为低碳联邦学习设计自适应架构搜索，提升用户参与稳定性。
Designing Sustainable Federated Learning as a Service using Neural Architecture Search
- 基于消费者碳约束构建需求驱动的搜索空间，提前筛选可行模型。
- 动态评估候选架构碳足迹，保障训练在硬性碳限下可持续。
- 智能调度策略兼顾性能、可行性与数据覆盖，适合绿色计算场景。
FLaaS（联邦学习即服务）消费者的可持续性约束给碳排放可行的联邦训练带来重大挑战，常导致不可行的用户参与和不稳定的训练过程。本文提出可持续联邦学习即服务（SFLaaS），一种面向异构可持续约束的碳约束神经架构搜索框架。通过需求驱动的搜索空间，将消费者可持续性画像转化为执行前的可行架构区域；设计消费者级别的碳可行性估计机制，动态评估候选架构在变化碳条件下的表现；提出可持续的消费者调度策略，自适应选择可行用户并分配本地任务，以维持用户参与度与统计数据覆盖。采用进化搜索策略，在硬性碳约束下联合优化预测性能、用户可行性与参与覆盖率。在真实数据集与模拟环境中的实验验证了该方法的有效性。
原文摘要 · Abstract (English)
The sustainability constraints of FLaaS consumers pose significant challenges to maintaining carbon-feasible federated training in FLaaS environments. These constraints often lead to infeasible consumer participation and unstable federated training under hard carbon constraints. We propose a Sustainable Federated Learning as a Service (SFLaaS), a carbon- constrained Neural Architecture Search (NAS) framework for heteroge- neous sustainable constraints. We introduce a requirement-driven search space that transforms consumer sustainability profiles into a feasible architecture region before federated execution. We develop a consumer-level carbon feasibility estimation mechanism to evaluate candidate architectures under dynamic carbon conditions. We propose a sustainable con- sumer scheduling strategy that adaptively selects feasible consumers and allocates local workloads to preserve consumer participation and statistical data coverage. An evolutionary search strategy jointly optimised for predictive performance, consumer feasibility, and participation coverage under hard carbon constraints. Experiments on real-world datasets and a simulated environment demonstrate the effectiveness of the proposed approach.
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。