstract

Dimensionality reduction methods are unsupervised approaches which learn low-dimensional spaces where some properties of the initial space, typically the notion of "neighborhood", are preserved. Such methods usually require propagation on large k-NN graphs or complicated optimization solvers. On the other hand, self-supervised learning approaches, typically used to learn representations from scratch, rely on simple and more scalable frameworks for learning. In this paper, we propose TLDR, a dimensionality reduction method for generic input spaces that is porting the recent self-supervised learning framework of Zbontar et al. (2021) to the specific task of dimensionality reduction, over arbitrary representations. We propose to use nearest neighbors to build pairs from a training set and a redundancy reduction loss to learn an encoder that produces representations invariant across such pairs. TLDR is a method that is simple, easy to train, and of broad applicability; it consists of an of

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykalantidis2021tldr

Related papers

• Order-preserving Dimension Reduction For Multimodal Semantic Embedding (2024)2.26
• Dimensionality-reduction Techniques For Approximate Nearest Neighbor Search: A Survey And Evaluation (2024)0.00
• Self-calibrating Neural Networks For Dimensionality Reduction (2016)0.00
• Learning-based Dimensionality Reduction For Computing Compact And Effective Local Feature Descriptors (2022)9.99
• Representation Learning By Reconstructing Neighborhoods (2018)0.00
• Finding Significant Features For Few-shot Learning Using Dimensionality Reduction (2021)2.26
• Interactive Dimensionality Reduction Using Similarity Projections (2018)8.09
• Local Distance Metric Learning For Nearest Neighbor Algorithm (2018)0.00