activity
20182026
most citedFedKD: Communication Efficient Federated Learning via Knowledge Distillation

623 citations · 1.9k across the 71 of their papers we have counts for

collaborators
Showing 2022Show all

23 papers · 1 filter

cs.LG2022★ 4 cited

Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimization

Yueqi Xie, Weizhong Zhang, Renjie Pi +4

Non-IID data distribution across clients and poisoning attacks are two main challenges in real-world federated learning (FL) systems. While both of them have attracted great resear…

cs.AI2022

Effective and Efficient Query-aware Snippet Extraction for Web Search

Jingwei Yi, Fangzhao Wu, Chuhan Wu +4

Query-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. Although important, it…

cs.IR2022★ 1 cited

Federated Unlearning for On-Device Recommendation

Wei Yuan, Hongzhi Yin, Fangzhao Wu +3

The increasing data privacy concerns in recommendation systems have made federated recommendations (FedRecs) attract more and more attention. Existing FedRecs mainly focus on how t…

cs.CR2022★ 19 cited

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

Xuanli He, Qiongkai Xu, Yi Zeng +4

Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, a recent…

cs.CV2022★ 3 cited

FedX: Unsupervised Federated Learning with Cross Knowledge Distillation

Sungwon Han, Sungwon Park, Fangzhao Wu +4

This paper presents FedX, an unsupervised federated learning framework. Our model learns unbiased representation from decentralized and heterogeneous local data. It employs a two-s…

cs.IR2022★ 2 cited

Two-Stage Neural Contextual Bandits for Personalised News Recommendation

Mengyan Zhang, Thanh Nguyen-Tang, Fangzhao Wu +3

We consider the problem of personalised news recommendation where each user consumes news in a sequential fashion. Existing personalised news recommendation methods focus on exploi…