Ling Ding
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
Research Subjects
Research Interests
Ling Ding has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Yang Xiang
Tongji University, Shanghai, China
6 shared publications - Bo Zhang
Shanghai Normal University
4 shared publications - Jianting Chen
Tongji University, Shanghai, China
3 shared publications Chang Guo
2 shared publicationsMeizi Li
2 shared publications- Meizi Li
College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, China
2 shared publications
Latest Publications
- 3 October 2026
- Published by Elsevier in Information Sciences
- Vol. 762
HeRaKT: Heterogeneous bidirectional modeling for response-aware knowledge tracing
- 3 October 2026
- Published by Elsevier in Information Sciences
- Vol. 762
HeRaKT: Heterogeneous bidirectional modeling for response-aware knowledge tracing
- 19 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
SIGNAL: Synergistic multi-granularity semantic alignment learning for multimodal recommendation
- 19 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
SIGNAL: Synergistic multi-granularity semantic alignment learning for multimodal recommendation
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (3) , 3288-3305
Uncertainty-Aware Bayesian Graph Convolutional Network With Sequential Transfer Learning: A Framework for Gravitational Source Identification in Social Networks
Social networks exhibit a Gravitational Field phenomenon, where key nodes, called Gravitational Sources, generate influential zones in their neighborhoods. Traditional methods mainly rely on centrality metrics or heuristic approaches that estimate influence. But they fail to capture the dual characteristics of topology and dynamics required for accurately identifying Gravitational Sources. Identifying Gravitational Sources faces three main challenges: 1) how to construct an effective evaluation mechanism to calculate gravitational source scores; 2) how to achieve effective model training in large-scale network environments with label scarcity; and 3) how to quantify the uncertainty of prediction results to enhance identification reliability. To address these challenges, we propose uncertainty-aware Bayesian graph convolutional network with sequential transfer learning (UBGCN-STL). Our approach integrates an evaluation method that combines centrality and influence metrics, employs a sequential transfer learning strategy to leverage knowledge from label-rich small networks for large networks, and incorporates a Bayesian mechanism for uncertainty-aware predictions. Experiments on seven real-world networks (social, protein interaction, and animal networks) show that UBGCN-STL outperforms representative baseline methods based on centrality, network structure, or learning models (LCNN, NDM, IpGCN), achieving superior predictive performance and reliable uncertainty quantification even with limited labels.
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (3) , 3288-3305
Uncertainty-Aware Bayesian Graph Convolutional Network With Sequential Transfer Learning: A Framework for Gravitational Source Identification in Social Networks
Social networks exhibit a Gravitational Field phenomenon, where key nodes, called Gravitational Sources, generate influential zones in their neighborhoods. Traditional methods mainly rely on centrality metrics or heuristic approaches that estimate influence. But they fail to capture the dual characteristics of topology and dynamics required for accurately identifying Gravitational Sources. Identifying Gravitational Sources faces three main challenges: 1) how to construct an effective evaluation mechanism to calculate gravitational source scores; 2) how to achieve effective model training in large-scale network environments with label scarcity; and 3) how to quantify the uncertainty of prediction results to enhance identification reliability. To address these challenges, we propose uncertainty-aware Bayesian graph convolutional network with sequential transfer learning (UBGCN-STL). Our approach integrates an evaluation method that combines centrality and influence metrics, employs a sequential transfer learning strategy to leverage knowledge from label-rich small networks for large networks, and incorporates a Bayesian mechanism for uncertainty-aware predictions. Experiments on seven real-world networks (social, protein interaction, and animal networks) show that UBGCN-STL outperforms representative baseline methods based on centrality, network structure, or learning models (LCNN, NDM, IpGCN), achieving superior predictive performance and reliable uncertainty quantification even with limited labels.
- 12 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 326
Intent disentangling model with hypergraph for next POI recommendation
- 12 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 326
Intent disentangling model with hypergraph for next POI recommendation
- 25 October 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 330
Dual contrastive learning-based hypergraph convolutional network for aspect-based sentiment classification
- 25 October 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 330
Dual contrastive learning-based hypergraph convolutional network for aspect-based sentiment classification
- 19 February 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (4) , 1-27
Reinforced logical reasoning over KGs for interpretable recommendation system
- 19 February 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (4) , 1-27
Reinforced logical reasoning over KGs for interpretable recommendation system
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
SeCor: Aligning Semantic and Collaborative Representations by Large Language Models for Next-Point-of-Interest Recommendations
The widespread adoption of location-based applications has created a growing demand for point-of-interest (POI) recommendation, which aims to predict a user’s next POI based on their historical check-in data and current location. However, existing methods often struggle to capture the intricate relationships within check-in data. This is largely due to their limitations in representing temporal and spatial information and underutilizing rich semantic features. While large language models (LLMs) offer powerful semantic comprehension to solve them, they are limited by hallucination and the inability to incorporate global collaborative information. To address these issues, we propose a novel method SeCor, which treats POI recommendation as a multi-modal task and integrates semantic and collaborative representations to form an efficient hybrid encoding. SeCor first employs a basic collaborative filtering model to mine interaction features. These embeddings, as one modal information, are fed into LLM to align with semantic representation, leading to efficient hybrid embeddings. To mitigate the hallucination, SeCor recommends based on the hybrid embeddings rather than directly using the LLM’s output text. Extensive experiments on three public real-world datasets show that SeCor outperforms all baselines, achieving improved recommendation performance by effectively integrating collaborative and semantic information through LLMs.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessSeCor: Aligning Semantic and Collaborative Representations by Large Language Models for Next-Point-of-Interest Recommendations
The widespread adoption of location-based applications has created a growing demand for point-of-interest (POI) recommendation, which aims to predict a user’s next POI based on their historical check-in data and current location. However, existing methods often struggle to capture the intricate relationships within check-in data. This is largely due to their limitations in representing temporal and spatial information and underutilizing rich semantic features. While large language models (LLMs) offer powerful semantic comprehension to solve them, they are limited by hallucination and the inability to incorporate global collaborative information. To address these issues, we propose a novel method SeCor, which treats POI recommendation as a multi-modal task and integrates semantic and collaborative representations to form an efficient hybrid encoding. SeCor first employs a basic collaborative filtering model to mine interaction features. These embeddings, as one modal information, are fed into LLM to align with semantic representation, leading to efficient hybrid embeddings. To mitigate the hallucination, SeCor recommends based on the hybrid embeddings rather than directly using the LLM’s output text. Extensive experiments on three public real-world datasets show that SeCor outperforms all baselines, achieving improved recommendation performance by effectively integrating collaborative and semantic information through LLMs.
