Yangyi Liu

Yangyi Liu

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
3 November 2022 in Frontiers in Pharmacology
Verified
Journal Article
Open access
YXYing Xiong
Ying Xiong
QWQinxuan Wang
Qinxuan Wang
YLYangyi Liu
Yangyi Liu
JWJingwen Wei
Jingwen Wei
XCXiaolei Chen
Xiaolei Chen
Objectives: Tumours remain a serious threat to human life. Following rapid progress in oncology research, tyrosine kinase inhibitors have been used to treat multiple tumour types. Given the great influence of kidneys on pharmacokinetics, renal toxicities associated with TKIs have attracted attention. However, the TKIs with the lowest risks of renal impairment are unclear. In this study, we conducted a Bayesian network meta-analysis to compare the incidence of renal impairment among different TKIs in patients with tumours.Methods and analysis: Six databases (PubMed, EMBASE, The Cochrane Library, Chinese National Knowledge Infrastructure, Wanfang Data, and China Biomedical Literature Database) were electronically searched from inception to 1 November 2021 to identify randomized controlled trials on the incidence of renal impairment for different TKIs in patients with tumours. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias of the included studies. Then, a pairwise meta-analysis was conducted using Stata version 13, and network meta-analysis within the Bayesian framework was conducted using R software version 3.5.3 with the package “gemtc 0.8–2” recalling JAGS (version 4.3.0).Results: Overall, 34 randomized controlled trials were included in this study. Although renal toxicity was common among patients receiving TKIs, the incidence and severity greatly differed among the drugs and studies. Elevated creatinine and protein levels were the most common nephrotoxic events, whereas haematuria was relatively rare. Among TKIs, nintedanib and ripretinib carried the lowest risks of renal impairment.Conclusion: TKIs displayed different profiles of renal toxicity because of their different targets and underlying mechanisms. Clinicians should be aware of the risks of renal impairment to select the optimal treatment and improve patient adherence to treatment.Systematic Review Registration: [www.crd.york.ac.uk/prospero/], identifier [CRD42022295853].

26 October 2023 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
YLYangyi Liu
Yangyi Liu
SRStefano Rini
Stefano Rini
SSSadaf Salehkalaibar
Sadaf Salehkalaibar
Jun ChenJun Chen
Jun Chen
In federated learning (FL), the communication constraint between the remote clients and the Parameter Server (PS) is a crucial bottleneck. For this reason, model updates must be compressed so as to minimize the loss in accuracy resulting from the communication constraint. This paper proposes “M- magnitude weighted L2 distortion + 2 degrees of freedom ” (M22) algorithm, a rate-distortion inspired approach to gradient compression for federated training of deep neural networks (DNNs). In particular, we propose a family of distortion measures between the original gradient and the reconstruction we referred to as “ M -magnitude weighted L 2 ” distortion, and we assume that gradient updates follow an i.i.d. distribution – generalized normal or Weibull, which have two degrees of freedom. In both the distortion measure and the gradient distribution, there is one free parameter for each that can be fitted as a function of the iteration number. Given a choice of gradient distribution and distortion measure, we design the quantizer to minimize the expected distortion in gradient reconstruction. To measure the gradient compression performance under a communication constraint, we define the per-bit accuracy as the optimal improvement in accuracy that one bit of communication brings to the centralized model over the training period. Using this performance measure, we systematically benchmark the choice of gradient distribution and distortion measure. We provide substantial insights on the role of these choices and argue that significant performance improvements can be attained using such a rate-distortion inspired compressor.

2 June 2026 in Entropy
Verified
Journal Article
Open access
PDF file
LLLiangyan Li
Liangyan Li
YLYangyi Liu
Yangyi Liu
YNYimo Ning
Yimo Ning
SRStefano Rini
Stefano Rini
Jun ChenJun Chen
Jun Chen
We introduce the symmetric co-skewness moment (SCKM)—a third-order informational dissimilarity metric that consistently outperforms state-of-the-art client-selection heuristics in federated learning (FL) under heterogeneous data. Unlike similarity-driven schemes, SCKM minimizes redundancy by favoring clients with complementary gradients, delivering faster and more stable convergence even at high heterogeneity levels. Operating on highly compressed 0.5% gradient summaries, our framework provides two operating modes for different deployment scales: (i) SCKM-Select directly ranks and schedules a small candidate pool, whereas (ii) SCKM-Cluster adds a fast, elbow-guided clustering step to scalably choose from thousands of users. We evaluate both variants on a VGG-16 model across multiple non-IID partition schemes and initializations, observing consistent gains over leading cosine-similarity, loss-sketch, and max-diversity baselines—without increasing the communication budget.

30 April 2026 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YLYangyi Liu
Yangyi Liu
SRStefano Rini
Stefano Rini
Jun ChenJun Chen
Jun Chen
Federated Learning (FL) has gained increasing popularity due to its ability to harness diverse datasets from multiple sources without the need for centralized data. Extensive research has focused on reducing the cost of communications between remote clients and the parameter server. However, existing works fail to comprehensively leverage the correlation among the gradients at the remote clients. In this work, we propose GCFed – a novel FL framework that exploits the clients’ gradient correlation to reduce communication costs while maintaining satisfactory convergence. Specifically, we propose an information-theoretic problem formulation that considers the model update problem in a single FL iteration as a multi-terminal source coding problem in the context of rate-distortion theory. We solve the associated optimization problem using convex semi-definite relaxation techniques with an iterative algorithm and leverage the solution to develop a joint approach for correlation-aware client selection and rate allocation. Extensive experiments are conducted to validate the effectiveness of our proposed framework and approaches as compared to state-of-the-art methods. Our code is available at: https://github.com/yangyiliu21/GCFed.

19 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
LLLiangyan Li
Liangyan Li
YLYangyi Liu
Yangyi Liu
YNYimo Ning
Yimo Ning
SRStefano Rini
Stefano Rini
Jun ChenJun Chen
Jun Chen
Federated Learning (FL) has emerged as a powerful paradigm for leveraging diverse datasets from multiple sources while preserving data privacy by avoiding centralized storage. However, many existing approaches fail to account for the intricate gradient correlations between remote clients, a limitation that becomes especially problematic in data heterogeneity scenarios. In this work, we propose a novel FL framework utilizing Power-Norm Cosine Similarity (PNCS) to improve client selection for model aggregation. By capturing higher-order gradient moments, PNCS addresses non-IID data challenges, enhancing convergence speed and accuracy. Additionally, we introduce a simple algorithm ensuring diverse client selection through a selection history queue. Experiments with a VGG16 model across varied data partitions demonstrate consistent improvements over state-of-the-art methods.