# Continual Learning on Noisy Data Streams via Self-Purified Replay

arXiv: https://arxiv.org/abs/2110.07735 · HTML: https://mlsanity.com/paper/2110.07735/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 75 of its 104 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 30 of 75)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [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)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)

## Built on by (most cited first, 27 of 27)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Representation Compensation Networks for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.05402/) (2022)
- [Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries](https://mlsanity.com/paper/2203.15355/) (2022)
- [SIESTA: Efficient Online Continual Learning with Sleep](https://mlsanity.com/paper/2303.10725/) (2023)
- [Learnable Distribution Calibration for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2210.00232/) (2022)
- [Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory](https://mlsanity.com/paper/2309.15413/) (2023)
- [CNLL: A Semi-supervised Approach For Continual Noisy Label Learning](https://mlsanity.com/paper/2204.09881/) (2022)
- [Effects of Auxiliary Knowledge on Continual Learning](https://mlsanity.com/paper/2206.02577/) (2022)
- [Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling](https://mlsanity.com/paper/2407.15429/) (2024)
- [Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation](https://mlsanity.com/paper/2503.22136/) (2025)
- [Revisiting Supervision for Continual Representation Learning](https://mlsanity.com/paper/2311.13321/) (2023)
- [Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos](https://mlsanity.com/paper/2212.13495/) (2022)
- [Dynamic Prototype Rehearsal for Continual ECG Arrhythmia Detection](https://mlsanity.com/paper/2501.07555/) (2025)
- [ErrorEraser: Unlearning Data Bias for Improved Continual Learning](https://mlsanity.com/paper/2506.09347/) (2025)
- [LiSA: Lifelong Safety Adaptation via Conservative Policy Induction](https://mlsanity.com/paper/2605.14454/) (2026)
- [On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning](https://mlsanity.com/paper/2305.03648/) (2023)
- [May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels](https://mlsanity.com/paper/2408.14284/) (2024)
- [AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation](https://mlsanity.com/paper/2409.08516/) (2024)
- [RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks](https://mlsanity.com/paper/2411.16870/) (2024)
- [Continual Learning in the Presence of Spurious Correlation](https://mlsanity.com/paper/2303.11863/) (2023)
- [Continual Learning via Self-Probe Gradients](https://mlsanity.com/paper/2609.32771/) (2026)
- [Evolving Knowledge Mining for Class Incremental Segmentation](https://mlsanity.com/paper/2306.02027/) (2023)
- [Sample Weight Estimation Using Meta-Updates for Online Continual Learning](https://mlsanity.com/paper/2401.15973/) (2024)
- [Data Stream Sampling with Fuzzy Task Boundaries and Noisy Labels](https://mlsanity.com/paper/2404.04871/) (2024)
- [UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning](https://mlsanity.com/paper/2605.09862/) (2026)
- [Theory of Continual Learning Against Data Poisoning Attacks](https://mlsanity.com/paper/2606.29841/) (2026)
- [Reliable Replay through Spatial Coherence in Online Continual Learning](https://mlsanity.com/paper/2609.33725/) (2026)

## Abstract (arXiv)

Continually learning in the real world must overcome many challenges, among which noisy labels are a common and inevitable issue. In this work, we present a repla-ybased continual learning framework that simultaneously addresses both catastrophic forgetting and noisy labels for the first time. Our solution is based on two observations; (i) forgetting can be mitigated even with noisy labels via self-supervised learning, and (ii) the purity of the replay buffer is crucial. Building on this regard, we propose two key components of our method: (i) a self-supervised replay technique named Self-Replay which can circumvent erroneous training signals arising from noisy labeled data, and (ii) the Self-Centered filter that maintains a purified replay buffer via centrality-based stochastic graph ensembles. The empirical results on MNIST, CIFAR-10, CIFAR-100, and WebVision with real-world noise demonstrate that our framework can maintain a highly pure replay buffer amidst noisy streamed data while greatly outperforming the combinations of the state-of-the-art continual learning and noisy label learning methods. The source code is available at http://vision.snu.ac.kr/projects/SPR