Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
This work tackles the problem of on-device model adaptation to real-time data shifts for edge computing applications, representing an incremental improvement over existing fine-tuning methods.
The paper addresses the challenge of real-time data distribution shifts on devices by introducing Persona, a prototype-based parameter editing framework that enhances model generalization without retraining, achieving competitive performance on vision and recommendation tasks across multiple datasets.
The on-device real-time data distribution shift on devices challenges the generalization of lightweight on-device models. This critical issue is often overlooked in current research, which predominantly relies on data-intensive and computationally expensive fine-tuning approaches. To tackle this, we introduce Persona, a novel personalized method using a prototype-based, backpropagation-free parameter editing framework to enhance model generalization without post-deployment retraining. Persona employs a neural adapter in the cloud to generate a parameter editing matrix based on real-time device data. This matrix adeptly adapts on-device models to the prevailing data distributions, efficiently clustering them into prototype models. The prototypes are dynamically refined via the parameter editing matrix, facilitating efficient evolution. Furthermore, the integration of cross-layer knowledge transfer ensures consistent and context-aware multi-layer parameter changes and prototype assignment. Extensive experiments on vision task and recommendation task on multiple datasets confirm Persona's effectiveness and generality.