# Learning from Data Streams: An Overview and Update

arXiv: https://arxiv.org/abs/2212.14720 · HTML: https://mlsanity.com/paper/2212.14720/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 152 references that are in the map.
- First posted on arXiv 30 Dec 2022.

## Builds on (most cited first, 25 of 25)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [On Calibration and Out-of-domain Generalization](https://mlsanity.com/paper/2102.10395/) (2021)
- [A Deeper Look at Experience Replay](https://mlsanity.com/paper/1712.01275/) (2017)
- [Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset](https://mlsanity.com/paper/2010.11395/) (2020)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [Extremely Fast Decision Tree](https://mlsanity.com/paper/1802.08780/) (2018)
- [Spiking Neural Networks and Online Learning: An Overview and Perspectives](https://mlsanity.com/paper/1908.08019/) (2019)
- [Streaming convolutional neural networks for end-to-end learning with multi-megapixel images](https://mlsanity.com/paper/1911.04432/) (2019)
- [Model-based Reinforcement Learning: A Survey](https://mlsanity.com/paper/2006.16712/) (2020)
- [Concept Drift Adaptation by Exploiting Historical Knowledge](https://mlsanity.com/paper/1702.03500/) (2017)
- [A Survey on Semi-Supervised Learning for Delayed Partially Labelled Data Streams](https://mlsanity.com/paper/2106.09170/) (2021)
- [One-Pass Learning with Incremental and Decremental Features](https://mlsanity.com/paper/1605.09082/) (2016)
- [Learning Parameter Distributions to Detect Concept Drift in Data Streams](https://mlsanity.com/paper/2010.09388/) (2020)
- [How good is the Electricity benchmark for evaluating concept drift adaptation](https://mlsanity.com/paper/1301.3524/) (2013)
- [Change Detection for Local Explainability in Evolving Data Streams](https://mlsanity.com/paper/2209.02764/) (2022)
- [Tiny Machine Learning for Concept Drift](https://mlsanity.com/paper/2107.14759/) (2021)
- [Concept-drifting Data Streams are Time Series; The Case for Continuous Adaptation](https://mlsanity.com/paper/1810.02266/) (2018)
- [Dynamic Model Tree for Interpretable Data Stream Learning](https://mlsanity.com/paper/2203.16181/) (2022)
- [Multi-label Methods for Prediction with Sequential Data](https://mlsanity.com/paper/1609.08349/) (2016)
- [Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances](https://mlsanity.com/paper/1909.05367/) (2019)
- [Nowcasting the Financial Time Series with Streaming Data Analytics under Apache Spark](https://mlsanity.com/paper/2202.11820/) (2022)

## Built on by (most cited first, 5 of 5)

- [Out-of-Distribution Generalization in Time Series: A Survey](https://mlsanity.com/paper/2503.13868/) (2025)
- [Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams](https://mlsanity.com/paper/2412.10545/) (2024)
- [The Window Dilemma: Why Concept Drift Detection is Ill-Posed](https://mlsanity.com/paper/2602.06456/) (2026)
- [Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference](https://mlsanity.com/paper/2605.31239/) (2026)
- [Challenges in Evaluating Explanation Methods for Static and Evolving Data](https://mlsanity.com/paper/2608.06351/) (2026)

## Abstract (arXiv)

The literature on machine learning in the context of data streams is vast and growing. However, many of the defining assumptions regarding data-stream learning tasks are too strong to hold in practice, or are even contradictory such that they cannot be met in the contexts of supervised learning. Algorithms are chosen and designed based on criteria which are often not clearly stated, for problem settings not clearly defined, tested in unrealistic settings, and/or in isolation from related approaches in the wider literature. This puts into question the potential for real-world impact of many approaches conceived in such contexts, and risks propagating a misguided research focus. We propose to tackle these issues by reformulating the fundamental definitions and settings of supervised data-stream learning with regard to contemporary considerations of concept drift and temporal dependence; and we take a fresh look at what constitutes a supervised data-stream learning task, and a reconsideration of algorithms that may be applied to tackle such tasks. Through and in reflection of this formulation and overview, helped by an informal survey of industrial players dealing with real-world data streams, we provide recommendations. Our main emphasis is that learning from data streams does not impose a single-pass or online-learning approach, or any particular learning regime; and any constraints on memory and time are not specific to streaming. Meanwhile, there exist established techniques for dealing with temporal dependence and concept drift, in other areas of the literature. For the data streams community, we thus encourage a shift in research focus, from dealing with often-artificial constraints and assumptions on the learning mode, to issues such as robustness, privacy, and interpretability which are increasingly relevant to learning in data streams in academic and industrial settings.