Jiaying Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jiaying Liu has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Feng Xia
School of Computing Technologies, RMIT University
10 shared publications - Shuo Yu
School of Computer Science and Technology, Dalian University of Technology
6 shared publications - Jing Ren
RMIT University, Australia
4 shared publications - Xiangjie Kong
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China
4 shared publications - Bo Xu
Dalian University of Technology, Dalian, Liaoning, China
3 shared publications - Mingliang Hou
Guangdong Institute of Smart Education, Jinan University, Guangzhou, China
2 shared publications
Latest Publications
- 20 November 2026
- Published by Elsevier in Expert Systems with Applications
Skeleton Construction for Scientific Information System with Multi-View Graph Learning
- 20 November 2026
- Published by Elsevier in Expert Systems with Applications
Skeleton Construction for Scientific Information System with Multi-View Graph Learning
- 20 November 2026
- Published by Elsevier in Expert Systems with Applications
Painting Poetry Generation: A Benchmark Dataset and Feedback Framework for Cross-Modal Alignment
- 20 November 2026
- Published by Elsevier in Expert Systems with Applications
Painting Poetry Generation: A Benchmark Dataset and Feedback Framework for Cross-Modal Alignment
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5240-5244
PatentMerit: A Holistic System for In-depth Technology Understanding
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5240-5244
Open AccessPatentMerit: A Holistic System for In-depth Technology Understanding
- 14 July 2026
- Published by Elsevier in Technovation
- Vol. 156
Internationalization or localization? The impact of U.S.-China technological decoupling on Chinese enterprises’ knowledge acquisition
- 14 July 2026
- Published by Elsevier in Technovation
- Vol. 156
Internationalization or localization? The impact of U.S.-China technological decoupling on Chinese enterprises’ knowledge acquisition
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3656-3665
Bridging Semantic Understanding and Popularity Bias with LLMs
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3656-3665
Open AccessBridging Semantic Understanding and Popularity Bias with LLMs
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4553-4564
Explaining Synergistic Effects in Social Recommendations
In social recommenders, the inherent nonlinearity and opacity of synergistic effects across multiple social networks hinders users from understanding how diverse information is leveraged for recommendations, consequently diminishing explainability. However, existing explainers can only identify the topological information in social networks that significantly influences recommendations, failing to further explain the synergistic effects among this information. Inspired by existing findings that synergistic effects enhance mutual information between inputs and predictions to generate information gain, we extend this discovery to graph data. We quantify graph information gain to identify subgraphs embodying synergistic effects. Based on the theoretical insights, we propose SemExplainer, which explains synergistic effects by identifying subgraphs that embody them. SemExplainer first extracts explanatory subgraphs from multi-view social networks to generate preliminary importance explanations for recommendations. A conditional entropy optimization strategy to maximize information gain is developed, thereby further identifying subgraphs that embody synergistic effects from explanatory subgraphs. Finally, SemExplainer searches for paths from users to recommended items within the synergistic subgraphs to generate explanations for the recommendations. Extensive experiments on three datasets demonstrate the superiority of SemExplainer over baseline methods, providing superior explanations of synergistic effects. The implementation is available at https://github.com/yushuowiki/SemExplainer.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4553-4564
Open AccessExplaining Synergistic Effects in Social Recommendations
In social recommenders, the inherent nonlinearity and opacity of synergistic effects across multiple social networks hinders users from understanding how diverse information is leveraged for recommendations, consequently diminishing explainability. However, existing explainers can only identify the topological information in social networks that significantly influences recommendations, failing to further explain the synergistic effects among this information. Inspired by existing findings that synergistic effects enhance mutual information between inputs and predictions to generate information gain, we extend this discovery to graph data. We quantify graph information gain to identify subgraphs embodying synergistic effects. Based on the theoretical insights, we propose SemExplainer, which explains synergistic effects by identifying subgraphs that embody them. SemExplainer first extracts explanatory subgraphs from multi-view social networks to generate preliminary importance explanations for recommendations. A conditional entropy optimization strategy to maximize information gain is developed, thereby further identifying subgraphs that embody synergistic effects from explanatory subgraphs. Finally, SemExplainer searches for paths from users to recommended items within the synergistic subgraphs to generate explanations for the recommendations. Extensive experiments on three datasets demonstrate the superiority of SemExplainer over baseline methods, providing superior explanations of synergistic effects. The implementation is available at https://github.com/yushuowiki/SemExplainer.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4440-4449
Knowledge-Enhanced Multimodal Fake News Detection: Semantic Visual and Priority Fusion
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4440-4449
Open AccessKnowledge-Enhanced Multimodal Fake News Detection: Semantic Visual and Priority Fusion
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP, 1-15
Semantic-Aware Heterogeneous Graph Learning for Fake News Detection
