cs.LGMar 2, 2026

A Practical Guide to Streaming Continual Learning

Authors: Andrea Cossu, Federico Giannini, Giacomo Ziffer, Alessio Bernardo, Alexander Gepperth, Emanuele Della Valle, Barbara Hammer, Davide Bacciu

Organizations: Computer Science Department, University of Pisa, Largo Bruno Pontecorvo, 3, Pisa, 56127, Italy · DEIB, Politecnico di Milano, Via Giuseppe Ponzio, 34, Milano, 20133, Italy · Motus ml, Milano, Italy · University of Applied Sciences Fulda, Germany · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

Figure 1: Overview of the structure of this manuscript. We start with an introduction to non-stationary environments, followed by a short background on streaming and continual learning, before discussing the streaming continual learning paradigm together with an empirical example motivating why it is needed.
Figure 2: Illustrations of various concept drift types. The red line represents the theoretical decision boundary of the problem that the model must fit. 2(b) depicts a real drift where the decision boundary shifts. 2(c) represents a zoom-in virtual drift that concentrates on a subset of the initial feature space. 2(d) shows a pure expansionary virtual drift introducing a new, previously unseen feature subspace. 2(e) displays a drift involving both familiar and new subspaces without altering the original decision boundary. Finally, 2(f) illustrates a combination of virtual and real drift, resulting in changes to the decision boundary within the previously known subspace.
Figure 3: An RL control loop: as a reaction to actions a(t)a(t) taken by the agent, it receives observations o(t)o(t) and rewards r(t)r(t) .
Figure 4: Virtual and real drift in Continual Reinforcement Learning (CRL). In this example scenario, a robot is rewarded or punished when touching certain objects, depending on form, color, and displayed symbol. Left: an object that should be touched, giving +10 reward. Middle: virtual drift, introducing a different object that should not be touched (or else: +10 reward). Right: real drift, changing the reward previously obtained for touching the object to punishment.
Figure 5: Summary of SML and CL, with some examples of popular state-of-the-art approaches and popular libraries. We refer to existing reviews for an in-depth treatment of either field.
Figure 6: Illustration of digits 1 , 7 , 0 , and 8 using a seven-segment display representation. Each digit is encoded as a binary vector over seven dimensions (x1,…,x7)(x_{1},\dots,x_{7}) , where each xix_{i} corresponds to one segment (on = 1, off = 0). Although some digits share subsets of active segments (e.g., 1 and 7 ), their full encodings place them in distinct regions of the input space. This simplified scenario reflects the nature of virtual drifts in our experiments, where new digits introduce non-overlapping patterns in the input distribution. While MNIST uses grayscale pixel values in a high-dimensional space, the same principle holds: each digit activates a different subset of features, occupying a unique region in the space.
Figure 7: Prequential evaluation results averaged over the ten executions (considering Cohen’s Kappa score). In the virtual drift scenario ( 8(a) ), the Naive classifier performs well. ER and AGEM obtain slightly lower performance, since they balance between plasticity and stability. In the real drift scenarios ( 8(b) ), the Naive classifier and AGEM perform equally, since the AGEM strategy has no impact. ER has strong difficulties to learn the new concept since it tries to mitigate forgetting. ARF is plastic in both scenarios.
Figure 8: CL learning evaluation. After each drift, the models are tested over the current and all the previous test sets, and the average Cohen’s Kappa score is computed. Finally, results are averaged over the ten executions. On the virtual drift scenario ( 8(a) ), ER and AGEM are stable, while ARF and the Naive classifier catastrophically forget previous concepts. On the virtual drift scenario ( 8(b) ), all the models cannot avoid forgetting. This is due to the fact that the concepts are in contradiction, and the model cannot solve both of them jointly.
 Virtual drift scenarioReal drift scenario
 Kavg\mathbf{K_{avg}}BWT\mathbf{BWT}Kavg\mathbf{K_{avg}}BWT\mathbf{BWT}
AGEM0.89 ± 0.06-0.13 ± 0.100.24 ± 0.01-0.99 ± 0.05
ARF0.40 ± 0.09-0.83 ± 0.140.24 ± 0.00-1.06 ± 0.00
ER0.94 ± 0.02-0.04 ± 0.020.27 ± 0.02-0.85 ± 0.08
Naive0.46 ± 0.09-0.77 ± 0.140.24 ± 0.01-1.00 ± 0.04
Table 1: Mean and standard deviation of the CL metrics over the ten executions using Cohen’s Kappa score.
More in this topic

Continual Learning

Continual Learning studies how models acquire knowledge from changing data streams while retaining or selectively revising what they learned before.

See all 294 papers

Explore similar work

CardsList

  1. Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments

    Mar 2, 2026Federico Giannini, Giacomo Ziffer, Andrea Cossu +1Continual LearningOnline Continual Learning

    DEIB, Politecnico di Milano, Milano, 20133, Italy · Computer Science Department, University of Pisa, Pisa, Italy

  2. Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence

    Mar 9, 2026Federico Giannini, Sandro D'Andrea, Emanuele Della ValleContinual LearningOnline Continual Learning

    DEIB - Politecnico di Milano

  3. To Retain or to Adapt? Generalizing Continual Learning

    Jul 6, 2026Giulia Lanzillotta, Mandana Samiei, Doina Precup +2Continual LearningOnline Continual Learning

    ETH AI Center, Department of Computer Science, ETH Zürich · Mila - Quebec AI Institute, School of Computer Science, McGill University · Mila - Quebec AI Institute +1