Zhiyuan Wang

Enhancing Federated Learning with In-Cloud Unlabeled Data

2022 · 2022 IEEE 38th International Conference on Data Engineering (ICDE)

Federated learning (FL) has been widely applied to collaboratively train deep learning (DL) models on massive end devices (i.e., clients). Due to the limited storage capacity and high labeling cost, there are always insufficient data …

Measurement and Analysis of Electrical Field around Secondary Equipment of Electronic Transformer in Equivalent GIS Due to Switch Operation

2022 · 2022 4th International Conference on Power and Energy Technology (ICPET)

The radiated E-field around secondary equipment of electronic current transformer and electronic voltage transformer are measured using the developed 3-D E-field measurement system under switch on operation of an equivalent 330 kV GIS system. Based …

Adaptive Block-Wise Regularization and Knowledge Distillation for Enhancing Federated Learning

2023 · IEEE/ACM Transactions on Networking

Federated Learning (FL) is a distributed model training framework that allows multiple clients to collaborate on training a global model without disclosing their local data in edge computing (EC) environments. However, FL usually faces statistical …

BCC: Re-architecting Congestion Control in DCNs

2024

The nature of datacenter traffic is a high volume of bursty tiny flows and standing long flows, which forms the coexistence of transient and persistent congestion. Traditional congestion control (CC) algorithms have inherent limitations in …

Data-Augmented Few-Shot Neural Emulator for Computer-Model System Identification

2025 · arXiv (Cornell University)

Partial differential equations (PDEs) underpin the modeling of many natural and engineered systems. It can be convenient to express such models as neural PDEs rather than using traditional numerical PDE solvers by replacing part or …

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees

2025 · arXiv (Cornell University)

Uncertainty quantification (UQ) for foundation models is essential to identify and mitigate potential hallucinations in automatically generated text. However, heuristic UQ approaches lack formal guarantees for key metrics such as the false discovery rate (FDR) …

Efficient non-destructive direct characterization of arbitrary many-body quantum channels

2025 · npj Quantum Information

Quantum process tomography (QPT) is a crucial technique for characterizing unknown quantum channels. However, traditional QPT methods encounter scalability problems as the particle numbers increase, requiring exponentially more state preparations and measurement operators. The characteristics …