Xiaolu Chen

Xiaolu Chen

Auto-generated profile, based on publicly available information

Xiaolu Chen

University of Electronic Science and Technology of China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications

3 September 2025 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
CHChenghao Huang
Chenghao Huang
XCXiaolu Chen
Xiaolu Chen
Yanru ZhangYanru Zhang
Yanru Zhang
Hao WangHao Wang
Hao Wang
Heterogeneity arising from label distribution skew and data scarcity can cause inaccuracy and unfairness in IC applications that heavily rely on distributed computing. To deal with it, this article proposes a novel PFL algorithm, named federated contrastive shareable representations (FedCoSRs), to facilitate knowledge sharing among clients while maintaining data privacy. Specifically, the parameters of local models’ shallow layers and typical local representations are both considered as shareable information for the server and are aggregated globally. To address performance degradation caused by label distribution skew among clients, CL is adopted between local and global representations to enrich local knowledge. Additionally, to ensure fairness for clients with scarce data, FedCoSR introduces adaptive local aggregation to coordinate the global model involvement in each client. Our simulations demonstrate FedCoSR’s effectiveness in mitigating label heterogeneity by achieving accuracy and fairness improvements over existing methods on datasets with varying degrees of label heterogeneity.

22 May 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XCXiaolu Chen
Xiaolu Chen
CHChenghao Huang
Chenghao Huang
Yanru ZhangYanru Zhang
Yanru Zhang
Hao WangHao Wang
Hao Wang
The rapid expansion of distributed photovoltaic (PV) installations worldwide, many being behind-the-meter (BTM) systems, has significantly challenged energy management and grid operations, as unobservable PV generation further complicates the supply-demand balance. Therefore, estimating this generation from net load, known as PV disaggregation, is critical. Given privacy concerns and the need for large training datasets, federated learning (FL) becomes a promising approach, but statistical heterogeneity, arising from geographical and behavioral variations among prosumers, poses new challenges to PV disaggregation. To overcome these challenges, a privacy-preserving distributed PV disaggregation framework is proposed using personalized FL (PFL). The proposed method employs a two-level framework that combines local and global modeling. At the local level, a Transformer-based PV disaggregation model is designed to generate solar irradiance embeddings for representing local PV conditions. A novel adaptive local aggregation mechanism is adopted to mitigate the impact of statistical heterogeneity on the local model, extracting a portion of global information that benefits the local model. At the global level, a central server aggregates information uploaded from multiple data centers, preserving privacy while enabling cross-center knowledge sharing. Experiments on real-world data demonstrate the effectiveness of this proposed framework, showing improved accuracy and robustness compared to benchmark methods.

4 October 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
WCWeilong Chen
Weilong Chen
WHWenhao Hu
Wenhao Hu
XCXiaolu Chen
Xiaolu Chen
WYWeimin Yuan
Weimin Yuan
YWYan Wang
Yan Wang
ZHZhu Han
Zhu Han
With billions of users worldwide, accurately predicting social media popularity is crucial for assessing user behavior, forecasting trends, and enhancing social interactions and business strategies. However, this task presents significant challenges. Firstly, the extraction of valuable insights is complicated by the presence of tri-modal data (visual, text, structured) and pervasive noise. Secondly, the applicability of knowledge acquired during the pre-training phase is often limited due to discrepancies with downstream prediction tasks during the fine-tuning phase. Existing methods for Social Media Popularity Prediction (SMPP), including traditional models and Visual-and-language Models (VLMs), struggle to overcome these challenges, thereby failing to achieve satisfactory accuracy. To tackle these challenges, we propose a novel approach named Tri-Modal Transformers with Mixture-of-Modality-Experts (TTME) for SMPP. TTME integrates Artificial Intelligence Generated Content to mitigate data noise and incorporate a mix of Modality Experts in pre-training phases to effectively utilize tri-modal data. Moreover, to address training disparity, we explore strategies for downstream task adaptation including the integration of diverse pre-training experts and the implementation of DistillSoftmax. Through empirical evaluation, we demonstrate that the TTME significantly improves the accuracy of social media popularity predictions, effectively utilizes tri-modal data with noise, and enhances transferring knowledge from pre-training to downstream tasks.


7 April 2021
Verified
Conference Paper
Closed access
ZLZhiqiang Liu
Zhiqiang Liu
LWLiu Wei-Ming
Liu Wei-Ming
CXChen Xiao-Lu
Chen Xiao-Lu
LCLiu Chun-Hui
Liu Chun-Hui
BYBai Yun-Peng
Bai Yun-Peng
XCXu Cai
Xu Cai
Due to the wind farm 35kV system single-phase grounding fault capacitance current is relatively large, Therefore, the wind farm 35kV system adopts the bus configuration Z-type grounding transformer and the neutral point is grounded by small resistance, Zero sequence protection are used to quickly remove the single phase ground fault.In this paper, the single-phase ground fault of wind power plant collection wire in Eastern Inner Mongoliais is taken as an example. introduces the working principle of zero sequence current transformer,Clarify the setting and matching principles of zero sequence protection,,Comparing the different wiring modes of several cable shielding layers will be cause how Influence on the secondary measurement current of zero-sequence transformer, Analyze the zero sequence protection rejection of the set wire,The cause of the grounding tripping event. Summarizes the cable shield connection mode correctly,And propose rectification measures on site.