mlsanityData to 14 Oct 2026

Continual Learning in Practice

arXiv 1903.05202 ↗First posted 12 Mar 2019stat.ML cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and adapt to new tasks. This represents continual AutoML or Automatically Adaptive Machine Learning. We describe the challenges and proposes a reference architecture.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 11; 2023: 5; 2024: 4; 2025: 1.

28 papers.

Sort:

  1. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  2. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  3. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  4. 2022Multiplayer Performative Prediction: Learning in Decision-Dependent Gamescited by 44
  5. 2021DualNet: Continual Learning, Fast and Slowcited by 39
  6. 2022Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractorcited by 27
  7. 2021Knowledge-Adaptation Priorscited by 20
  8. 2021Continual Learning in Deep Networks: an Analysis of the Last Layercited by 17
  9. 2024On the Diminishing Returns of Width for Continual Learningcited by 12
  10. 2023Continual Learning for Predictive Maintenance: Overview and Challengescited by 10
  11. 2022Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrapcited by 9
  12. 2023Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insightscited by 8
16 more
  1. 2022Explanation Shift: Detecting distribution shifts on tabular data via the explanation spacecited by 7
  2. 2023Explanation Shift: How Did the Distribution Shift Impact the Model?cited by 6
  3. 2021Desiderata for Explainable AI in statistical production systems of the European Central Bankcited by 5
  4. 2022An Empirical Evaluation of Flow Based Programming in the Machine Learning Deployment Contextcited by 5
  5. 2022Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation of Predictive Modelscited by 5
  6. 2023Modyn: Data-Centric Machine Learning Pipeline Orchestrationcited by 5
  7. 2025Sequence Transferability and Task Order Selection in Continual Learningcited by 5
  8. 2021Towards better data discovery and collection with flow-based programmingcited by 3
  9. 2021On The Reliability Of Machine Learning Applications In Manufacturing Environmentscited by 3
  10. 2022Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddingscited by 3
  11. 2024Balancing Continual Learning and Fine-tuning for Human Activity Recognitioncited by 3
  12. 2024Towards Stable Machine Learning Model Retraining via Slowly Varying Sequencescited by 2
  13. 2022Introducing explainable supervised machine learning into interactive feedback loops for statistical production systemcited by 0
  14. 2022Improving Feature Generalizability with Multitask Learning in Class Incremental Learningcited by 0
  15. 2022Continual Learning, Fast and Slowcited by 0
  16. 2024Development of an End-to-end Machine Learning System with Application to In-app Purchasescited by 0