# Improving Classification Accuracy with Graph Filtering

arXiv: https://arxiv.org/abs/2101.04789 · HTML: https://mlsanity.com/paper/2101.04789/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Shake-Shake regularization](https://mlsanity.com/paper/1705.07485/) (2017)
- [Leveraging the Feature Distribution in Transfer-based Few-Shot Learning](https://mlsanity.com/paper/2006.03806/) (2020)

## Built on by (most cited first, 3 of 3)

- [CDC: A Simple Framework for Complex Data Clustering](https://mlsanity.com/paper/2403.03670/) (2024)
- [Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification](https://mlsanity.com/paper/2209.08527/) (2022)
- [High-order Multi-view Clustering for Generic Data](https://mlsanity.com/paper/2209.10838/) (2022)

## Abstract (arXiv)

In machine learning, classifiers are typically susceptible to noise in the training data. In this work, we aim at reducing intra-class noise with the help of graph filtering to improve the classification performance. Considered graphs are obtained by connecting samples of the training set that belong to a same class depending on the similarity of their representation in a latent space. We show that the proposed graph filtering methodology has the effect of asymptotically reducing intra-class variance, while maintaining the mean. While our approach applies to all classification problems in general, it is particularly useful in few-shot settings, where intra-class noise can have a huge impact due to the small sample selection. Using standardized benchmarks in the field of vision, we empirically demonstrate the ability of the proposed method to slightly improve state-of-the-art results in both cases of few-shot and standard classification.