mlsanityData to 7 Oct 2026

Kernel Continual Learning

arXiv 2107.05757 ↗First posted 12 Jul 2021cs.LG cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific classifiers based on kernel ridge regression. This does not require memory replay and systematically avoids task interference in the classifiers. We further introduce variational random features to learn a data-driven kernel for each task. To do so, we formulate kernel continual learning as a variational inference problem, where a random Fourier basis is incorporated as the latent variable. The variational posterior distribution over the random Fourier basis is inferred from the coreset of each task. In this way, we are able to generate more informative kernels specific to each task, and, more importantly, the coreset size can be reduced to achieve more compact memory, resulting in more efficient continual learning based on episodic memory. Extensive evaluation on four benchmarks demonstrates the effectiveness and promise of kernels for continual learning.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 40 of its 59 references that are in the map. First posted on arXiv 12 Jul 2021.

Builds on

40 of 59 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  8. 2016Progressive Neural Networkscited by 1,332
  9. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  10. 2017Continual Learning with Deep Generative Replaycited by 1,152
  11. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  12. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
28 more
  1. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  2. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  3. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  4. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  5. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  6. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  7. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  8. 2015Deep Kernel Learningcited by 440
  9. 2017Variational Continual Learningcited by 335
  10. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  11. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  12. 2020Supermasks in Superpositioncited by 223
  13. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 197
  14. 2020Understanding the Role of Training Regimes in Continual Learningcited by 177
  15. 2020Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semanticscited by 158
  16. 2019Functional Regularisation for Continual Learning with Gaussian Processescited by 121
  17. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  18. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  19. 2018Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilizationcited by 104
  20. 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 100
  21. 2020Continual Learning in Low-rank Orthogonal Subspacescited by 99
  22. 2016Stochastic Variational Deep Kernel Learningcited by 92
  23. 2018Learning with SGD and Random Featurescited by 33
  24. 2020Learning to Learn Kernels with Variational Random Featurescited by 18
  25. 2019Adaptive Deep Kernel Learningcited by 15
  26. 2016Multi-task and Lifelong Learning of Kernelscited by 7
  27. 2018Closed-Loop Memory GAN for Continual Learningcited by 7
  28. 2019Attention-Based Structural-Plasticitycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 8; 2024: 4; 2025: 2; 2026: 4.

27 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  3. 2022Remember the Past: Distilling Datasets into Addressable Memories for Neural Networkscited by 104
  4. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  5. 2022Bayesian Prompt Learning for Image-Language Model Generalizationcited by 51
  6. 2022Architecture Matters in Continual Learningcited by 46
  7. 2022LifeLonger: A Benchmark for Continual Disease Classificationcited by 28
  8. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  9. 2023Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospectscited by 22
  10. 2022Continual Variational Autoencoder Learning via Online Cooperative Memorizationcited by 12
  11. 2024Never-Ending Behavior-Cloning Agent for Robotic Manipulationcited by 10
  12. 2025FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Datacited by 5
15 more
  1. 2023Few-shot Class-incremental Learning for Cross-domain Disease Classificationcited by 4
  2. 2026Lifelong Language-Conditioned Robotic Manipulation Learningcited by 4
  3. 2023OER: Offline Experience Replay for Continual Offline Reinforcement Learningcited by 3
  4. 2024Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognitioncited by 3
  5. 2026Lifelong Embodied Navigation Learningcited by 3
  6. 2023On the Effectiveness of Equivariant Regularization for Robust Online Continual Learningcited by 2
  7. 2023EMO: Episodic Memory Optimization for Few-Shot Meta-Learningcited by 2
  8. 2024Informed Spectral Normalized Gaussian Processes for Trajectory Predictioncited by 2
  9. 2023SequeL: A Continual Learning Library in PyTorch and JAXcited by 1
  10. 2024Selective Attention-based Modulation for Continual Learningcited by 1
  11. 2026All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptationcited by 1
  12. 2021Generative Kernel Continual learningcited by 0
  13. 2023Hierarchical Memory Pool Based Edge Semi-Supervised Continual Learning Methodcited by 0
  14. 2025Incrementally Learning Multiple Diverse Data Domains via Multi-Source Dynamic Expansion Modelcited by 0
  15. 2026Information as Structural Alignment: A Dynamical Theory of Continual Learningcited by 0