An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage

Ioannis Theologitis; Debin Meng; Stylianos Eleftheriadis; Vasileios Lolis; Konstantinos Votis

cs.LGAug 20, 2026

An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage

Authors: Ioannis Theologitis, Debin Meng, Stylianos Eleftheriadis, Vasileios Lolis, Konstantinos Votis

Organizations: Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece · School of Electronic Engineering and Computer Science, Queen Mary University of London, UK

Abstract

Artificial intelligence can support cultural heritage and digital humanities through large-scale retrieval and analysis of digitized collections. However, cultural heritage data are often distributed across institutions, constrained by ownership and access restrictions, and continuously evolving over time. Federated Continual Learning (FCL) is well suited to this setting, as it enables models to learn from distributed and sequential data without sharing raw collections. In this paper, we propose FedCurv-DR, a lightweight, regularisation-based FCL strategy. The method accumulates parameter-importance estimates across clients and experiences to protect learned knowledge, while updating them only at fixed intervals to minimize communication and computation overhead. We evaluate FedCurv-DR in a continual learning scenario using the WikiArt image dataset for genre classification with evolving styles, reporting performance, energy, and fairness metrics. Our results show that FedCurv- DR reduces forgetting and balances performance, fairness, and energy efficiency for sustainable AI in cultural heritage.

Figures & tables

Fig. 1: Overview of the federated continual learning process. Art institutions across Europe collaborate on training a single global model for image classification on their evolving collections, without sharing private data. Institutions periodically send model updates, rather than raw data, to a server operated by a trusted coordinating party, which aggregates them into a shared global model.

Fig. 2: Visualisation of the dataset partitioning with Dirichlet partitioner ( $\alpha=1$ ) among three clients for each experience (style).

Method	Final Stream Acc.(%) $\uparrow$	BWT(pp) $\uparrow$	Disparity(pp) $\downarrow$	Energy(kWh) $\downarrow$
FedAvg	63.18	-11.30	7.22	0.0296
FedCurv(EWC)	63.99	-12.32	3.09	0.0448
FedCurv(EWC-DR)	65.46	-10.26	4.56	0.0458
FedCurv-DR(interval=2, beta=0.95)	66.92	-6.92	2.89	0.0385
FedCurv-DR(interval=5, beta=0.95)	65.86	-7.49	5.91	0.0334

TABLE I: Summary of Final Accuracy, Backward Transfer, Disparity, and Energy Consumption Across Methods

Panel of Figure 4 — Fig. 3: Comparison of federated continual learning strategies across communication rounds. (a) Full-stream accuracy evaluates retention over all learned experiences. (b) Current-experience accuracy measures performance on the active experience. (c) Accuracy disparity reports client-level performance differences as a proxy for fairness.

Regularization-Based Continual Learning

See all 13 papers

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data
Jun 9, 2026Masoume Gholizade, Fabrizio Ruffini, Pietro Ducange +1Continual Learning Federated Continual Learning
Department of Information Engineering, University of Pisa, Largo Lucio Lazzarino 1, Pisa, 56122, Italy
Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problem
Aug 21, 2026Nazreen Shah, Naveen Kumar Reddy Somireddy, Zubair Shaban +2Federated Continual Learning Catastrophic Forgetting
IIIT Delhi India · IIT Dharwad India
Accurate and Resource-Efficient Federated Continual Learning
Jun 9, 2026Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan +2Communication-Efficient Distributed Training Continual Learning
University of Southern California · Los Angeles, USA · DEVCOM Army Research Office +1

Jun 9, 2026J/K move · Enter open · S save

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

Masoume Gholizade, Fabrizio Ruffini, Pietro Ducange, Francesco Marcelloni

Department of Information Engineering, University of Pisa, Largo Lucio Lazzarino 1, Pisa, 56122, Italy

Continual Learning Federated Continual Learning Privacy-Preserving ML Federated Learning

Open paper AskPDF arXiv

Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitly assume data stationarity. In real-world settings-such as healthcare, industrial IoT (IIOT), cybersecurity, and smart cities-data streams are inherently non-stationary, leading classical FL methods to suffer from performance degradation, instability, and catastrophic forgetting. Continual Learning (CL) addresses learning under evolving data distributions but has been largely studied in centralized settings, overlooking key constraints of federated systems, including privacy, limited communication, and client heterogeneity. Federated Continual Learning (FCL) emerges at the intersection of FL and CL, aiming to support lifelong, adaptive, and privacy-aware learning over distributed and non-stationary data. This survey provides a comprehensive and systematic overview of FCL. We first present a formal definition of the FCL problem and clarify its distinctive characteristics. We then analyze the limitations of classical FL under non-stationary conditions, highlighting how CL principles support long-term adaptation. To organize the rapidly growing literature, we propose a multi-dimensional taxonomy of FCL approaches. Furthermore, we review representative application domains and data modalities, summarize commonly used evaluation metrics, and discuss experimental perspectives for assessing long-term performance and forgetting. Finally, we highlight key open challenges, including handling extreme heterogeneity under temporal drift, designing scalable and privacy-preserving memory mechanisms, and establishing standardized benchmarks. This survey aims to serve as a reference and a roadmap for advancing FCL toward robust and deployable real-world systems.

Abstract

Regularization-Based Continual Learning

Explore similar work

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problem

Accurate and Resource-Efficient Federated Continual Learning