Yong Li

Prof. Dr. Yong Li


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
9 November 2017 in IEEE Access
Verified
Journal Article
Open access
YLYong Li
Yong Li
ZHZhiqiu Huang
Zhiqiu Huang
YWYong Wang
Yong Wang
BFBingwu Fang
Bingwu Fang
Cross-project defect prediction (CPDP) is a field of study where a software project lacking enough local data can use data from other projects to build defect predictors. To support CPDP, the cross-project data must be carefully filtered before being applied locally. Researchers have devised and implemented a plethora of various data filters for the improvement of CPDP performance. However, it is still unclear what data filter strategy is most effective, both generally and specifically in CPDP. The objective of this paper is to provide an extensive comparison of well-known data filters and a novel filter devised in this paper. We perform experiments on 44 releases of 14 open-source projects, and use Naive Bayes and Support Vector Machine as the underlying classifier. The results demonstrate that the data filter strategy improves the performance of cross-project defect prediction significantly, and the hierarchical select-based filter (HSBF) which we proposed performs significantly better. Moreover, when using appropriate data filter strategy, the defect predictor built from cross-project data can outperform the predictor learned by using within-project data.

10 October 2022
Verified
Conference Paper
Open access
YZYu Zheng
Yu Zheng
CGChen Gao
Chen Gao
JDJingtao Ding
Jingtao Ding
LYLingling Yi
Lingling Yi
DJDepeng Jin
Depeng Jin
MWMeng Wang
Meng Wang
Recommender systems are prone to be misled by biases in the data. Models trained with biased data fail to capture the real interests of users, thus it is critical to alleviate the impact of bias to achieve unbiased recommendation. In this work, we focus on an essential bias in micro-video recommendation, duration bias. Specifically, existing micro-video recommender systems usually consider watch time as the most critical metric, which measures how long a user watches a video. Since videos with longer duration tend to have longer watch time, there exists a kind of duration bias, making longer videos tend to be recommended more against short videos. In this paper, we empirically show that commonly-used metrics are vulnerable to duration bias, making them NOT suitable for evaluating micro-video recommendation. To address it, we further propose an unbiased evaluation metric, called WTG (short for Watch Time Gain). Empirical results reveal that WTG can alleviate duration bias and better measure recommendation performance. Moreover, we design a simple yet effective model named DVR (short for Debiased Video Recommendation) that can provide unbiased recommendation of micro-videos with varying duration, and learn unbiased user preferences via adversarial learning. Extensive experiments based on two real-world datasets demonstrate that DVR successfully eliminates duration bias and significantly improves recommendation performance with over 30% relative progress. Codes and datasets are released at https://github.com/tsinghua-fib-lab/WTG-DVR.

11 May 2022 in Connection Science
Verified
Journal Article
Open access
LLLu Liang
Lu Liang
YLYong Li
Yong Li
MWMing Wen
Ming Wen
YLYing Liu
Ying Liu
In the era of big data, there are numerous duplicate code snippets on the Internet, it is especially necessary to make use of them to build new software projects. In this paper, we present a toolkit (KG4Py) for generating a knowledge graph of Python files in GitHub repositories and conducting semantic search with the knowledge graph. In KG4Py, we remove all duplicate files in 317 K Python files and perform static code analyses of these files by using a concrete syntax tree (CST) to build a code knowledge graph of Python functions. We integrate a pre-trained model with an unsupervised model to generate a new model, and combine this new model with a code knowledge graph for the purpose of searching code snippets with natural language descriptions. The experimental results show that KG4Py achieves good performance in both the construction of the code knowledge graph and the semantic search of code snippets.

