mlsanityData to 7 Oct 2026

Certified Continual Learning for Neural Network Regression

arXiv 2407.06697 ↗First posted 9 Jul 2024cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural networks in practice are often re-trained over time to cope with new data distribution or for solving different tasks (a.k.a. continual learning). Once re-trained, the verified correctness of the neural network is likely broken, particularly in the presence of the phenomenon known as catastrophic forgetting. In this work, we propose an approach called certified continual learning which improves existing continual learning methods by preserving, as long as possible, the established correctness properties of a verified network. Our approach is evaluated with multiple neural networks and on two different continual learning methods. The results show that our approach is efficient and the trained models preserve their certified correctness and often maintain high utility.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 38 of its 61 references that are in the map. First posted on arXiv 9 Jul 2024.

Builds on

38 of 61 references.

References · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2016Learning without Forgettingcited by 2,465
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  9. 2016Progressive Neural Networkscited by 1,332
  10. 2017Continual Learning with Deep Generative Replaycited by 1,152
  11. 2018Experience Replay for Continual Learningcited by 1,074
  12. 2016End to End Learning for Self-Driving Carscited by 1,000
26 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  3. 2019Three scenarios for continual learningcited by 610
  4. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  5. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  6. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  7. 2017Variational Continual Learningcited by 335
  8. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  9. 2018Certified Defenses against Adversarial Examplescited by 305
  10. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  11. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  12. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 197
  13. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 183
  14. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  15. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  16. 2018Generative replay with feedback connections as a general strategy for continual learningcited by 103
  17. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
  18. 2020Verification of Deep Convolutional Neural Networks Using ImageStarscited by 75
  19. 2018Training verified learners with learned verifierscited by 50
  20. 2020Continual Learning for Anomaly Detection in Surveillance Videoscited by 49
  21. 2018Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgettingcited by 46
  22. 2022Causality-based Neural Network Repaircited by 44
  23. 2021Provable Repair of Deep Neural Networkscited by 39
  24. 2021Probabilistic Verification of Neural Networks Against Group Fairnesscited by 17
  25. 2022NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training Historycited by 8
  26. 2020SOCRATES: Towards a Unified Platform for Neural Network Analysiscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Verification of Bit-Flip Attacks against Quantized Neural Networkscited by 2
  2. 2025A Comprehensive Study of Deep Learning Model Fixing Approachescited by 2
  3. 2026Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offscited by 1
  4. 2025Towards provable probabilistic safety for scalable embodied AI systemscited by 0
  5. 2026Continual Learning for non-stationary regression via Memory-Efficient Replaycited by 0