Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments

Federico Giannini; Giacomo Ziffer; Andrea Cossu; Vincenzo Lomonaco

cs.LGMar 2, 2026

Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments

Authors: Federico Giannini, Giacomo Ziffer, Andrea Cossu, Vincenzo Lomonaco

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

Abstract

Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this arduous task. We put forward a unified setting that harnesses the benefits of both CL and SML: their ability to quickly adapt to non-stationary data streams without forgetting previous knowledge. We refer to this setting as Streaming Continual Learning (SCL). SCL does not replace either CL or SML. Instead, it extends the techniques and approaches considered by both fields. We start by briefly describing CL and SML and unifying the languages of the two frameworks. We then present the key features of SCL. We finally highlight the importance of bridging the two communities to advance the field of intelligent systems.

Figures & tables

Panel of Figure 1 — Figure 1: Comparison between a Continual Learning algorithm $A^{\text{CL}}$ and Streaming Machine Learning algorithm $A^{\text{SML}}$ trained on a possibly infinite sequence of items, indexed by the subscript $i$ . ( 1(a) ) Continual Learning with a model $h$ and an external memory $M$ . Training is performed on one training item’s data $D_{i}$ at a time. The test sets $D_{1}^{\text{test}},D_{2}^{\text{test}},\ldots,D_{i}^{\text{test}}$ are used for evaluation. ( 1(b) ) Streaming Machine Learning with a model $h$ and a stream of items’ data $D_{i}$ , where each $D_{i}$ contains a mini-batch of a few examples. Each $D_{i}$ is used both for the testing and the training phases.

Figure 2: Comparison between Continual Learning Scenarios and Drifts in Streaming Machine Learning. The red dashed line highlights the decision boundary, while grey dots represent data no longer available. Different shapes represent novel data that may still fall into the same classes as the previous experience, as per Domain Incremental Learning, or may represent new classes (denoted by different colors), as per Class Incremental Learning. In Domain-Incremental learning, each experience contains examples from all classes, while new experiences introduce new examples only, potentially leading to virtual drift. Class-Incremental learning is prone to concept evolution since it exclusively introduces examples of new classes in each new experience. Task-Incremental learning assigns a task label to each example. It can be viewed as a concept drift or a concept evolution, depending on whether we consider the class labels of all tasks or only those of the current task.

Panel of Table 1 — Table 1: Comparison of key properties of Continual Learning (CL), Streaming Machine Learning (SML), and the proposed Streaming Continual Learning (SCL) frameworks. We refer to CL for both CL and OCL paradigms. Only a few recent pioneering OCL works apply autonomous drift detection, which is not present in CL. CL does not apply to learn from a few data points, while OCL was meant to fulfil this need. SCL acts as a real unifying paradigm incorporating SML and CL goals and techniques.

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

A Practical Guide to Streaming Continual Learning
Mar 2, 2026Andrea Cossu, Federico Giannini, Giacomo Ziffer +5Continual Learning Streaming Algorithms
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 +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 Learning Online Continual Learning
DEIB - Politecnico di Milano
To Retain or to Adapt? Generalizing Continual Learning
Jul 6, 2026Giulia Lanzillotta, Mandana Samiei, Doina Precup +2Continual Learning Online 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

Mar 2, 2026J/K move · Enter open · S save

A Practical Guide to Streaming Continual Learning

Andrea Cossu, Federico Giannini, Giacomo Ziffer, Alessio Bernardo+4

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+2

Continual Learning Streaming Algorithms

Open paper AskPDF 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.

Abstract

Continual Learning

Explore similar work

A Practical Guide to Streaming Continual Learning

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

To Retain or to Adapt? Generalizing Continual Learning