Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Recall-Oriented Continual Learning with Generative Adversarial Meta-Model (2403.03082v1)

Published 5 Mar 2024 in cs.LG, cs.AI, and cs.CV

Abstract: The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the recall-oriented continual learning framework to address this challenge. Inspired by the human brain's ability to separate the mechanisms responsible for stability and plasticity, our framework consists of a two-level architecture where an inference network effectively acquires new knowledge and a generative network recalls past knowledge when necessary. In particular, to maximize the stability of past knowledge, we investigate the complexity of knowledge depending on different representations, and thereby introducing generative adversarial meta-model (GAMM) that incrementally learns task-specific parameters instead of input data samples of the task. Through our experiments, we show that our framework not only effectively learns new knowledge without any disruption but also achieves high stability of previous knowledge in both task-aware and task-agnostic learning scenarios. Our code is available at: https://github.com/bigdata-inha/recall-oriented-cl-framework.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Uncertainty-based Continual Learning with Adaptive Regularization. In Advances in Neural Information Processing Systems.
  2. Wasserstein generative adversarial networks. In International conference on machine learning, 214–223. PMLR.
  3. Weight uncertainty in neural network. In International conference on machine learning, 1613–1622. PMLR.
  4. Bulatov, Y. 2011. Notmnist dataset. Google (Books/OCR). Technical report, Tech. Rep.[Online]. Available: http://yaroslavvb. blogspot. it/2011/09 ….
  5. Dark Experience for General Continual Learning: a Strong, Simple Baseline. In Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020.
  6. Efficient Lifelong Learning with A-GEM. In International Conference on Learning Representations.
  7. Continual Learning with Tiny Episodic Memories. arXiv preprint arXiv:1902.10486, 2019.
  8. A Cluster Separation Measure. IEEE Trans. Pattern Anal. Mach. Intell., 1(2): 224–227.
  9. Uncertainty-guided Continual Learning with Bayesian Neural Networks. In International Conference on Learning Representations.
  10. Adversarial continual learning. In The European Conference on Computer Vision, 386–402.
  11. Fisher, R. A. 1936. The use of multiple measurements in taxonomic problems. Annals of eugenics, 7(2): 179–188.
  12. Generative Adversarial Nets. In Ghahramani, Z.; Welling, M.; Cortes, C.; Lawrence, N.; and Weinberger, K., eds., Advances in Neural Information Processing Systems, volume 27, 2672–2680.
  13. Improved Training of Wasserstein GANs. In Advances in Neural Information Processing Systems, 5767–5777.
  14. HyperNetworks. In International Conference on Learning Representations.
  15. Deep Residual Learning for Image Recognition. In Conference on Computer Vision and Pattern Recognition, 770–778.
  16. Posterior Meta-Replay for Continual Learning. In Advances in Neural Information Processing Systems.
  17. Averaging Weights Leads to Wider Optima and Better Generalization. In Uncertainty in Artificial Intelligence.
  18. Meta-Consolidation for Continual Learning. In Advances in Neural Information Processing Systems.
  19. FearNet: Brain-Inspired Model for Incremental Learning. In International Conference on Learning Representations.
  20. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.
  21. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13): 3521–3526.
  22. Learning multiple layers of features from tiny images.
  23. Bayesian hypernetworks. arXiv preprint arXiv:1710.04759.
  24. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. In Advances in Neural Information Processing Systems.
  25. Gradient-based learning applied to document recognition. Proc. IEEE, 86(11): 2278–2324.
  26. Gradient episodic memory for continual learning. Advances in neural information processing systems, 30.
  27. Multi-Domain Multi-Task Rehearsal for Lifelong Learning. In Thirty-Fifth AAAI Conference on Artificial Intelligence.
  28. A Simple Baseline for Bayesian Uncertainty in Deep Learning. In Advances in Neural Information Processing Systems.
  29. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 7765–7773.
  30. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review, 102(3): 419.
  31. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation, volume 24, 109–165. Elsevier.
  32. Reading digits in natural images with unsupervised feature learning.
  33. Learning to remember: A synaptic plasticity driven framework for continual learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 11321–11329.
  34. Complementary learning systems. Cognitive science, 38(6): 1229–1248.
  35. Continual lifelong learning with neural networks: A review. Neural Networks, 113: 54–71.
  36. HyperGAN: A Generative Model for Diverse, Performant Neural Networks. In Proceedings of the 36th International Conference on Machine Learning, 5361–5369.
  37. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2001–2010.
  38. Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference. In International Conference on Learning Representations.
  39. Gradient Projection Memory for Continual Learning. In International Conference on Learning Representations.
  40. The cognitive neuroscience of constructive memory: remembering the past and imagining the future. Philosophical Transactions of the Royal Society B: Biological Sciences, 362(1481): 773–786.
  41. Overcoming Catastrophic Forgetting with Hard Attention to the Task. In Dy, J. G.; and Krause, A., eds., Proceedings of the International Conference on Machine Learning.
  42. Continual Learning with Deep Generative Replay. In Advances in Neural Information Processing Systems, 2990–2999.
  43. Brain-inspired replay for continual learning with artificial neural networks. Nature communications, 11(1): 1–14.
  44. Three types of incremental learning. Nature Machine Intelligence, 1–13.
  45. Continual learning with hypernetworks. In International Conference on Learning Representations.
  46. Adversarial Distillation of Bayesian Neural Network Posteriors. In Proceedings of the 35th International Conference on Machine Learning, 5177–5186.
  47. Memory Replay GANs: Learning to Generate New Categories without Forgetting. In Advances in Neural Information Processing Systems.
  48. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747.
  49. Lifelong Learning with Dynamically Expandable Networks. In International Conference on Learning Representations.
  50. Continual Learning Through Synaptic Intelligence. In Proceedings of the International Conference on Machine Learning.
  51. HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning. In International Conference on Machine Learning, 27075–27098.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Haneol Kang (1 paper)
  2. Dong-Wan Choi (10 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now