3 citations · 9 across the 10 of their papers we have counts for
10 papers
Stochastic Controlled Averaging for Federated Learning with Communication Compression
Xinmeng Huang, Ping Li, Xiaoyun Li
Communication compression, a technique aiming to reduce the information volume to be transmitted over the air, has gained great interests in Federated Learning (FL) for the potenti…
Differentially Private One Permutation Hashing and Bin-wise Consistent Weighted Sampling
Xiaoyun Li, Ping Li
Minwise hashing (MinHash) is a standard algorithm widely used in the industry, for large-scale search and learning applications with the binary (0/1) Jaccard similarity. One common…
Differential Privacy with Random Projections and Sign Random Projections
Ping Li, Xiaoyun Li
In this paper, we develop a series of differential privacy (DP) algorithms from a family of random projections (RP) for general applications in machine learning, data mining, and i…
Building K-Anonymous User Cohorts with\\ Consecutive Consistent Weighted Sampling (CCWS)
Xinyi Zheng, Weijie Zhao, Xiaoyun Li +1
To retrieve personalized campaigns and creatives while protecting user privacy, digital advertising is shifting from member-based identity to cohort-based identity. Under such iden…
OPORP: One Permutation + One Random Projection
Ping Li, Xiaoyun Li
Consider two -dimensional data vectors (e.g., embeddings): . In many embedding-based retrieval (EBR) applications where the vectors are generated from trained models, $D=2…
Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression
Xiaoyun Li, Ping Li
In federated learning (FL) systems, e.g., wireless networks, the communication cost between the clients and the central server can often be a bottleneck. To reduce the communicatio…
-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy
Chenglin Fan, Ping Li, Xiaoyun Li
When designing clustering algorithms, the choice of initial centers is crucial for the quality of the learned clusters. In this paper, we develop a new initialization scheme, calle…
Breaking the Linear Error Barrier in Differentially Private Graph Distance Release
Chenglin Fan, Ping Li, Xiaoyun Li
Releasing all pairwise shortest path (APSP) distances between vertices on general graphs under weight Differential Privacy (DP) is known as a challenging task. In the previous atte…
Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising
Weijie Zhao, Xuewu Jiao, Mingqing Hu +3
Click-Through Rate (CTR) prediction is a crucial component in the online advertising industry. In order to produce a personalized CTR prediction, an industry-level CTR prediction m…
Layer-wise and Dimension-wise Locally Adaptive Federated Learning
Belhal Karimi, Ping Li, Xiaoyun Li
In the emerging paradigm of Federated Learning (FL), large amount of clients such as mobile devices are used to train possibly high-dimensional models on their respective data. Com…