While heterogeneous graph learning (HGL) is a promising approach for fake news detection, current methods struggle to capture complex relationships among neighborhoods due to their reliance on binary interactions. This limitation can lead to missed critical information and jeopardize performance. We address this issue by proposing a novel semantic-aware heterogeneous graph representation learning (SHEAR) method. SHEAR leverages network motifs, i.e., higher order substructures, to represent heterogeneous behavioral semantic patterns, which are then encoded into low-dimensional embeddings. The semantic information is incorporated into the news nodes by aggregating motif instance embeddings of the same type via an instance-level attention module. SHEAR assigns scores to each motif type using a semantic-level attention module, reflecting the relative importance of different semantic information. The final news node representations are obtained by fusing these embeddings. Experimental results on real-world datasets demonstrate that SHEAR significantly outperforms existing methods in fake news detection, showcasing the benefits of incorporating behavioral semantic patterns with network motifs for enhanced classification performance.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP, 1-15
Semantic-Aware Heterogeneous Graph Learning for Fake News Detection
While heterogeneous graph learning (HGL) is a promising approach for fake news detection, current methods struggle to capture complex relationships among neighborhoods due to their reliance on binary interactions. This limitation can lead to missed critical information and jeopardize performance. We address this issue by proposing a novel semantic-aware heterogeneous graph representation learning (SHEAR) method. SHEAR leverages network motifs, i.e., higher order substructures, to represent heterogeneous behavioral semantic patterns, which are then encoded into low-dimensional embeddings. The semantic information is incorporated into the news nodes by aggregating motif instance embeddings of the same type via an instance-level attention module. SHEAR assigns scores to each motif type using a semantic-level attention module, reflecting the relative importance of different semantic information. The final news node representations are obtained by fusing these embeddings. Experimental results on real-world datasets demonstrate that SHEAR significantly outperforms existing methods in fake news detection, showcasing the benefits of incorporating behavioral semantic patterns with network motifs for enhanced classification performance.
- Open Access
- 15 July 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58  (10) , 1-27
Revolutionizing scholarly impact: advanced evaluations, predictive models, and future directions
Artificial intelligence (AI) is revolutionising scholarly impact evaluation and prediction. By integrating AI and machine learning techniques, researchers can leverage diverse academic networks and multiple sources of academic big data. This integration transforms traditional evaluation methods that rely on structured measurements such as citation counts and journal impact factors, into more comprehensive and objective evaluations. In this paper, we dive deep into latest advancements in scholarly impact evaluation and prediction within the context of AI. We categorize existing models, highlighting their similarities and distinctions, with a particular emphasis on AI-enabled approaches. Building upon the analysis, we discuss the ongoing challenges in scholarly impact research and outline future directions in this field.
- 15 July 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58  (10) , 1-27
Open AccessRevolutionizing scholarly impact: advanced evaluations, predictive models, and future directions
Artificial intelligence (AI) is revolutionising scholarly impact evaluation and prediction. By integrating AI and machine learning techniques, researchers can leverage diverse academic networks and multiple sources of academic big data. This integration transforms traditional evaluation methods that rely on structured measurements such as citation counts and journal impact factors, into more comprehensive and objective evaluations. In this paper, we dive deep into latest advancements in scholarly impact evaluation and prediction within the context of AI. We categorize existing models, highlighting their similarities and distinctions, with a particular emphasis on AI-enabled approaches. Building upon the analysis, we discuss the ongoing challenges in scholarly impact research and outline future directions in this field.
- 28 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71  (00189391) , 5847-5868
Three Decades of Cross-Border Mergers and Acquisitions Research: Mapping the Field and Paths Forward
Previous reviews of cross-border mergers and acquisitions (M&As) have not provided an integrative and evolutionary analysis, and the academic literature generally reflects a fragmented research perspective. Therefore, this study combined a bibliometric analysis and text-mining to analyze the evolution of theories and topics as well as theory-topic co-occurrence. We also used a topic modelling technique to divide the articles into 10 subareas and further analyzed their subthemes and dynamics. Overall, we examined 1,197 articles published from 1989 to 2022. This study contributes to the current literature by providing data on theory-topic co-occurrence and its evolution in cross-border M&As, conducting theory-topic co-occurrence analysis that identifies popular research trends and provides new insights into how to integrate M&As practices with theories, identifying 10 sub-areas via bibliometric analysis and BERTopic modelling, and identifying key theories and emerging themes to be examined in future studies.
- 28 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71  (00189391) , 5847-5868
Three Decades of Cross-Border Mergers and Acquisitions Research: Mapping the Field and Paths Forward
Previous reviews of cross-border mergers and acquisitions (M&As) have not provided an integrative and evolutionary analysis, and the academic literature generally reflects a fragmented research perspective. Therefore, this study combined a bibliometric analysis and text-mining to analyze the evolution of theories and topics as well as theory-topic co-occurrence. We also used a topic modelling technique to divide the articles into 10 subareas and further analyzed their subthemes and dynamics. Overall, we examined 1,197 articles published from 1989 to 2022. This study contributes to the current literature by providing data on theory-topic co-occurrence and its evolution in cross-border M&As, conducting theory-topic co-occurrence analysis that identifies popular research trends and provides new insights into how to integrate M&As practices with theories, identifying 10 sub-areas via bibliometric analysis and BERTopic modelling, and identifying key theories and emerging themes to be examined in future studies.