用意见动态模型实现个性化与抗攻击的分布式学习
Personalized and Resilient Distributed Learning Through Opinion Dynamics
- 融合梯度下降与意见动力学，实现个性化模型学习
- 在恶意节点存在下仍保持高全局准确率
- 参数可调，兼顾个性化与系统韧性
本文针对多智能体网络系统中分布式学习的两大实际挑战——个性化与鲁棒性展开研究。个性化要求异构智能体基于自身数据和任务训练专属模型，同时保持良好泛化能力；而学习过程必须抵御网络攻击或异常数据干扰。受二者概念相似性的启发，我们提出一种结合分布式梯度下降与Friedkin-Johnsen意见动力学模型的算法，可同时满足上述需求。理论分析给出了收敛速度及最终模型所在邻域的量化结果，可通过调节参数灵活控制个性化或鲁棒性强度。数值实验在合成与真实数据集上验证了该方法的有效性，在存在恶意节点的情况下，其个性化模型的全局准确率显著优于标准策略。
原文摘要 · Abstract (English)
In this paper, we address two practical challenges of distributed learning in multi-agent network systems, namely personalization and resilience. Personalization is the need of heterogeneous agents to learn local models tailored to their own data and tasks, while still generalizing well; on the other hand, the learning process must be resilient to cyberattacks or anomalous training data to avoid disruption. Motivated by a conceptual affinity between these two requirements, we devise a distributed learning algorithm that combines distributed gradient descent and the Friedkin-Johnsen model of opinion dynamics to fulfill both of them. We quantify its convergence speed and the neighborhood that contains the final learned models, which can be easily controlled by tuning the algorithm parameters to enforce a more personalized/resilient behavior. We numerically showcase the effectiveness of our algorithm on synthetic and real-world distributed learning tasks, where it achieves high global accuracy both for personalized models and with malicious agents compared to standard strategies.
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。