249 citations · 1.2k across the 42 of their papers we have counts for
7 papers · 1 filter
Federated Learning with Flexible Control
Shiqiang Wang, Jake Perazzone, Mingyue Ji +1
Federated learning (FL) enables distributed model training from local data collected by users. In distributed systems with constrained resources and potentially high dynamics, e.g.…
Flexible Vertical Federated Learning with Heterogeneous Parties
Timothy Castiglia, Shiqiang Wang, Stacy Patterson
We propose Flexible Vertical Federated Learning (Flex-VFL), a distributed machine algorithm that trains a smooth, non-convex function in a distributed system with vertically partit…
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
Timothy Castiglia, Anirban Das, Shiqiang Wang +1
We propose Compressed Vertical Federated Learning (C-VFL) for communication-efficient training on vertically partitioned data. In C-VFL, a server and multiple parties collaborative…
A Unified Analysis of Federated Learning with Arbitrary Client Participation
Shiqiang Wang, Mingyue Ji
Federated learning (FL) faces challenges of intermittent client availability and computation/communication efficiency. As a result, only a small subset of clients can participate i…
Joint Coreset Construction and Quantization for Distributed Machine Learning
Hanlin Lu, Changchang Liu, Shiqiang Wang +4
Coresets are small, weighted summaries of larger datasets, aiming at providing provable error bounds for machine learning (ML) tasks while significantly reducing the communication…
KerGNNs: Interpretable Graph Neural Networks with Graph Kernels
Aosong Feng, Chenyu You, Shiqiang Wang +1
Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted com…
Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization
Jake Perazzone, Shiqiang Wang, Mingyue Ji +1
Federated learning (FL) is a useful tool in distributed machine learning that utilizes users' local datasets in a privacy-preserving manner. When deploying FL in a constrained wire…