Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning

• URL: http://arxiv.org/abs/2308.01698v1
• Date: Thu, 3 Aug 2023 11:33:50 GMT
• Title: Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning
• Authors: Yuhang Zhou, Jiangchao Yao, Feng Hong, Ya Zhang, and Yanfeng Wang
• Abstract summary: Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples. Memory-replay CIL consolidates old knowledge by replaying a small number of old classes of samples saved in the memory. Our theoretical analysis shows that the destruction of old knowledge can be effectively alleviated by balancing the contribution of samples from the current phase and those saved in the memory.
• Score: 27.117753965919025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e., catastrophic forgetting, the mainstream paradigm is memory-replay CIL, which consolidates old knowledge by replaying a small number of old classes of samples saved in the memory. Despite effectiveness, the inherent destruction-reconstruction dynamics in memory-replay CIL are an intrinsic limitation: if the old knowledge is severely destructed, it will be quite hard to reconstruct the lossless counterpart. Our theoretical analysis shows that the destruction of old knowledge can be effectively alleviated by balancing the contribution of samples from the current phase and those saved in the memory. Motivated by this theoretical finding, we propose a novel Balanced Destruction-Reconstruction module (BDR) for memory-replay CIL, which can achieve better knowledge reconstruction by reducing the degree of maximal destruction of old knowledge. Specifically, to achieve a better balance between old knowledge and new classes, the proposed BDR module takes into account two factors: the variance in training status across different classes and the quantity imbalance of samples from the current phase and memory. By dynamically manipulating the gradient during training based on these factors, BDR can effectively alleviate knowledge destruction and improve knowledge reconstruction. Extensive experiments on a range of CIL benchmarks have shown that as a lightweight plug-and-play module, BDR can significantly improve the performance of existing state-of-the-art methods with good generalization.

Related papers

• Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning [64.93848182403116]
  Current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. We introduce the Stable Hadamard Memory, a novel memory model for reinforcement learning agents. Our approach significantly outperforms state-of-the-art memory-based methods on challenging partially observable benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T03:50:17Z)
• Fine-Grained Gradient Restriction: A Simple Approach for Mitigating Catastrophic Forgetting [41.891312602770746]
  Gradient Episodic Memory (GEM) achieves balance by utilizing a subset of past training samples to restrict the update direction of the model parameters. We show that memory strength is effective mainly because it improves GEM's ability generalization and therefore leads to a more favorable trade-off.
  arXiv  Detail & Related papers  (2024-10-01T17:03:56Z)
• Balanced Residual Distillation Learning for 3D Point Cloud Class-Incremental Semantic Segmentation [13.627816749091727]
  Class-incremental learning (CIL) thrives due to its success in processing the influx of information by learning from continuously added new classes. We propose a novel balanced residual distillation framework (BRD-CIL) to push the performance bar of CIL to a new higher level.
  arXiv  Detail & Related papers  (2024-08-02T16:09:06Z)
• TEAL: New Selection Strategy for Small Buffers in Experience Replay Class Incremental Learning [7.627299398469962]
  We introduce TEAL, a novel approach to populate the memory with exemplars. We show that TEAL improves the average accuracy of the SOTA method XDER as well as ER and ER-ACE on several image recognition benchmarks.
  arXiv  Detail & Related papers  (2024-06-30T12:09:08Z)
• Few-Shot Class-Incremental Learning with Prior Knowledge [94.95569068211195]
  We propose Learning with Prior Knowledge (LwPK) to enhance the generalization ability of the pre-trained model. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-02-02T08:05:35Z)
• Class-Incremental Learning: A Survey [84.30083092434938]
  Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally. CIL tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. We provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms.
  arXiv  Detail & Related papers  (2023-02-07T17:59:05Z)
• A Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)
• Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning [113.58691755215663]
  We develop RetroPrompt to help a model strike a balance between generalization and memorization. In contrast with vanilla prompt learning, RetroPrompt constructs an open-book knowledge-store from training instances. Extensive experiments demonstrate that RetroPrompt can obtain better performance in both few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2022-05-29T16:07:30Z)
• Brain-inspired feature exaggeration in generative replay for continual learning [4.682734815593623]
  When learning new classes, the internal representation of previously learnt ones can often be overwritten. Recent developments in neuroscience have uncovered a method through which the brain avoids its own form of memory interference. This paper presents a new state-of-the-art performance on the classification of early classes in the class-incremental learning dataset CIFAR100.
  arXiv  Detail & Related papers  (2021-10-26T10:49:02Z)
• Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting [100.75479161884935]
  We propose a novel training paradigm called Remembering for the Right Reasons (RRR) RRR stores visual model explanations for each example in the buffer and ensures the model has "the right reasons" for its predictions. We demonstrate how RRR can be easily added to any memory or regularization-based approach and results in reduced forgetting.
  arXiv  Detail & Related papers  (2020-10-04T10:05:27Z)

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.