- Open Access
- 20 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (7) , 1-21
MABERT: Mask-Attention-Based BERT for Chinese Event Extraction
Event extraction is an essential but challenging task in information extraction. This task has considerably benefited from pre-trained language models, such as BERT. However, when it comes to the trigger-word mismatch problem in languages without natural delimiters, existing methods ignore the complement of lexical information to BERT. In addition, the inherent multi-role noise problem could limit the performance of methods when one sentence contains multiple events. In this article, we propose a Mask-Attention-based BERT (MABERT) framework for Chinese event extraction to address the above problems. Firstly, in order to avoid trigger-word mismatch and integrate lexical features into BERT layers directly, a mask-attention-based transformer augmented with two mask matrices is devised to replace the original one in BERT. By the mask-attention-based transformer, the character sequence interacts with external lexical semantics sufficiently and keeps its structure information at the same time. Moreover, against the multi-role noise problem, we make use of event type information from representation and classification, two aspects to enrich entity features, where type markers and event-schema-based mask matrix are proposed. Experimental results on the widely used ACE2005 dataset show the effectiveness of our proposed MABERT on Chinese event extraction task compared with other state-of-the-art methods.
- 20 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (7) , 1-21
Open AccessMABERT: Mask-Attention-Based BERT for Chinese Event Extraction
Event extraction is an essential but challenging task in information extraction. This task has considerably benefited from pre-trained language models, such as BERT. However, when it comes to the trigger-word mismatch problem in languages without natural delimiters, existing methods ignore the complement of lexical information to BERT. In addition, the inherent multi-role noise problem could limit the performance of methods when one sentence contains multiple events. In this article, we propose a Mask-Attention-based BERT (MABERT) framework for Chinese event extraction to address the above problems. Firstly, in order to avoid trigger-word mismatch and integrate lexical features into BERT layers directly, a mask-attention-based transformer augmented with two mask matrices is devised to replace the original one in BERT. By the mask-attention-based transformer, the character sequence interacts with external lexical semantics sufficiently and keeps its structure information at the same time. Moreover, against the multi-role noise problem, we make use of event type information from representation and classification, two aspects to enrich entity features, where type markers and event-schema-based mask matrix are proposed. Experimental results on the widely used ACE2005 dataset show the effectiveness of our proposed MABERT on Chinese event extraction task compared with other state-of-the-art methods.
- 26 March 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 200
Hybrid neural tagging model for open relation extraction
- 26 March 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 200
Hybrid neural tagging model for open relation extraction
- 25 April 2021
- Vol. 38 (2) , 333-341
[Brain tissue microstructure parameters estimation method based on proximal gradient network].
Diffusion tensor imaging technology can provide information on the white matter of the brain, which can be used to explore changes in brain tissue structure, but it lacks the specific description of the microstructure information of brain tissue. The neurite orientation dispersion and density imaging make up for its shortcomings. But in order to accurately estimate the brain microstructure, a large number of diffusion gradients are needed, and the calculation is complex and time-consuming through maximum likelihood fitting. Therefore, this paper proposes a kind of microstructure parameters estimation method based on the proximal gradient network, which further avoids the classic fitting paradigm. The method can accurately estimate the parameters while reducing the number of diffusion gradients, and achieve the purpose of imaging quality better than the neurite orientation dispersion and density imaging model and accelerated microstructure imaging via convex optimization model.
- 25 April 2021
- Vol. 38 (2) , 333-341
[Brain tissue microstructure parameters estimation method based on proximal gradient network].
Diffusion tensor imaging technology can provide information on the white matter of the brain, which can be used to explore changes in brain tissue structure, but it lacks the specific description of the microstructure information of brain tissue. The neurite orientation dispersion and density imaging make up for its shortcomings. But in order to accurately estimate the brain microstructure, a large number of diffusion gradients are needed, and the calculation is complex and time-consuming through maximum likelihood fitting. Therefore, this paper proposes a kind of microstructure parameters estimation method based on the proximal gradient network, which further avoids the classic fitting paradigm. The method can accurately estimate the parameters while reducing the number of diffusion gradients, and achieve the purpose of imaging quality better than the neurite orientation dispersion and density imaging model and accelerated microstructure imaging via convex optimization model.