# Graph convolutional networks for learning with few clean and many noisy labels

arXiv: https://arxiv.org/abs/1910.00324 · HTML: https://mlsanity.com/paper/1910.00324/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 8 of 8)

- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [Learning with Neighbor Consistency for Noisy Labels](https://mlsanity.com/paper/2202.02200/) (2022)
- [Consistency Regularization Can Improve Robustness to Label Noise](https://mlsanity.com/paper/2110.01242/) (2021)
- [DETA: Denoised Task Adaptation for Few-Shot Learning](https://mlsanity.com/paper/2303.06315/) (2023)
- [Knowledge Learning with Crowdsourcing: A Brief Review and Systematic Perspective](https://mlsanity.com/paper/2206.09315/) (2022)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data](https://mlsanity.com/paper/2501.02476/) (2025)
- [A Survey on Graph Neural Networks for Fraud Detection in Ride Hailing Platforms](https://mlsanity.com/paper/2512.23777/) (2025)

## Abstract (arXiv)

In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each class, the GCN is treated as a binary classifier, which learns to discriminate clean from noisy examples using a weighted binary cross-entropy loss function. The GCN-inferred "clean" probability is then exploited as a relevance measure. Each noisy example is weighted by its relevance when learning a classifier for the end task. We evaluate our method on an extended version of a few-shot learning problem, where the few clean examples of novel classes are supplemented with additional noisy data. Experimental results show that our GCN-based cleaning process significantly improves the classification accuracy over not cleaning the noisy data, as well as standard few-shot classification where only few clean examples are used.