Xueyang Wu
YOU?
Author Swipe
View article: LitLinker: Supporting the Ideation of Interdisciplinary Contexts with Large Language Models for Teaching Literature in Elementary Schools
LitLinker: Supporting the Ideation of Interdisciplinary Contexts with Large Language Models for Teaching Literature in Elementary Schools Open
Teaching literature under interdisciplinary contexts (e.g., science, art) that connect reading materials has become popular in elementary schools. However, constructing such contexts is challenging as it requires teachers to explore substa…
View article: Federated Learning for Predicting Postoperative Remission of Patients with Acromegaly: A Multicentered Study
Federated Learning for Predicting Postoperative Remission of Patients with Acromegaly: A Multicentered Study Open
We demonstrate that the DFL workflow without data sharing should be a more appropriate method in ML tasks in multicentered studies. And the DFL workflow should be further exploited in clinical researches in other departments and it can enc…
View article: Delving into Differentially Private Transformer
Delving into Differentially Private Transformer Open
Deep learning with differential privacy (DP) has garnered significant attention over the past years, leading to the development of numerous methods aimed at enhancing model accuracy and training efficiency. This paper delves into the probl…
View article: FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation
FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation Open
Traditional federated learning (FL) algorithms, such as FedAvg, fail to handle non-i.i.d data because they learn a global model by simply averaging biased local models that are trained on non-i.i.d local data, therefore failing to model th…
View article: DPFormer: Learning Differentially Private Transformer on Long-Tailed Data
DPFormer: Learning Differentially Private Transformer on Long-Tailed Data Open
The Transformer has emerged as a versatile and effective architecture with broad applications. However, it still remains an open problem how to efficiently train a Transformer model of high utility with differential privacy guarantees. In …
View article: Revisiting Hyperparameter Tuning with Differential Privacy
Revisiting Hyperparameter Tuning with Differential Privacy Open
Hyperparameter tuning is a common practice in the application of machine learning but is a typically ignored aspect in the literature on privacy-preserving machine learning due to its negative effect on the overall privacy parameter. In th…
View article: A Phonetic-Semantic Pre-Training Model for Robust Speech Recognition
A Phonetic-Semantic Pre-Training Model for Robust Speech Recognition Open
Robustness is a long-standing challenge for automatic speech recognition (ASR) as the applied environment of any ASR system faces much noisier speech samples than clean training corpora. However, it is impractical to annotate every types o…
View article: WrapperFL: A Model Agnostic Plug-in for Industrial Federated Learning
WrapperFL: A Model Agnostic Plug-in for Industrial Federated Learning Open
Federated learning, as a privacy-preserving collaborative machine learning paradigm, has been gaining more and more attention in the industry. With the huge rise in demand, there have been many federated learning platforms that allow feder…
View article: An Efficient Industrial Federated Learning Framework for AIoT: A Face Recognition Application
An Efficient Industrial Federated Learning Framework for AIoT: A Face Recognition Application Open
Recently, the artificial intelligence of things (AIoT) has been gaining increasing attention, with an intriguing vision of providing highly intelligent services through the network connection of things, leading to an advanced AI-driven eco…
View article: A De Novo Divide-and-Merge Paradigm for Acoustic Model Optimization in Automatic Speech Recognition
A De Novo Divide-and-Merge Paradigm for Acoustic Model Optimization in Automatic Speech Recognition Open
Due to the rising awareness of privacy protection and the voluminous scale of speech data, it is becoming infeasible for Automatic Speech Recognition (ASR) system developers to train the acoustic model with complete data as before. In this…
View article: Real-World Image Datasets for Federated Learning
Real-World Image Datasets for Federated Learning Open
Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private. While research efforts on federated learning have been growing tr…