Liyi Chen

Liyi Chen

Auto-generated profile, based on publicly available information

Liyi Chen

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China

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
22 April 2025
Verified
Conference Paper
Open access
SZShengzhe Zhang
Shengzhe Zhang
LCLiyi Chen
Liyi Chen
DSDazhong Shen
Dazhong Shen
CWChao Wang
Chao Wang
HXHui Xiong
Hui Xiong

10 July 2024
Verified
Conference Paper
Open access
WWWei Wu
Wei Wu
CWChao Wang
Chao Wang
DSDazhong Shen
Dazhong Shen
CQChuan Qin
Chuan Qin
LCLiyi Chen
Liyi Chen
HXHui Xiong
Hui Xiong
Collaborative filtering methods based on graph neural networks (GNNs) have witnessed significant success in recommender systems (RS), capitalizing on their ability to capture collaborative signals within intricate user-item relationships via message-passing mechanisms. However, these GNN-based RS inadvertently introduce excess linear correlation between user and item embeddings, contradicting the goal of providing personalized recommendations. While existing research predominantly ascribes this flaw to the over-smoothing problem, this paper underscores the critical, often overlooked role of the over-correlation issue in diminishing the effectiveness of GNN representations and subsequent recommendation performance. Up to now, the over-correlation issue remains unexplored in RS. Meanwhile, how to mitigate the impact of over-correlation while preserving collaborative filtering signals is a significant challenge. To this end, this paper aims to address the aforementioned gap by undertaking a comprehensive study of the over-correlation issue in graph collaborative filtering models. Firstly, we present empirical evidence to demonstrate the widespread prevalence of over-correlation in these models. Subsequently, we dive into a theoretical analysis which establishes a pivotal connection between the over-correlation and over-smoothing issues. Leveraging these insights, we introduce the Adaptive Feature De-correlation Graph Collaborative Filtering (AFDGCF) framework, which dynamically applies correlation penalties to the feature dimensions of the representation matrix, effectively alleviating both over-correlation and over-smoothing issues. The efficacy of the proposed framework is corroborated through extensive experiments conducted with four representative graph collaborative filtering models across four publicly available datasets. Our results show the superiority of AFDGCF in enhancing the performance landscape of graph collaborative filtering models.

23 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
LCLiyi Chen
Liyi Chen
ZLZhi Li
Zhi Li
WHWeidong He
Weidong He
GCGong Cheng
Gong Cheng
Tong XuTong Xu
Tong Xu
ECEnhong Chen
Enhong Chen
Entity summarization is a novel and efficient way to understand real-world facts and solve the increasing information overload problem in large-scale knowledge graphs (KG). Existing studies mainly rely on ranking independent entity descriptions as a list under a certain scoring standard such as importance. However, they often ignore the relatedness and even semantic overlap between individual descriptions. This may seriously interfere with the contribution judgment of descriptions for entity summarization. Actually, the entity summary is a whole to comprehensively integrate the main aspects of entity descriptions, which could be naturally treated as a set. Unfortunately, the exploration of these set characteristics for entity summarization is still an open issue with great challenges. To that end, we draw inspiration from a set completion perspective and propose an entity summarization method with complementarity and salience (ESCS) to deeply exploit description complementarity and salience in order to form a summary set for the target entity. Specifically, we first generate entity description representations with textual features in the description embedding module. For the purpose of learning complementary relationships within the entire summary set, we devise a bi-directional long short-term memory structure to capture global complementarity for each summary in the summary complementarity learning module. Meanwhile, in order to estimate the salience of individual descriptions, we calculate similarities between semantic embeddings of the target entity and its property-value pairs in the description salience learning module. Next, with a joint learning stage, we can optimize ESCS from a set completion perspective. Finally, a summary generation strategy is designed to infer the entire summary set step-by-step for the target entity. Extensive experiments on a public benchmark have clearly demonstrated the effectiveness of ESCS and revealed the potential of set completion in entity summarization task.

13 May 2024
Verified
Conference Paper
Open access
LCLiyi Chen
Liyi Chen
CQChuan Qin
Chuan Qin
YSYing Sun
Ying Sun
XSXin Song
Xin Song
Tong XuTong Xu
Tong Xu
HXHui Xiong
Hui Xiong
In recent years, the rise of online Knowledge Management Systems (KMSs) has significantly improved work efficiency in enterprises. Knowledge development prediction, as a critical application within these online platforms, enables organizations to proactively address knowledge gaps and align their learning initiatives with evolving job requirements. However, it still confronts challenges in exploring the influence of collaborative networks on knowledge development and adapting to ecological situations in working environment. To this end, in this paper, we propose a Collaboration-Aware Hybrid Learning approach (CAHL) for predicting the future knowledge acquisition of employees and quantifying the impact of various knowledge learning patterns. Specifically, to fully harness the inherent rules of knowledge development, we first learn the knowledge co-occurrence and prerequisite relationships with an association prompt attention mechanism to generate effective knowledge representations through a specially-designed Job Knowledge Embedding module. Then, we aggregate the features of mastering knowledge and work collaborators for employee representations in another Employee Embedding module. Moreover, we propose to model the process of employee knowledge development via a Hybrid Learning Simulation module that integrates both collaborative learning and self learning to predict future-acquired job knowledge of employees. Finally, extensive experiments conducted on a real-world dataset clearly validate the effectiveness of CAHL.

10 July 2024
Verified
Conference Paper
Open access
LZLili Zhao
Lili Zhao
QLQi Liu
Qi Liu
LYLinan Yue
Linan Yue
WCWei Chen
Wei Chen
LCLiyi Chen
Liyi Chen
CSChao Song
Chao Song
Deep Neural Networks (DNNs), despite their notable progress across information retrieval tasks, encounter the issues of shortcut learning and struggle with poor generalization due to their reliance on spurious correlations between features and labels. Current research mainly mitigates shortcut learning behavior using augmentation and distillation techniques, but these methods could be laborious and introduce unwarranted biases. To tackle these, in this paper, we propose COMI, a novel method to COrrect and MItigate shortcut learning behavior. Inspired by the ways students solve shortcuts in educational scenarios, we aim to reduce model's reliance on shortcuts and enhance its ability to extract underlying information integrated with standard Empirical Risk Minimization (ERM). Specifically, we first design Correct Habit (CoHa) strategy to retrieve the top m challenging samples for priority training, which encourages model to rely less on shortcuts in the early training. Then, to extract more meaningful underlying information, the information derived from ERM is separated into task-relevant and task-irrelevant information, the former serves as the primary basis for model predictions, while the latter is considered non-essential. However, within task-relevant information, certain potential shortcuts contribute to overconfident predictions. To mitigate this, we design Deep Mitigation (DeMi) network with shortcut margin loss to adaptively control the feature weights of shortcuts and eliminate their influence. Besides, to counteract unknown shortcut tokens issue in NLP, we adopt locally interpretable module-LIME to help recognize shortcut tokens. Finally, extensive experiments conducted on NLP and CV tasks demonstrate the effectiveness of COMI, which can perform well on both IID and OOD samples.

26 September 2023 in BMC Immunology
Verified
Journal Article
Open access
PDF file
JZJichong Zhu
Jichong Zhu
WTWeiming Tan
Weiming Tan
XZXinli Zhan
Xinli Zhan
QLQing Lu
Qing Lu
TLTuo Liang
Tuo Liang
CLChong Liu
Chong Liu
Background: HLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination. Methods: This study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated. Results: Six factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases. Conclusion: To conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.