Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing

• URL: http://arxiv.org/abs/2509.06552v1
• Date: Mon, 08 Sep 2025 11:06:50 GMT
• Title: Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
• Authors: Zheqi Lv, Wenqiao Zhang, Kairui Fu, Qi Tian, Shengyu Zhang, Jiajie Su, Jingyuan Chen, Kun Kuang, Fei Wu,
• Abstract summary: We introduce Persona, a novel personalized method to enhance model generalization without post-deployment retraining.<n> Persona employs a neural adapter in the cloud to generate a parameter editing matrix based on real-time device data.<n>The prototypes are dynamically refined via the parameter editing matrix, facilitating efficient evolution.
• Score: 101.07855433979519
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers [9.270463842274394]
  Vision Transformers (ViTs) have demonstrated strong performance across a wide range of vision tasks, yet their substantial computational and memory demands hinder efficient deployment on resource-constrained mobile and edge devices.<n>This paper introduces TAP-ViTs, a novel task-adaptive pruning framework that generates device-specific pruned ViT models without requiring access to any raw local data.
  arXiv  Detail & Related papers  (2026-01-05T09:00:08Z)
• Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering [49.212940215720884]
  We propose a steering framework that generates sample-level interference from user data and injects it into the model's forward pass for personalized adaptation.<n>Our method significantly enhances personalization performance in fast-shifting environments while maintaining robustness across varying interaction modes and context lengths.
  arXiv  Detail & Related papers  (2025-10-31T06:01:04Z)
• GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts [58.95913531746308]
  We consider the problem of test-time domain generalization, where a model is trained on several source domains and adjusted on target domains never seen during training.<n>We propose to generate multiple layer parameters on the fly during inference by a lightweight meta-learned transformer, which we call textitGeneralizeFormer.
  arXiv  Detail & Related papers  (2025-02-15T10:10:49Z)
• Research on Personalized Compression Algorithm for Pre-trained Models Based on Homomorphic Entropy Increase [2.6513322539118582]
  We explore the challenges and evolution of two key technologies in the current field of AI: Vision Transformer model and Large Language Model (LLM) Vision Transformer captures global information by splitting images into small pieces, but its high reference count and compute overhead limit deployment on mobile devices. LLM has revolutionized natural language processing, but it also faces huge deployment challenges.
  arXiv  Detail & Related papers  (2024-08-16T11:56:49Z)
• A Predictive Model Based on Transformer with Statistical Feature Embedding in Manufacturing Sensor Dataset [2.07180164747172]
  This study proposes a novel predictive model based on the Transformer, utilizing statistical feature embedding and window positional encoding. The model's performance is evaluated in two problems: fault detection and virtual metrology, showing superior results compared to baseline models. The results support the model's applicability across various manufacturing industries, demonstrating its potential for enhancing process management and yield.
  arXiv  Detail & Related papers  (2024-07-09T08:59:27Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning [30.251155072822055]
  Prototype-based HyperAdapter (PHA) is a novel framework built on the adapter-tuning and hypernetwork. It introduces an instance-dense retriever and prototypical hypernetwork to generate conditional modules in a sample-efficient manner. We show that PHA strikes a better trade-off between trainable parameters, accuracy on stream tasks, and sample efficiency.
  arXiv  Detail & Related papers  (2023-10-18T02:42:17Z)
• Multi-Metric AutoRec for High Dimensional and Sparse User Behavior Data Prediction [10.351592131677018]
  We propose a multi-metric AutoRec (MMA) based on the representative AutoRec. MMA enjoys the multi-metric orientation from a set of dispersed metric spaces, achieving a comprehensive representation of user data. MMA can outperform seven other state-of-the-art models in predicting unobserved user behavior data.
  arXiv  Detail & Related papers  (2022-12-20T12:28:07Z)
• DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization [66.27399823422665]
  Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications.<n>We propose an efficient Device-cloUd collaborative parametErs generaTion framework DUET.
  arXiv  Detail & Related papers  (2022-09-12T13:26:26Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.