8 papers
PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes
Yiming Zhou, Jiahao Wang, Mingyue Cheng +3
While collaborative forecasting on distributed time series is highly desirable, directly pooling localized datasets is often impractical due to data sharing constraints. Federated…
Efficient Segment Anything with Depth-Aware Fusion and Limited Training Data
Yiming Zhou, Xuenjie Xie, Panfeng Li +3
Segment Anything Models (SAM) achieve impressive universal segmentation performance but require massive datasets (e.g., 11M images) and rely solely on RGB inputs. Recent efficient…
Differentially Private Perturbed Push-Sum Protocol and Its Application in Non-Convex Optimization
Yiming Zhou, Kaiping Xue, Enhong Chen
In decentralized networks, nodes cannot ensure that their shared information will be securely preserved by their neighbors, making privacy vulnerable to inference by curious nodes.…
FUSCO: High-Performance Distributed Data Shuffling via Transformation-Communication Fusion
Zhuoran Zhu, Chunyang Zhu, Hao Lin +9
Large-scale Mixture-of-Experts (MoE) models rely on \emph{expert parallelism} for efficient training and inference, which splits experts across devices and necessitates distributed…
Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation
Hanyu Zhang, Yiming Zhou, Jinxia Zhang
Open-vocabulary camouflaged object segmentation requires models to segment camouflaged objects of arbitrary categories unseen during training, placing extremely high demands on gen…
Scalable Hessian-free Proximal Conjugate Gradient Method for Nonconvex and Nonsmooth Optimization
Yiming Zhou, Wei Dai
This work studies a composite minimization problem involving a differentiable function q and a nonsmooth function h, both of which may be nonconvex. This problem is ubiquitous in s…