# A Practical Guide to Streaming Continual Learning

arXiv: https://arxiv.org/abs/2603.01677 · HTML: https://mlsanity.com/paper/2603.01677/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 87 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [River: machine learning for streaming data in Python](https://mlsanity.com/paper/2012.04740/) (2020)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges](https://mlsanity.com/paper/1907.00182/) (2019)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time](https://mlsanity.com/paper/2211.14238/) (2022)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data](https://mlsanity.com/paper/2108.09020/) (2021)
- [Continual Learning: Applications and the Road Forward](https://mlsanity.com/paper/2311.11908/) (2023)
- [SpaceNet: Make Free Space For Continual Learning](https://mlsanity.com/paper/2007.07617/) (2020)
- [CLAD: A realistic Continual Learning benchmark for Autonomous Driving](https://mlsanity.com/paper/2210.03482/) (2022)
- [Avalanche: A PyTorch Library for Deep Continual Learning](https://mlsanity.com/paper/2302.01766/) (2023)
- [Drinking from a Firehose: Continual Learning with Web-scale Natural Language](https://mlsanity.com/paper/2007.09335/) (2020)
- [A Comprehensive Empirical Evaluation on Online Continual Learning](https://mlsanity.com/paper/2308.10328/) (2023)
- [Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments](https://mlsanity.com/paper/1810.07348/) (2018)
- [Adiabatic replay for continual learning](https://mlsanity.com/paper/2303.13157/) (2023)

## Built on by (most cited first, 2 of 2)

- [Streaming Hierarchical Inference with Tabular Foundation Models](https://mlsanity.com/paper/2609.07956/) (2026)
- [Online Learning via Learned Latent Bayesian Tracking](https://mlsanity.com/paper/2609.31559/) (2026)

## Abstract (arXiv)

Continual Learning (CL) and Streaming Machine Learning (SML) study the ability of agents to learn from a stream of non-stationary data. Despite sharing some similarities, they address different and complementary challenges. While SML focuses on rapid adaptation after changes (concept drifts), CL aims to retain past knowledge when learning new tasks. After a brief introduction to CL and SML, we discuss Streaming Continual Learning (SCL), an emerging paradigm providing a unifying solution to real-world problems, which may require both SML and CL abilities. We claim that SCL can i) connect the CL and SML communities, motivating their work towards the same goal, and ii) foster the design of hybrid approaches that can quickly adapt to new information (as in SML) without forgetting previous knowledge (as in CL). We conclude the paper with a motivating example and a set of experiments, highlighting the need for SCL by showing how CL and SML alone struggle in achieving rapid adaptation and knowledge retention.