Contrastive Continual Learning for Model Adaptability in Internet of Things

TL;DR

This paper reviews contrastive continual learning (CCL) techniques tailored for IoT environments, addressing challenges like nonstationarity, privacy, and resource constraints to improve model adaptability and robustness.

Contribution

It introduces a unified formulation of CCL for IoT, proposes an IoT-specific architecture, and discusses evaluation protocols and domain-specific challenges.

Findings

Unified CCL problem formulation for IoT

IoT-oriented CCL architecture proposed

Discussion of domain-specific challenges and evaluation metrics

Abstract

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.