分而勿忘：持续学习中选择性训练专家的集成
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
AI总结：
提出SEED方法，通过为每个任务仅选择并微调一个最优专家（以高斯分布表示类别），增加专家多样性，在无样本保留的类增量学习中实现最先进性能。
摘要：
类增量学习正变得越来越流行，因为它帮助模型在不忘却已有知识的同时拓宽其适用性。该领域的一个趋势是使用专家混合技术，即不同模型协同工作以解决任务。然而，专家通常使用全部任务数据一次性训练，这使得它们都容易遗忘且增加计算负担。为解决这一局限，我们提出了一种名为SEED的新方法。SEED仅为当前任务选择一个最优专家，并使用该任务的数据仅微调这一专家。为此，每个专家用高斯分布表示每个类别，并基于这些分布的相似性选择最优专家。因此，SEED在保持该集成方法高稳定性的同时，增加了专家内部的多样性和异质性。大量实验表明，SEED在无样本保留设置下的多种场景中达到了最先进的性能，展示了通过数据实现专家多样化在持续学习中的潜力。
英文摘要：
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation, we introduce a novel approach named SEED. SEED selects only one, the most optimal expert for a considered task, and uses data from this task to fine-tune only this expert. For this purpose, each expert represents each class with a Gaussian distribution, and the optimal expert is selected based on the similarity of those distributions. Consequently, SEED increases diversity and heterogeneity within the experts while maintaining the high stability of this ensemble method. The extensive experiments demonstrate that SEED achieves state-of-the-art performance in exemplar-free settings across various scenarios, showing the potential of expert diversification through data in 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。
