动态专家混合模型应对数据分布剧烈变化，缓解遗忘问题。
Dynamic Mixture of Experts Against Severe Distribution Shifts
- 引入动态专家混合架构，按需激活专用专家处理不同数据分布。
- 在持续学习和强化学习场景中显著降低灾难性遗忘，性能优于传统扩展方法。
- 无需任务标识，适合真实世界中未知分布流的在线学习任务。
构建能够持续学习并适应不断变化数据流的神经网络，是持续学习（CL）和强化学习（RL）的核心挑战。这一终身学习问题常被表述为可塑性-稳定性困境，涉及可塑性丧失和灾难性遗忘等问题。与神经网络不同，生物大脑通过容量增长保持可塑性，这启发研究者探索在人工网络中动态增加容量的方法。以往方案往往缺乏参数效率或依赖显式任务索引，而专家混合（Mixture-of-Experts, MoE）架构通过为不同分布分配专用专家提供了有前景的替代方案。本文旨在评估动态MoE在持续学习与强化学习环境中的表现，并与现有网络扩展方法进行基准对比。
原文摘要 · Abstract (English)
The challenge of building neural networks that can continuously learn and adapt to evolving data streams is central to the fields of continual learning (CL) and reinforcement learning (RL). This lifelong learning problem is often framed in terms of the plasticity-stability dilemma, focusing on issues like loss of plasticity and catastrophic forgetting. Unlike neural networks, biological brains maintain plasticity through capacity growth, inspiring researchers to explore similar approaches in artificial networks, such as adding capacity dynamically. Prior solutions often lack parameter efficiency or depend on explicit task indices, but Mixture-of-Experts (MoE) architectures offer a promising alternative by specializing experts for distinct distributions. This paper aims to evaluate a DynamicMoE approach for continual and reinforcement learning environments and benchmark its effectiveness against existing network expansion methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。