mlsanityData to 7 Oct 2026

Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach

arXiv 2407.09039 ↗First posted 12 Jul 2024cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new methodology, coined as Tabular-data Rehearsal-based Incremental Lifelong Learning framework (TRIL3), designed to address the phenomenon of catastrophic forgetting in tabular data classification problems. TRIL3 uses the prototype-based incremental generative model XuILVQ to generate synthetic data to preserve old knowledge and the DNDF algorithm, which was modified to run in an incremental way, to learn classification tasks for tabular data, without storing old samples. After different tests to obtain the adequate percentage of synthetic data and to compare TRIL3 with other CL available proposals, we can conclude that the performance of TRIL3 outstands other options in the literature using only 50% of synthetic data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 30 of its 64 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

30 of 64 references.

References · 30

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  4. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  6. 2017Continual Learning with Deep Generative Replaycited by 1,152
  7. 2020Learning under Concept Drift: A Reviewcited by 470
  8. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  9. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  10. 2019On Tiny Episodic Memories in Continual Learningcited by 299
  11. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  12. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
18 more
  1. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  2. 2018Generative replay with feedback connections as a general strategy for continual learningcited by 103
  3. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 92
  4. 2021Rehearsal revealed: The limits and merits of revisiting samples in continual learningcited by 76
  5. 2020Gradient-based Editing of Memory Examples for Online Task-free Continual Learningcited by 62
  6. 2017Deep Generative Dual Memory Network for Continual Learningcited by 59
  7. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  8. 2018Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgettingcited by 46
  9. 2023Avalanche: A PyTorch Library for Deep Continual Learningcited by 33
  10. 2021An Investigation of Replay-based Approaches for Continual Learningcited by 26
  11. 2018Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networkscited by 23
  12. 2022Task-Free Continual Learning via Online Discrepancy Distance Learningcited by 22
  13. 2021Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturingcited by 19
  14. 2019Overcoming Catastrophic Forgetting by Generative Regularizationcited by 13
  15. 2023Continual Learning with Dirichlet Generative-based Rehearsalcited by 7
  16. 2021Continual learning of longitudinal health recordscited by 5
  17. 2023Decentralised and collaborative machine learning framework for IoTcited by 4
  18. 2022Continual Learning with Invertible Generative Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Tree of Concepts: Interpretable Continual Learners in Non-Stationary Clinical Domainscited by 1
  2. 2025Continual Learning at the Edge: An Agnostic IIoT Architecturecited by 0
  3. 2026Continual Learning for non-stationary regression via Memory-Efficient Replaycited by 0
  4. 2026MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Boundcited by 0
  5. 2026Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classificationcited by 0