# One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes

arXiv: https://arxiv.org/abs/2102.07834 · HTML: https://mlsanity.com/paper/2102.07834/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 8 of 8)

- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [Soft-Label Dataset Distillation and Text Dataset Distillation](https://mlsanity.com/paper/1910.02551/) (2019)
- [Practical Coreset Constructions for Machine Learning](https://mlsanity.com/paper/1703.06476/) (2017)
- ['Less Than One'-Shot Learning: Learning N Classes From M<N Samples](https://mlsanity.com/paper/2009.08449/) (2020)
- [On the approximability of covering points by lines and related problems](https://mlsanity.com/paper/1312.2549/) (2013)
- [Optimal 1-NN Prototypes for Pathological Geometries](https://mlsanity.com/paper/2011.00228/) (2020)

## Built on by (most cited first, 4 of 4)

- [On the Informativeness of Supervision Signals](https://mlsanity.com/paper/2211.01407/) (2022)
- [Can Humans Do Less-Than-One-Shot Learning?](https://mlsanity.com/paper/2202.04670/) (2022)
- [Learning New Tasks from a Few Examples with Soft-Label Prototypes](https://mlsanity.com/paper/2210.17437/) (2022)
- [Exploring the potential of prototype-based soft-labels data distillation for imbalanced data classification](https://mlsanity.com/paper/2403.17130/) (2024)

## Abstract (arXiv)

Increasingly large datasets are rapidly driving up the computational costs of machine learning. Prototype generation methods aim to create a small set of synthetic observations that accurately represent a training dataset but greatly reduce the computational cost of learning from it. Assigning soft labels to prototypes can allow increasingly small sets of prototypes to accurately represent the original training dataset. Although foundational work on `less than one'-shot learning has proven the theoretical plausibility of learning with fewer than one observation per class, developing practical algorithms for generating such prototypes remains an unexplored territory. We propose a novel, modular method for generating soft-label prototypical lines that still maintains representational accuracy even when there are fewer prototypes than the number of classes in the data. In addition, we propose the Hierarchical Soft-Label Prototype k-Nearest Neighbor classification algorithm based on these prototypical lines. We show that our method maintains high classification accuracy while greatly reducing the number of prototypes required to represent a dataset, even when working with severely imbalanced and difficult data. Our code is available at https://github.com/ilia10000/SLkNN.