AI 中文总结
针对大语言模型微调中分层联邦遗忘面临的挑战，提出HermesHFL框架，通过参数高效微调支持选择性遗忘等。制定统一优化问题，开发Neogen框架解决，实验表明该框架在模型效用等多方面优于现有基线。
AI 中文摘要
大语言模型（LLM）微调中的分层联邦遗忘（HFUL）面临诸多挑战，如分层聚合、动态客户端参与和强参数耦合。选择性去除客户端贡献困难，因为模型更新跨多个聚合阶段传播，且遗忘请求可能与客户端离开和重新加入同时发生。为解决这些问题，我们提出HermesHFL，这是一个分层联邦学习框架，支持选择性遗忘、动态客户端参与和客户端重新集成，通过LoRA的参数高效微调（PEFT）实现可扩展的LLM微调。我们制定了一个统一的优化问题，联合建模异构客户端行为下的客户端参与、边缘关联、激励分配和遗忘。为有效解决此问题，我们开发了Neogen，一种神经引导的双层进化优化框架，结合CMA-ES进行连续激励优化和基于CHC的进化机制进行离散参与和关联决策。神经代理进一步加速优化并提高搜索效率。在LLM微调任务上的大量实验表明，HermesHFL在模型效用、遗忘有效性、收敛稳定性和资源效率方面始终优于现有基线。
英文摘要
Hierarchical federated unlearning (HFUL) for large language model (LLM) fine-tuning faces significant challenges due to hierarchical aggregation, dynamic client participation, and strong parameter coupling in LLM adaptation. Selectively removing client contributions is particularly difficult because model updates propagate across multiple aggregation stages while unlearning requests may coincide with client departures and rejoining. To address these issues, we propose HermesHFL, a hierarchical federated learning framework that supports selective unlearning, dynamic client participation, and client reintegration for scalable LLM fine-tuning via parameter-efficient fine-tuning (PEFT) with LoRA. We formulate a unified optimization problem that jointly models client participation, edge association, incentive allocation, and unlearning under heterogeneous client behaviors. To solve this problem efficiently, we develop Neogen, a neural-guided bilevel evolutionary optimization framework that combines CMA-ES for continuous incentive optimization with a CHC-based evolutionary mechanism for discrete participation and association decisions. A neural surrogate further accelerates optimization and improves search efficiency. Extensive experiments on LLM fine-tuning tasks demonstrate that HermesHFL consistently outperforms state-of-the-art baselines in model utility, unlearning effectiveness, convergence stability, and resource efficiency.
Comments15pages,8 figures
