Shapley神经元值用于持续学习：哪些神经元最为关键？
Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
AI总结：
本文提出Shapley神经元估值框架，通过量化持续学习中神经元重要性，实现无缓冲的持续学习，实验显示其在类别增量学习和任务增量学习中分别提升准确率2.88%和6.46%。
摘要：
持续学习使神经网络能够按顺序学习任务而不遗忘先前知识。然而，神经网络面临灾难性遗忘问题，即学习新任务会降低先前任务的性能。我们通过Shapley神经元估值（SNV）解决此问题，该框架基于合作博弈理论，量化持续学习中的神经元重要性。SNV选择性冻结重要神经元，保持其他神经元的可塑性，实现无缓冲的持续学习，无需扩展架构。在ImageNet-1k实验中，SNV在类别增量学习和任务增量学习场景中分别比第二基准方法提升准确率2.88%和6.46%。
英文摘要：
Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgetting, where learning new tasks degrades performance on earlier ones. We address this problem with Shapley Neuron Valuation (SNV), a principled framework that quantifies Neuron importance in continual learning, grounded in cooperative game theory. SNV selectively freezes important Neurons while keeping others plastic, enabling buffer-free continual learning without expanding architecture. Experiments on ImageNet-1k show that SNV consistently outperforms existing buffer-free methods. In particular, SNV improves accuracy by +2.88% in the class incremental learning and +6.46% in the task incremental learning scenarios compared to the second baseline.
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。
