Chaoyue Niu

Chaoyue Niu

Auto-generated profile, based on publicly available information

Chaoyue Niu

Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 July 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
HHHonglan Huang
Honglan Huang
WSWei Shi
Wei Shi
YFYanghe Feng
Yanghe Feng
CNChaoyue Niu
Chaoyue Niu
GCGuangquan Cheng
Guangquan Cheng
ZLZhong Liu
Zhong Liu
Federated learning (FL) is an emerging distributed machine learning (ML) framework that operates under privacy and communication constraints. To mitigate the data heterogeneity underlying FL, clustered FL (CFL) was proposed to learn customized models for different client groups. However, due to the lack of effective client selection strategies, the CFL process is relatively slow, and the model performance is also limited in the presence of nonindependent and identically distributed (non-IID) client data. In this work, for the first time, we propose selecting participating clients for each cluster with active learning (AL) and call our method active client selection for CFL (ACFL). More specifically, in each ACFL round, each cluster filters out a small set of clients, which are the most informative clients according to some AL metrics [e.g., uncertainty sampling, query-by-committee (QBC), loss], and aggregates only its model updates to update the cluster-specific model. We empirically evaluate our ACFL approach on the public MNIST, CIFAR-10, and LEAF synthetic datasets with class-imbalanced settings. Compared with several FL and CFL baselines, the results reveal that ACFL can dramatically speed up the learning process while requiring less client participation and significantly improving model accuracy with a relatively low communication overhead.

3 November 2020 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
CNChaoyue Niu
Chaoyue Niu
FWFan Wu
Fan Wu
STShaojie Tang
Shaojie Tang
SMShuai Ma
Shuai Ma
GCGuihai Chen
Guihai Chen
The ubiquitous needs for extracting insights from data are driving the emergence of service providers to offer predictions given the inputs from customers. During this process, it is important and highly nontrivial for the service providers to generate proofs of honest predictions without leaking the key parameters of their trained models. In addition, the customers are usually unwilling to reveal their sensitive inputs. In this paper, we proposed MVP, which enables Machine learning prediction in a Verifiable and Privacy preserving fashion. MVP features the properties of polynomial decomposition and prime-order bilinear groups to simultaneously facilitate oblivious evaluation and batch outcome verification while maintaining function privacy and input privacy. We further instantiated MVP with Support Vector Machines (SVMs) and extensively evaluated its performance for the spam detection task on three practical Short Message Service (SMS) datasets. Our analysis and evaluation results reveal that MVP achieves the desired properties while incurring low computation and communication overhead.

1 January 2024 in INFORMS Journal on Computing
Verified
Journal Article
Closed access
YYYikai Yan
Yikai Yan
CNChaoyue Niu
Chaoyue Niu
YDYucheng Ding
Yucheng Ding
Zhenzhe ZhengZhenzhe Zheng
Zhenzhe Zheng
STShaojie Tang
Shaojie Tang
GCGuihai Chen
Guihai Chen
Federated learning is a new distributed machine learning framework, where numerous heterogeneous clients collaboratively train a model without sharing training data. In this work, we consider a practical and ubiquitous issue when deploying federated learning in mobile environments: intermittent client availability, where the set of eligible clients may change during the training process. Such intermittent client availability would seriously deteriorate the performance of the classical federated averaging algorithm (FedAvg). Thus, we propose a simple distributed nonconvex optimization algorithm, called federated latest averaging (FedLaAvg), which leverages the latest gradients of all clients, even when the clients are not available, to jointly update the global model in each iteration. Our theoretical analysis shows that FedLaAvg achieves guaranteed convergence and a sublinear speedup with respect to the total number of clients. We implement FedLaAvg along with several baselines and evaluate them over the benchmarking MNIST and Sentiment140 data sets. The evaluation results demonstrate that FedLaAvg achieves more stable training than FedAvg in both convex and nonconvex settings and reaches a sublinear speedup. Source code and online supplement are available at the IJOC GitHub site ( http://dx.doi.org/10.1287/ijoc.2022.0057.cd , https://github.com/INFORMSJoC/2022.0057 ). History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Leaning. Funding: This work was supported by the National Key R&D Program of China [Grant 2022ZD0119100], the National Natural Science Foundation of China (NSFC) [Grants 61972252, 61972254, 62072303, 62025204, 62132018, 62202296, and 62202297], the Alibaba Innovation Research (AIR) Program, and the Tencent Rhino Bird Key Research Project. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0057 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0057 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

24 August 2024
Verified
Conference Paper
Open access
YDYucheng Ding
Yucheng Ding
CNChaoyue Niu
Chaoyue Niu
FWFan Wu
Fan Wu
STShaojie Tang
Shaojie Tang
CLChengfei Lyu
Chengfei Lyu
GCGuihai Chen
Guihai Chen
Many billion-scale large language models (LLMs) have been released for resource-constraint mobile devices to provide local LLM inference service when cloud-based powerful LLMs are not available. However, the capabilities of current on-device LLMs still lag behind those of cloud-based LLMs, and how to effectively and efficiently enhance on-device LLM inference becomes a practical requirement. We thus propose to collect the user's historical interactions with the cloud-based LLM and build an external datastore on the mobile device for enhancement using nearest neighbors search. Nevertheless, the full datastore improves the quality of token generation at the unacceptable expense of much slower generation speed. To balance performance and efficiency, we propose to select an optimal subset of the full datastore within the given size limit, the optimization objective of which is proven to be submodular. We further design an offline algorithm, which selects the subset after the construction of the full datastore, as well as an online algorithm, which performs selection over the stream and can be flexibly scheduled. We theoretically analyze the performance guarantee and the time complexity of the offline and the online designs to demonstrate effectiveness and scalability. We finally take three ChatGPT related dialogue datasets and four different on-device LLMs for evaluation. Evaluation results show that the proposed designs significantly enhance LLM performance in terms of perplexity while maintaining fast token generation speed. Practical overhead testing on the smartphone reveal the efficiency of on-device datastore subset selection from memory usage and computation overhead.

14 August 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
CNChaoyue Niu
Chaoyue Niu
Zhenzhe ZhengZhenzhe Zheng
Zhenzhe Zheng
FWFan Wu
Fan Wu
STShaojie Tang
Shaojie Tang
XGXiaofeng Gao
Xiaofeng Gao
GCGuihai Chen
Guihai Chen
With the commoditization of personal privacy, pricing private data has become an intriguing problem. In this paper, we study noisy aggregate statistics trading from the perspective of a data broker in data markets. We thus propose ERATO, which enables aggrEgate statistics pRicing over privATe cOrrelated data. On one hand, ERATO guarantees arbitrage freeness against cunning data consumers. On the other hand, ERATO compensates data owners for their privacy losses using both bottom-up and top-down designs. We further apply ERATO to three practical aggregate statistics, namely weighted sum, probability distribution fitting, and degree distribution, and extensively evaluate their performances on MovieLens dataset, 2009 RECS dataset, and two SNAP large social network datasets, respectively. Our analysis and evaluation results reveal that ERATO well balances utility and privacy, achieves arbitrage freeness, and compensates data owners more fairly than differential privacy based approaches.

3 December 2024
Verified
Conference Paper
Open access
YDYucheng Ding
Yucheng Ding
CNChaoyue Niu
Chaoyue Niu
YYYikai Yan
Yikai Yan
Zhenzhe ZhengZhenzhe Zheng
Zhenzhe Zheng
FWFan Wu
Fan Wu
RJRongfei Jia
Rongfei Jia