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

arXiv: https://arxiv.org/abs/2509.06552 · HTML: https://mlsanity.com/paper/2509.06552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 70 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (2021)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Pixel-Adaptive Convolutional Neural Networks](https://mlsanity.com/paper/1904.05373/) (2019)
- [CARAFE: Content-Aware ReAssembly of FEatures](https://mlsanity.com/paper/1905.02188/) (2019)
- [Mining Latent Structures for Multimedia Recommendation](https://mlsanity.com/paper/2104.09036/) (2021)
- [GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs](https://mlsanity.com/paper/2410.10329/) (2024)
- [DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization](https://mlsanity.com/paper/2209.05227/) (2022)
- [Device-Cloud Collaborative Learning for Recommendation](https://mlsanity.com/paper/2104.06624/) (2021)
- [Intelligent Model Update Strategy for Sequential Recommendation](https://mlsanity.com/paper/2302.07335/) (2023)
- [Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning](https://mlsanity.com/paper/2205.14833/) (2022)

## Abstract (arXiv)

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.