5 papers · 1 filter
FedAPM: Federated Learning via ADMM with Partial Model Personalization
Shengkun Zhu, Feiteng Nie, Jinshan Zeng +6
In federated learning (FL), the assumption that datasets from different devices are independent and identically distributed (i.i.d.) often does not hold due to user differences, an…
On Simplifying Large-Scale Spatial Vectors: Fast, Memory-Efficient, and Cost-Predictable k-means
Yushuai Ji, Zepeng Liu, Sheng Wang +2
The k-means algorithm can simplify large-scale spatial vectors, such as 2D geo-locations and 3D point clouds, to support fast analytics and learning. However, when processing large…
Personalized Federated Learning via ADMM with Moreau Envelope
Shengkun Zhu, Jinshan Zeng, Sheng Wang +2
Personalized federated learning (PFL) is an approach proposed to address the issue of poor convergence on heterogeneous data. However, most existing PFL frameworks require strong a…
On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness
Shengkun Zhu, Jinshan Zeng, Sheng Wang +4
Statistical heterogeneity is a root cause of tension among accuracy, fairness, and robustness of federated learning (FL), and is key in paving a path forward. Personalized FL (PFL)…
Efficient k-means with Individual Fairness via Exponential Tilting
Shengkun Zhu, Jinshan Zeng, Yuan Sun +3
In location-based resource allocation scenarios, the distances between each individual and the facility are desired to be approximately equal, thereby ensuring fairness. Individual…