# Data Stream Sampling with Fuzzy Task Boundaries and Noisy Labels

arXiv: https://arxiv.org/abs/2404.04871 · HTML: https://mlsanity.com/paper/2404.04871/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 7 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Continual Learning of Context-dependent Processing in Neural Networks](https://mlsanity.com/paper/1810.01256/) (2018)
- [Template-Based Named Entity Recognition Using BART](https://mlsanity.com/paper/2106.01760/) (2021)
- [Uncertainty-based Continual Learning with Adaptive Regularization](https://mlsanity.com/paper/1905.11614/) (2019)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [The Measure and Mismeasure of Fairness](https://mlsanity.com/paper/1808.00023/) (2018)
- [Self-Supervised Training Enhances Online Continual Learning](https://mlsanity.com/paper/2103.14010/) (2021)
- [Continually Learning Self-Supervised Representations with Projected Functional Regularization](https://mlsanity.com/paper/2112.15022/) (2021)
- [Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries](https://mlsanity.com/paper/2203.15355/) (2022)
- [Continual Learning on Noisy Data Streams via Self-Purified Replay](https://mlsanity.com/paper/2110.07735/) (2021)
- [Concept Drift Detection from Multi-Class Imbalanced Data Streams](https://mlsanity.com/paper/2104.10228/) (2021)

## Abstract (arXiv)

In the realm of continual learning, the presence of noisy labels within data streams represents a notable obstacle to model reliability and fairness. We focus on the data stream scenario outlined in pertinent literature, characterized by fuzzy task boundaries and noisy labels. To address this challenge, we introduce a novel and intuitive sampling method called Noisy Test Debiasing (NTD) to mitigate noisy labels in evolving data streams and establish a fair and robust continual learning algorithm. NTD is straightforward to implement, making it feasible across various scenarios. Our experiments benchmark four datasets, including two synthetic noise datasets (CIFAR10 and CIFAR100) and real-world noise datasets (mini-WebVision and Food-101N). The results validate the efficacy of NTD for online continual learning in scenarios with noisy labels in data streams. Compared to the previous leading approach, NTD achieves a training speedup enhancement over two times while maintaining or surpassing accuracy levels. Moreover, NTD utilizes less than one-fifth of the GPU memory resources compared to previous leading methods.