Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests that structural collapse leads to loss of plasticity, as evidenced by changes in effective rank (eRank). This indicates a link to forgetting, since the networks lose the ability to expand their feature space to learn new tasks, which forces the network to overwrite existing representations. Therefore, in this study, we investigate the correlation between forgetting and collapse through the measurement of both weight and activation eRank. To be more specific, we evaluated four architectures, including MLP, ConvGRU, ResNet-18, and Bi-ConvGRU, in the split MNIST and Split CIFAR-100 benchmarks. Those models are trained through the SGD, Learning-without-Forgetting (LwF), and Experience Replay (ER) strategies separately. The results demonstrate that forgetting and collapse are strongly related, and different continual learning strategies help models preserve both capacity and performance in different efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse
While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where las…
Continual LearningOn Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks
In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual lear…
Continual LearningMitigating Mode Collapse by Sidestepping Catastrophic Forgetting
Generative Adversarial Networks (GANs) are a class of generative models used for various applications, but they have been known to suffer from the mode collapse problem, in which some modes of the target distribution are…
Continual LearningOvercoming Mode Collapse with Adaptive Multi Adversarial Training
Generative Adversarial Networks (GANs) are a class of generative models used for various applications, but they have been known to suffer from the mode collapse problem, in which some modes of the target distribution are…
Continual LearningTowards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximization
In our dynamic world where data arrives in a continuous stream, continual learning enables us to incrementally add new tasks/domains without the need to retrain from scratch. A major challenge in continual learning of la…
Continual LearningData AugmentationDiversityLanguage Modeling+1