5 January 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ALAi li Li
Ai li Li
YLYong Li
Yong Li
XGXiyu Gao
Xiyu Gao
The rapid development of artificial intelligence is reshaping learning concepts and instructional practices. Online learning overcomes temporal and spatial constraints, providing flexible and autonomous learning environments, and has become a central component of educational digitalization. However, the physical separation of teachers and learners makes it difficult to monitor learning progress effectively, while the abundance of learning resources often leads to learner disorientation and reduced learning efficiency. Consequently, effective planning of personalized learning paths is essential for reducing learning costs and improving learning outcomes. Traditional one-size-fits-all instructional models are insufficient to meet learners’ needs. In this context, designing transparent, adaptive, and personalized learning paths for individual learners has become an urgent research challenge. This study presents a comprehensive review of personalized learning path recommendation based on knowledge graphs. It analyzes existing methods from interdisciplinary perspectives, with particular emphasis on the theoretical role of Bloom’s taxonomy in guiding the design of learning paths. The review further summarizes core algorithm approaches, examines the characteristics and applicability of commonly used public datasets, and identifies major limitations and challenges in current research. Finally, it outlines future research directions aimed at enhancing transparency, adaptability, and explainability to support educational digital transformation and the realization of individualized instruction.

23 January 2018 in IEEE Access
Verified
Journal Article
Open access
YWYong Wang
Yong Wang
ZHZhiqiu Huang
Zhiqiu Huang
BFBingwu Fang
Bingwu Fang
YLYong Li
Yong Li
Spectrum-based fault localization (SFL) is a popular lightweight automatic software fault localization technique that uses coverage information of program execution to compute the likelihood of root cause of failure(s) for each program component and ranks them descending by their suspiciousness scores. However, some recent studies indicate a SFL technique to be useful only if the root cause(s) of failures is ranked at top k. Due to the nature of SFL technique, it is impossible that the root fault(s) is always ranked at top k, which may interfere with the usefulness of SFL in practice. To solve this issue, a SFL technique via enlarging the non-fault region to further improve fault absolute ranking was proposed. The idea behind this is that we can intuitively improve fault absolute ranking for a SFL technique if some non-fault components ranked higher were excluded from the fault ranking list. In the approach, we enlarge the non-fault region iteratively to narrow down the suspicious region based on two scenarios, and then rank those components in the suspicious region using existing SFL techniques. The empirical results indicate that our approach significantly helps existing SFL techniques to further improve their usefulness.

22 August 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Zhandong LiuZhandong Liu
Zhandong Liu
SRSong Ruixia
Song Ruixia
KLKe Li
Ke Li
YLYong Li
Yong Li
Scene text understanding, serving as a cornerstone technology for autonomous navigation, document digitization, and accessibility tools, has witnessed a paradigm shift from traditional methods relying on handcrafted features and multi-stage processing pipelines to contemporary deep learning frameworks capable of learning hierarchical representations directly from raw image inputs. This survey distinctly categorizes modern scene text recognition (STR) methodologies into three principal paradigms: two-stage detection frameworks that employ region proposal networks for precise text localization, single-stage detectors designed to optimize computational efficiency, and specialized architectures tailored to handle arbitrarily shaped text through geometric-aware modeling techniques. Concurrently, an in-depth analysis of text recognition paradigms elucidates the evolutionary trajectory from connectionist temporal classification (CTC) and sequence-to-sequence models to transformer-based architectures, which excel in contextual modeling and demonstrate superior performance. In contrast to prior surveys, this work uniquely emphasizes several key differences and contributions. Firstly, it provides a comprehensive and systematic taxonomy of STR methods, explicitly highlighting the trade-offs between detection accuracy, computational efficiency, and geometric adaptability across different paradigms. Secondly, it delves into the nuances of text recognition, illustrating how transformer-based models have revolutionized the field by capturing long-range dependencies and contextual information, thereby addressing challenges in recognizing complex text layouts and multilingual scripts. Furthermore, the survey pioneers the exploration of critical research frontiers, such as multilingual text adaptation, enhancing model robustness against environmental variations (e.g., lighting conditions, occlusions), and devising data-efficient learning strategies to mitigate the dependency on large-scale annotated datasets. By synthesizing insights from technical advancements across 28 benchmark datasets and standardized evaluation protocols, this study offers researchers a holistic perspective on the current state-of-the-art, persistent challenges, and promising avenues for future research, with the ultimate goal of achieving human-level scene text comprehension.