IDER：惰性经验重放用于可靠的持续学习
IDER: IDempotent Experience Replay for Reliable Continual Learning
AI总结：
IDER通过惰性性质提出新的经验重放方法，提升持续学习的可靠性与准确性，减少遗忘问题。
摘要：
灾难性遗忘，即神经网络在学习新任务时倾向于忘记之前学到的知识，一直是持续学习（CL）中的主要挑战。为解决这一挑战，已经提出了多种持续学习方法，并已证明这些方法可以减少遗忘。此外，在关键任务设置中部署的持续学习模型可以受益于不确定性意识，通过校准其预测以可靠地评估其置信度。然而，现有的不确定性意识持续学习方法存在计算开销大和与主流重放方法不兼容的问题。为了解决这个问题，我们提出了基于惰性性质的惰性经验重放（IDER），即重复函数应用产生相同输出的性质。具体来说，我们首先调整训练损失，使模型在当前数据流上变得惰性。此外，我们引入了惰性蒸馏损失。我们将当前模型的输出反馈到旧检查点，然后最小化重新处理输出与当前模型原始输出之间的距离。这产生了一个简单而有效的新的基线，用于构建可靠的持续学习器，可以无缝集成到其他持续学习方法中。在不同的持续学习基准上的广泛实验表明，IDER在提高预测可靠性的同时，同时提高了准确性和减少了遗忘。我们的结果表明，惰性作为部署高效且可信赖的持续学习系统的原则具有潜力，这在现实应用中是很有前景的。我们的代码可在https://github.com/YutingLi0606/Idempotent-Continual-Learning上找到。
英文摘要：
Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and shown to reduce forgetting. Furthermore, CL models deployed in mission-critical settings can benefit from uncertainty awareness by calibrating their predictions to reliably assess their confidences. However, existing uncertainty-aware continual learning methods suffer from high computational overhead and incompatibility with mainstream replay methods. To address this, we propose idempotent experience replay (IDER), a novel approach based on the idempotent property where repeated function applications yield the same output. Specifically, we first adapt the training loss to make model idempotent on current data streams. In addition, we introduce an idempotence distillation loss. We feed the output of the current model back into the old checkpoint and then minimize the distance between this reprocessed output and the original output of the current model. This yields a simple and effective new baseline for building reliable continual learners, which can be seamlessly integrated with other CL approaches. Extensive experiments on different CL benchmarks demonstrate that IDER consistently improves prediction reliability while simultaneously boosting accuracy and reducing forgetting. Our results suggest the potential of idempotence as a promising principle for deploying efficient and trustworthy continual learning systems in real-world applications.Our code is available at https://github.com/YutingLi0606/Idempotent-Continual-Learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
