activity
20212024
most citedAsymmetric Temperature Scaling Makes Larger Networks Teach Well Again

12 citations · 41 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2024

MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes

Xin-Chun Li, Shaoming Song, Yinchuan Li +4

In some real-world applications, data samples are usually distributed on local devices, where federated learning (FL) techniques are proposed to coordinate decentralized clients wi…

cs.LG2023★ 1 cited

ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation

Yan Zhuang, Zhenzhe Zheng, Yunfeng Shao +3

Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small…

cs.LG2022★ 12 cited

Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again

Xin-Chun Li, Wen-Shu Fan, Shaoming Song +4

Knowledge Distillation (KD) aims at transferring the knowledge of a well-performed neural network (the {\it teacher}) to a weaker one (the {\it student}). A peculiar phenomenon is…

cs.LG2022

To Store or Not? Online Data Selection for Federated Learning with Limited Storage

Chen Gong, Zhenzhe Zheng, Yunfeng Shao +3

Machine learning models have been deployed in mobile networks to deal with massive data from different layers to enable automated network management and intelligence on devices. To…

cs.LG2022

Avoid Overfitting User Specific Information in Federated Keyword Spotting

Xin-Chun Li, Jin-Lin Tang, Shaoming Song +5

Keyword spotting (KWS) aims to discriminate a specific wake-up word from other signals precisely and efficiently for different users. Recent works utilize various deep networks to…

cs.LG2021★ 1 cited

Domain Adaptation without Model Transferring

Kunhong Wu, Yucheng Shi, Yahong Han +3

In recent years, researchers have been paying increasing attention to the threats brought by deep learning models to data security and privacy, especially in the field of domain ad…