发表机构
Université Côte d’Azur（蔚蓝海岸大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究构建多目标优化框架下的去中心化协作持续学习方法，通过智能体本地存储过往样本、相邻智能体信息交换，解决稳定性-可塑性困境，可减少遗忘并提升跨任务平均均方偏差。
AI 中文摘要
在本研究中，我们将去中心化持续学习构建于多目标优化框架内。对于给定的推理任务t（对应于所有智能体代价函数共享的公共极小值），以分布式流式方式收集数据的智能体仅被允许执行局部计算，并通过底层通信图与相邻智能体交换信息。随着任务随时间依次演进，智能体必须适应新到达的任务，同时保留从先前学习任务中获得的知识。这一需求引发了著名的稳定性-可塑性困境：稳定性指保留先前知识的能力，可塑性指学习并适应新任务的能力。为解决稳定性挑战，智能体将过往任务的样本子集存储在本地内存缓冲区中。随后，通过恰当的多目标公式，存储的信息被整合至学习过程，使参数更新同时考虑当前任务与先前学习任务。我们在对个体代价函数和梯度噪声过程的一般假设下，从均方误差角度对所提出的去中心化持续学习方法进行了分析。分析表明，智能体间的合作可提升持续学习的性能。具体而言，通过与相邻智能体交换信息，去中心化协作学习能够利用局部观测数据和内存缓冲区的多样性，以提升跨任务的网络平均均方偏差（MSD）。最后，仿真结果验证了理论发现，以及该方法在减少遗忘、提升跨任务平均MSD方面的有效性。
英文摘要
In this work, we formulate decentralized continual learning within a multi-objective optimization framework. For a given inference task t (corresponding to a common minimizer shared by the cost functions of all agents), agents collecting data in a distributed and streamed manner are only allowed to perform local computations and to exchange information with neighboring agents over the underlying communication graph. As tasks evolve sequentially over time, agents must adapt to newly arriving tasks while retaining knowledge acquired from previously learned ones. This requirement leads to the wellknown stability plasticity dilemma, where stability refers to the ability to retain previous knowledge, while plasticity refers to the ability to learn and adapt to new tasks. To address the stability challenge, agents store subsets of samples from past tasks in local memory buffers. Then, through an appropriate multiobjective formulation, the stored information is incorporated into the learning process so that parameter updates account jointly for the current task and previously learned tasks. The proposed decentralized continual learning approach is analyzed in the mean square error sense under general assumptions on the individual cost functions and gradient noise processes. The analysis reveals that cooperation among agents improves the performance of continual learning. In particular, by exchanging information with neighboring agents, decentralized collaborative learning can exploit the diversity of locally observed data and memory buffers to improve the network average mean-square deviation (MSD) across tasks. Finally, simulations illustrate the theoretical findings and the effectiveness of the method in reducing forgetting and improving the average MSD across tasks.
