通过智能调整任务顺序和路径，显著降低物联网持续学习中的遗忘问题。
Algorithm Design for Continual Learning in IoT Networks
- 设计动态任务排序与路径优化策略，缓解连续学习遗忘。
- 提出多项式时间算法，理论保证近似比为1.5（欠参数）和1.5 + r^(1-T)（过参数）。
- 适用于自动驾驶等需自适应学习的物联网场景，特别适合任务序列可调控的系统。
持续学习（CL）是一种针对不同任务流数据的在线学习技术，旨在最小化对先前任务的遗忘损失。现有工作主要关注在给定任务序列下减少遗忘，但在相似任务持续出现时，对早期不同任务的遗忘仍严重。在实际物联网网络中，自动驾驶车辆可采样数据并学习不同任务，但其路径和任务顺序的调整会增加旅行成本。我们首次研究如何在持续学习中机会性地路由测试对象并改变任务序列。我们提出了一个新的优化问题，并证明其为NP难。我们设计了多项式时间算法，分别在欠参数和过参数情况下实现近似比3/2和3/2 + r^(1-T)，其中r = 1 - n/m，n为样本数，m为特征数，T为任务数。仿真结果验证了算法接近最优性能。
原文摘要 · Abstract (English)
Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the forgetting loss under a given task sequence. However, if similar tasks continuously appear to the end time, the forgetting loss is still huge on prior distinct tasks. In practical IoT networks, an autonomous vehicle to sample data and learn different tasks can route and alter the order of task pattern at increased travelling cost. To our best knowledge, we are the first to study how to opportunistically route the testing object and alter the task sequence in CL. We formulate a new optimization problem and prove it NP-hard. We propose a polynomial-time algorithm to achieve approximation ratios of $\frac{3}{2}$ for underparameterized case and $\frac{3}{2} + r^{1-T}$ for overparameterized case, respectively, where $r:=1-\frac{n}{m}$ is a parameter of feature number $m$ and sample number $n$ and $T$ is the task number. Simulation results verify our algorithm's close-to-optimum performance.
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。