STAR: Stability-Inducing Weight Perturbation for Continual Learning

• URL: http://arxiv.org/abs/2503.01595v1
• Date: Mon, 03 Mar 2025 14:32:03 GMT
• Title: STAR: Stability-Inducing Weight Perturbation for Continual Learning
• Authors: Masih Eskandar, Tooba Imtiaz, Davin Hill, Zifeng Wang, Jennifer Dy,
• Abstract summary: A key challenge in continual learning is that as the model is updated to learn new tasks, it becomes susceptible to catastrophic forgetting.<n>A popular approach to mitigate forgetting during continual learning is to maintain a small buffer of previously-seen samples and to replay them during training.<n>We propose a novel loss function, STAR, that exploits the worst-case parameter perturbation that reduces the KL-divergence of model predictions.
• Score: 4.623295991242981
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans can naturally learn new and varying tasks in a sequential manner. Continual learning is a class of learning algorithms that updates its learned model as it sees new data (on potentially new tasks) in a sequence. A key challenge in continual learning is that as the model is updated to learn new tasks, it becomes susceptible to catastrophic forgetting, where knowledge of previously learned tasks is lost. A popular approach to mitigate forgetting during continual learning is to maintain a small buffer of previously-seen samples and to replay them during training. However, this approach is limited by the small buffer size, and while forgetting is reduced, it is still present. In this paper, we propose a novel loss function, STAR, that exploits the worst-case parameter perturbation that reduces the KL-divergence of model predictions with that of its local parameter neighborhood to promote stability and alleviate forgetting. STAR can be combined with almost any existing rehearsal-based method as a plug-and-play component. We empirically show that STAR consistently improves the performance of existing methods by up to 15% across varying baselines and achieves superior or competitive accuracy to that of state-of-the-art methods aimed at improving rehearsal-based continual learning.

Related papers

• Temporal-Difference Variational Continual Learning [89.32940051152782]
  A crucial capability of Machine Learning models in real-world applications is the ability to continuously learn new tasks. In Continual Learning settings, models often struggle to balance learning new tasks with retaining previous knowledge. We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Class incremental learning with probability dampening and cascaded gated classifier [4.285597067389559]
  We propose a novel incremental regularisation approach called Margin Dampening and Cascaded Scaling. The first combines a soft constraint and a knowledge distillation approach to preserve past knowledge while allowing forgetting new patterns. We empirically show that our approach performs well on multiple benchmarks well-established baselines.
  arXiv  Detail & Related papers  (2024-02-02T09:33:07Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Continual Learning Beyond a Single Model [28.130513524601145]
  We show that employing ensemble models can be a simple yet effective method to improve continual performance. We propose a computationally cheap algorithm with similar runtime to a single model yet enjoying the performance benefits of ensembles.
  arXiv  Detail & Related papers  (2022-02-20T14:30:39Z)
• Center Loss Regularization for Continual Learning [0.0]
  In general, neural networks lack the ability to learn different tasks sequentially. Our approach remembers old tasks by projecting the representations of new tasks close to that of old tasks. We demonstrate that our approach is scalable, effective, and gives competitive performance compared to state-of-the-art continual learning methods.
  arXiv  Detail & Related papers  (2021-10-21T17:46:44Z)
• DIODE: Dilatable Incremental Object Detection [15.59425584971872]
  Conventional deep learning models lack the capability of preserving previously learned knowledge. We propose a dilatable incremental object detector (DIODE) for multi-step incremental detection tasks. Our method achieves up to 6.4% performance improvement by increasing the number of parameters by just 1.2% for each newly learned task.
  arXiv  Detail & Related papers  (2021-08-12T09:45:57Z)
• Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning [73.24988226158497]
  We consider the high-impact problem of Data-Free Class-Incremental Learning (DFCIL) We propose a novel incremental distillation strategy for DFCIL, contributing a modified cross-entropy training and importance-weighted feature distillation. Our method results in up to a 25.1% increase in final task accuracy (absolute difference) compared to SOTA DFCIL methods for common class-incremental benchmarks.
  arXiv  Detail & Related papers  (2021-06-17T17:56:08Z)
• Continual Deep Learning by Functional Regularisation of Memorable Past [95.97578574330934]
  Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. We propose a new functional-regularisation approach that utilises a few memorable past examples crucial to avoid forgetting. Our method achieves state-of-the-art performance on standard benchmarks and opens a new direction for life-long learning where regularisation and memory-based methods are naturally combined.
  arXiv  Detail & Related papers  (2020-04-29T10:47:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.