物联网中用于模型适应性的对比持续学习
Contrastive Continual Learning for Model Adaptability in Internet of Things
AI总结：
本文提出了一种面向物联网的对比持续学习方法，结合算法设计与系统现实，解决模型适应性问题并提出评估指导。
摘要：
物联网（IoT）部署运行在非平稳、动态的环境中，其中诸如传感器漂移、用户行为演变和异构用户隐私需求等因素可能影响应用效用。持续学习（CL）通过在时间推移过程中适应模型而不发生灾难性遗忘来解决这一问题。同时，对比学习已作为一种强大的表示学习范式，通过自监督的方式提高了鲁棒性和样本效率。本文回顾了对比持续学习（CCL）在物联网中的应用，将算法设计（重放、正则化、蒸馏、提示）与物联网系统现实（TinyML限制、间歇性连接、隐私）联系起来。我们提出了一种统一的问题表述，推导了融合对比和蒸馏损失的共同目标，提出了面向物联网的参考架构，用于设备端、边缘和云计算中的CCL，并提供了评估协议和指标的指导。最后，我们强调了与物联网领域相关的开放性独特挑战，如跨表格和流式物联网数据、概念漂移、联邦设置和节能训练。
英文摘要：
Internet of Things (IoT) deployments operate in nonstationary, dynamic environments where factors such as sensor drift, evolving user behavior, and heterogeneous user privacy requirements can affect application utility. Continual learning (CL) addresses this by adapting models over time without catastrophic forgetting. Meanwhile, contrastive learning has emerged as a powerful representation-learning paradigm that improves robustness and sample efficiency in a self-supervised manner. This paper reviews the usage of \emph{contrastive continual learning} (CCL) for IoT, connecting algorithmic design (replay, regularization, distillation, prompts) with IoT system realities (TinyML constraints, intermittent connectivity, privacy). We present a unifying problem formulation, derive common objectives that blend contrastive and distillation losses, propose an IoT-oriented reference architecture for on-device, edge, and cloud-based CCL, and provide guidance on evaluation protocols and metrics. Finally, we highlight open unique challenges with respect to the IoT domain, such as spanning tabular and streaming IoT data, concept drift, federated settings, and energy-aware training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
