mlsanityData to 14 Oct 2026

KAC: Kolmogorov-Arnold Classifier for Continual Learning

arXiv 2503.21076 ↗First posted 27 Mar 2025cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks. Inspired by the success of Kolmogorov-Arnold Networks (KAN) in preserving learning stability during simple continual regression tasks, we set out to explore their potential in more complex continual learning scenarios. In this paper, we introduce the Kolmogorov-Arnold Classifier (KAC), a novel classifier developed for continual learning based on the KAN structure. We delve into the impact of KAN's spline functions and introduce Radial Basis Functions (RBF) for improved compatibility with continual learning. We replace linear classifiers with KAC in several recent approaches and conduct experiments across various continual learning benchmarks, all of which demonstrate performance improvements, highlighting the effectiveness and robustness of KAC in continual learning. The code is available at https://github.com/Ethanhuhuhu/KAC.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 39 of its 60 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

39 of 60 references.

References · 39

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2016Learning without Forgettingcited by 2,496
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  4. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  6. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  7. 2017Continual Learning with Deep Generative Replaycited by 1,158
  8. 2021Learning to Prompt for Continual Learningcited by 944
  9. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  10. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 642
  11. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 450
  12. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
27 more
  1. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  2. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  3. 2023SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Modelcited by 180
  4. 2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 128
  5. 2023A Unified Continual Learning Framework with General Parameter-Efficient Tuningcited by 125
  6. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 122
  7. 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimalitycited by 121
  8. 2024Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learningcited by 117
  9. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  10. 2020A Comprehensive Study of Class Incremental Learning Algorithms for Visual Taskscited by 107
  11. 2016Why does deep and cheap learning work so well?cited by 100
  12. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 87
  13. 2024TKAN: Temporal Kolmogorov-Arnold Networkscited by 71
  14. 2024fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functionscited by 64
  15. 2024KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physicscited by 59
  16. 2024Consistent Prompting for Rehearsal-Free Continual Learningcited by 54
  17. 2019Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theoremcited by 49
  18. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 49
  19. 2024SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detectioncited by 44
  20. 2022Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentationcited by 37
  21. 2022Long-Tailed Class Incremental Learningcited by 36
  22. 2024Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problemscited by 35
  23. 2024Kolmogorov-Arnold Graph Neural Networkscited by 32
  24. 2023Dynamic Residual Classifier for Class Incremental Learningcited by 26
  25. 2023On the Optimal Expressive Power of ReLU DNNs and Its Application in Approximation with Kolmogorov Superposition Theoremcited by 13
  26. 2023Cross-Class Feature Augmentation for Class Incremental Learningcited by 8
  27. 2023Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensionscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Improving Memory Efficiency for Training KANs via Meta Learningcited by 3
  2. 2025Unifying Locality of KANs and Feature Drift Compensation Projection for Data-free Replay based Continual Face Forgery Detectioncited by 1
  3. 2025BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understandingcited by 0
  4. 2026Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networkscited by 0