Chorus: Harmonizing Context and Sensing Signals for Data-Free Model Customization in IoT

2025-12-17

AI Summary

To address poor model generalization in IoT sensing tasks—caused by dynamic contextual factors (e.g., environment, location) affecting sensor data—this paper proposes a target-domain-data-free online model customization framework. Our method comprises four key innovations: (1) cross-modal unsupervised reconstruction to learn robust contextual representations; (2) language-embedding-guided contextual regularization for semantic alignment; (3) a lightweight learnable gating head that dynamically fuses sensor and contextual evidence; and (4) a context-shift detection mechanism that triggers cache updates. Evaluated on IMU, speech, and WiFi-based sensing tasks, our approach improves accuracy on unseen contexts by up to 11.3% over baselines, while maintaining comparable inference latency—enabling efficient deployment on smartphones and edge devices.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In real-world IoT applications, sensor data is usually collected under diverse and dynamic contextual conditions where factors such as sensor placements or ambient environments can significantly affect data patterns and downstream performance. Traditional domain adaptation or generalization methods often ignore such context information or use simplistic integration strategies, making them ineffective in handling unseen context shifts after deployment. In this paper, we propose Chorus, a context-aware, data-free model customization approach that adapts models to unseen deployment conditions without requiring target-domain data. The key idea is to learn effective context representations that capture their influence on sensor data patterns and to adaptively integrate them based on the degree of context shift. Specifically, Chorus first performs unsupervised cross-modal reconstruction between unlabeled sensor data and language-based context embeddings, while regularizing the context embedding space to learn robust, generalizable context representations. Then, it trains a lightweight gated head on limited labeled samples to dynamically balance sensor and context contributions-favoring context when sensor evidence is ambiguous and vice versa. To further reduce inference latency, Chorus employs a context-caching mechanism that reuses cached context representations and updates only upon detected context shifts. Experiments on IMU, speech, and WiFi sensing tasks under diverse context shifts show that Chorus outperforms state-of-the-art baselines by up to 11.3% in unseen contexts, while maintaining comparable latency on smartphone and edge devices.

Problem

• Adapts models to unseen IoT conditions without target data
• Learns context representations to handle sensor data variations
• Dynamically balances sensor and context for robust performance

Innovation

• Unsupervised cross-modal reconstruction for context representation
• Lightweight gated head for dynamic sensor-context balancing
• Context-caching mechanism for reduced inference latency