Yang Liu

Yang Liu

Auto-generated profile, based on publicly available information

Yang Liu

University of California Santa Cruz

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
17 February 2025 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
SLSijia Liu
Sijia Liu
YYYuanshun Yao
Yuanshun Yao
JJJinghan Jia
Jinghan Jia
SCStephen Casper
Stephen Casper
NBNathalie Baracaldo
Nathalie Baracaldo
YLYang Liu
Yang Liu

6 February 2023 in BMC Nursing
Verified
Journal Article
Open access
PDF file
YGYi-Qiang Guo
Yi-Qiang Guo
QJQing-Mei Ju
Qing-Mei Ju
MYMiaoning You
Miaoning You
YLYang Liu
Yang Liu
AYAzlina Yusuf
Azlina Yusuf
LSLean Keng Soon
Lean Keng Soon
Objective: This study aimed to assess the level of depression, anxiety and stress among metastatic breast cancer (MBC) patients undergoing chemotherapy (CT) in Beijing, China. Methods: A cross-sectional study was conducted on 176 MBC women receiving CT, selected by purposive sampling. Data were collected using self-administered questionnaires that included participants’ socio-demographic status, DASS-21 and Brief COPE. Data were analyzed using descriptive statistics and general linear regression analysis. Results: The incidence of depression, anxiety and stress among MBC women were 52.3%, 60.2% and 36.9%, respectively. General linear regression showed that age, marital status, monthly income, physical functioning, emotional functioning, pain, dyspnea, and appetite loss were associated with depression. All variance determined the depression (R2) was 35.6%. Marital status, self-blame and behavioral disengagement were the predictors of stress and accounted for a 35.4% stress variance in MBC women. Conclusion: Our study demonstrated depression, anxiety, and stress prevalence are high in MBC women. Assessment of psychological distress (depression, anxiety, and stress) is important to recognise MBC patients who need help and further medical and mental help support. This study’s findings can increasingly highlight that depression, anxiety, and stress are substantial problems in MBC patients. Therefore, psychological interventions are needed to reduce depression, anxiety, and stress for MBC patients.

4 April 2017 in IEEE/ACM Transactions on Networking
Verified
Journal Article
Open access
YLYang Liu
Yang Liu
MLMingyan Liu
Mingyan Liu
We consider a crowd-sourcing problem where in the process of labeling massive data sets, multiple labelers with unknown annotation quality must be selected to perform the labeling task for each incoming data sample or task, with the results aggregated using for example simple or weighted majority voting rule. In this paper, we approach this labeler selection problem in an online learning framework, whereby the quality of the labeling outcome by a specific set of labelers is estimated so that the learning algorithm over time learns to use the most effective combinations of labelers. This type of online learning in some sense falls under the family of multi-armed bandit (MAB) problems, but with a distinct feature not commonly seen: since the data is unlabeled to begin with and the labelers' quality is unknown, their labeling outcome (or reward in the MAB context) cannot be readily verified; it can only be estimated against the crowd and be known probabilistically. We design an efficient online algorithm LS_OL using a simple majority voting rule that can differentiate high and low quality labelers over time, and is shown to have a regret (with respect to always using the optimal set of labelers) of O(log 2 T ) uniformly in time under mild assumptions on the collective quality of the crowd, thus regret free in the average sense. We discuss further performance improvement by using a more sophisticated majority voting rule, and show how to detect and filter out “bad” (dishonest, malicious or very incompetent) labelers to further enhance the quality of crowd-sourcing. Extension to the case when a labeler's quality is task-type dependent is also discussed using techniques from the literature on continuous arms. We establish a lower bound on the order of O(log T D 2 (T )), where D 2 (T) is an arbitrary function such that D 2 (T ) > O(1). We further provide a matching upper bound through a minor modification of the algorithm we proposed and studied earlier on. We present numerical results using both simulation and set of images labeled by amazon mechanic turks.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
XJXinyuan Ji
Xinyuan Ji
ZZZhaowei Zhu
Zhaowei Zhu
WXWei Xi
Wei Xi
OGOlga Gadyatskaya
Olga Gadyatskaya
ZSZilong Song
Zilong Song
YLYang Liu
Yang Liu
Federated Learning (FL) heavily depends on label quality for its performance. However, the label distribution among individual clients is always both noisy and heterogeneous. The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches. To tackle this issue, we propose FedFixer, where the personalized model is introduced to cooperate with the global model to effectively select clean client-specific samples. In the dual models, updating the personalized model solely at a local level can lead to overfitting on noisy data due to limited samples, consequently affecting both the local and global models’ performance. To mitigate overfitting, we address this concern from two perspectives. Firstly, we employ a confidence regularizer to alleviate the impact of unconfident predictions caused by label noise. Secondly, a distance regularizer is implemented to constrain the disparity between the personalized and global models. We validate the effectiveness of FedFixer through extensive experiments on benchmark datasets. The results demonstrate that FedFixer can perform well in filtering noisy label samples on different clients, especially in highly heterogeneous label noise scenarios.

4 August 2023
Verified
Conference Paper
Open access
JWJiaheng Wei
Jiaheng Wei
ZZZhaowei Zhu
Zhaowei Zhu
TLTianyi Luo
Tianyi Luo
EAEhsan Amid
Ehsan Amid
AKAbhishek Kumar
Abhishek Kumar
YLYang Liu
Yang Liu
The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e.g., via crowdsourcing). A typical way of using these separate labels is to first aggregate them into one and apply standard training methods. The literature has also studied extensively on effective aggregation approaches. This paper revisits this choice and aims to provide an answer to the question of whether one should aggregate separate noisy labels into single ones or use them separately as given. We theoretically analyze the performance of both approaches under the empirical risk minimization framework for a number of popular loss functions, including the ones designed specifically for the problem of learning with noisy labels. Our theorems conclude that label separation is preferred over label aggregation when the noise rates are high, or the number of labelers/annotations is insufficient. Extensive empirical results validate our conclusions.

4 August 2023
Verified
Conference Paper
Open access
QZQing Zhang
Qing Zhang
XZXiaoying Zhang
Xiaoying Zhang
YLYang Liu
Yang Liu
HWHongning Wang
Hongning Wang
MGMin Gao
Min Gao
RGRuocheng Guo
Ruocheng Guo
Recommendation systems aim to predict users' feedback on items not exposed to them yet. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic status of a user) that can affect both a user's exposure and feedback. Existing methods either (1) make untenable assumptions about these unmeasured variables or (2) directly infer latent confounders from users' exposure. However, they cannot guarantee the identification of counterfactual feedback, which can lead to biased predictions. In this work, we propose a novel method, i.e., identifiable deconfounder (iDCF), which leverages a set of proxy variables (e.g., observed user features) to resolve the aforementioned non-identification issue. The proposed iDCF is a general deconfounded recommendation framework that applies proximal causal inference to infer the unmeasured confounders and identify the counterfactual feedback with theoretical guarantees. Extensive experiments on various real-world and synthetic datasets verify the proposed method's effectiveness and robustness.