Personalized Model

Personalized models aim to tailor machine learning models to individual users or devices, addressing the limitations of generic models in handling diverse data distributions and user needs. Current research focuses on developing efficient algorithms for federated learning, where personalization occurs without centralizing sensitive data, often employing techniques like adapter modules, parameter decomposition, and meta-learning. This field is significant for improving the accuracy and fairness of AI systems across various applications, from personalized medicine and education to recommendation systems and human-robot interaction, by ensuring models effectively cater to individual characteristics.

Papers

March 25, 2022

Sparse Federated Learning with Hierarchical Personalized Models
Xiaofeng Liu, Qing Wang, Yunfeng Shao, Yinchuan Li
Personalized Federated Learning Personalized Model FedAvg Algorithm Proximal Gradient Descent Sparse Federated

February 18, 2022

PerFED-GAN: Personalized Federated Learning via Generative Adversarial Networks
Xingjian Cao, Gang Sun, Hongfang Yu, Mohsen Guizani
Generative Adversarial Network Personalized Federated Learning C Gan Personalized Model Federated Training

February 13, 2022

On the Convergence of Clustered Federated Learning
Jie Ma, Guodong Long, Tianyi Zhou, Jing Jiang, Chengqi Zhang
Early Stage Convergence Personalized Model Model Personalization Clustered Federated Learning Personalized Fl

February 12, 2022

Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents
Jing Yang Lee, Kong Aik Lee, Woon Seng Gan
Empathetic Dialogue Personalized Model Dialogue Response Conditional Variational Auto Encoder Inter Sentential

November 26, 2021

Deep Learning for Reaction-Diffusion Glioma Growth Modelling: Towards a Fully Personalised Model?
Corentin Martens, Antonin Rovai, Daniele Bonatto, Thierry Metens, Olivier Debeir, Christine Decaestecker, Serge Goldman, Gaetan Van Simaeys
Deep Learning Personalized Model Reaction Diffusion Synthetic Tumor Tumor Growth

November 16, 2021

On-Demand Unlabeled Personalized Federated Learning
Ohad Amosy, Gal Eyal, Gal Chechik
Differential Privacy Personalized Federated Learning Personalized Model Unlabeled Client