AI in 5G: The Case of Online Distributed Transfer Learning over Edge Networks
AI in 5G: The Case of Online Distributed Transfer Learning over Edge Networks
复制标题
DOI：
10.1109/infocom48880.2022.9796779
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Yulan Yuan;Lei Jiao;Konglin Zhu;Xiaojun Lin;Lin Zhang
中科院分区：
文献类型：
--
作者：
Yulan Yuan;Lei Jiao;Konglin Zhu;Xiaojun Lin;Lin Zhang
迁移学习不是从零开始训练，而是利用现有模型来帮助训练更准确的新模型。不幸的是，在分布式云边缘网络中实现迁移学习面临着在线训练、不确定网络环境、时间耦合控制决策以及资源消耗和模型准确性之间的平衡等关键挑战。我们将分布式迁移学习描述为一个长期成本优化的非线性混合整数规划。我们设计了多项式时间在线算法，利用保留先前决策和应用新决策之间的实时权衡，基于每个单一时隙的原始对偶一次性解决方案。在编排模型放置、数据调度和推理聚合的同时，我们的方法通过结合现有的离线模型和使用基于动态到达的数据样本的推理自适应更新的权重来训练的在线模型来生成新模型。可以证明，我们的方法导致的推理错误数量不大于单个最佳模型的常数倍，并且实现了总成本的恒定竞争比。评估已经证实，与现实世界的替代品相比，我们的方法具有优越的性能。
Transfer learning does not train from scratch but leverages existing models to help train the new model of better accuracy. Unfortunately, realizing transfer learning in distributed cloud-edge networks faces critical challenges such as online training, uncertain network environments, time-coupled control decisions, and the balance between resource consumption and model accuracy. We formulate distributed transfer learning as a non-linear mixed-integer program of long-term cost optimization. We design polynomial-time online algorithms by exploiting the real-time trade-off between preserving previous decisions and applying new decisions, based on primal-dual one-shot solutions for each single time slot. While orchestrating model placement, data dispatching, and inference aggregation, our approach produces new models via combining the existing offline models and the online models being trained using weights adaptively updated based on inference upon data samples that dynamically arrive. Our approach provably incurs the number of inference mistakes no greater than a constant times that of the single best model in hindsight, and achieves a constant competitive ratio for the total cost. Evaluations have confirmed the superior performance of our approach compared to alternatives on real-world traces.