Jiapu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jiapu Wang has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Junbin Gao
University of Sydney
10 shared publications - Baocai Yin
Beijing University of Technology
9 shared publications - Yongli Hu
Beijing University of Technology, Beijing, China
7 shared publications - Boyue Wang
Beijing University of Technology
6 shared publications - Shirui Pan
Griffith University, Australia
5 shared publications - Jiye Liang
Shanxi University
2 shared publications
Latest Publications
- Open Access
- 13 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-31
Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities
Retrieval-Augmented Generation (RAG) systems are often constrained by the “relevance myopia,” primarily focusing on fully relevant external information to supply missing or outdated facts while overlooking the potential of partially relevant knowledge to activate the internal knowledge of Large Language Models (LLMs). We challenge this paradigm by proposing that partially relevant knowledge can “awaken” latent semantic information within LLMs. We provide a theoretical framework, grounded in information theory, that explains this awakening effect: partially relevant knowledge reduces the conditional entropy of the answer by increasing the mutual information between the context and the model’s parametric knowledge. We thoroughly investigate the influence of different types of partially relevant knowledge by leveraging the gold reasoning path from Knowledge Graphs (KGs). Furthermore, we introduce a new problem called Unseen Entity Knowledge Graph Question Answering (UE-KGQA), where the entity mentioned in a question does not have a corresponding entity in the KG. Specifically, UE-KGQA simulates the realistic RAG with incomplete KGs and evaluates the effectiveness of the partially relevant knowledge. Experiments conducted on three KGQA datasets reveal that prompting with partially relevant knowledge substantially outperforms traditional similarity-based RAG methods, often susceptible to noisy and irrelevant outcomes.
- 13 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-31
Open AccessPrompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities
Retrieval-Augmented Generation (RAG) systems are often constrained by the “relevance myopia,” primarily focusing on fully relevant external information to supply missing or outdated facts while overlooking the potential of partially relevant knowledge to activate the internal knowledge of Large Language Models (LLMs). We challenge this paradigm by proposing that partially relevant knowledge can “awaken” latent semantic information within LLMs. We provide a theoretical framework, grounded in information theory, that explains this awakening effect: partially relevant knowledge reduces the conditional entropy of the answer by increasing the mutual information between the context and the model’s parametric knowledge. We thoroughly investigate the influence of different types of partially relevant knowledge by leveraging the gold reasoning path from Knowledge Graphs (KGs). Furthermore, we introduce a new problem called Unseen Entity Knowledge Graph Question Answering (UE-KGQA), where the entity mentioned in a question does not have a corresponding entity in the KG. Specifically, UE-KGQA simulates the realistic RAG with incomplete KGs and evaluates the effectiveness of the partially relevant knowledge. Experiments conducted on three KGQA datasets reveal that prompting with partially relevant knowledge substantially outperforms traditional similarity-based RAG methods, often susceptible to noisy and irrelevant outcomes.
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5202-5214
Integrating Entropy Regulation and Dual-Objective Optimization for Personalized Exercise Recommendation
Personalized exercise recommendation systems aim to enhance learning efficiency by dynamically guiding students toward content aligned with their evolving knowledge states. Among various approaches, Reinforcement Learning (RL) has emerged as an effective framework for modeling student-environment interactions as sequential decision-making processes. However, most existing RL-based methods typically reward recommendations that target unmastered knowledge concepts.Such reward-driven strategies are prone to local optima, restricting exploration of unattempted or less familiar knowledge concepts. In addition, they often overlook key learning factors, such as forgetting dynamics and exercise difficulty, leading to suboptimal outcomes. To address these issues, we propose a novel Integrating Entropy Regulation and Dual-objective Optimization Exercise Recommendation (IERDO-ER) method. Specifically, we introduce an entropy-based function to encourage broader exploration in the exercise space. We also design an end-to-end policy network that generates candidate exercises as next-step actions for the recommendation agent. To enable more adaptive and pedagogically sound recommendations, we develop a dual-objective reward mechanism that incorporates both anti-forgetting and gentleness objectives. This mechanism continuously balances policy optimization through a synergy of rewards and penalties. Experiments on three real-world educational datasets show that our approach consistently outperforms strong baselines, validating its effectiveness.
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5202-5214
Integrating Entropy Regulation and Dual-Objective Optimization for Personalized Exercise Recommendation
Personalized exercise recommendation systems aim to enhance learning efficiency by dynamically guiding students toward content aligned with their evolving knowledge states. Among various approaches, Reinforcement Learning (RL) has emerged as an effective framework for modeling student-environment interactions as sequential decision-making processes. However, most existing RL-based methods typically reward recommendations that target unmastered knowledge concepts.Such reward-driven strategies are prone to local optima, restricting exploration of unattempted or less familiar knowledge concepts. In addition, they often overlook key learning factors, such as forgetting dynamics and exercise difficulty, leading to suboptimal outcomes. To address these issues, we propose a novel Integrating Entropy Regulation and Dual-objective Optimization Exercise Recommendation (IERDO-ER) method. Specifically, we introduce an entropy-based function to encourage broader exploration in the exercise space. We also design an end-to-end policy network that generates candidate exercises as next-step actions for the recommendation agent. To enable more adaptive and pedagogically sound recommendations, we develop a dual-objective reward mechanism that incorporates both anti-forgetting and gentleness objectives. This mechanism continuously balances policy optimization through a synergy of rewards and penalties. Experiments on three real-world educational datasets show that our approach consistently outperforms strong baselines, validating its effectiveness.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 891-900
Graph-to-Tree: Topological Decomposition for Self-Supervised Learning
Every graph hides a tree: through tree decomposition—a foundational tool in modern graph theory with broad applications such as in computational power networks, any network can be unfolded into a hierarchy of overlapping vertex bags whose backbone is a tree. Leveraging this powerful lens, we propose Topological Decomposition for Self-supervised Learning (TopDSL), a framework that injects multi-scale signals into graph representation learning. Concretely, we: 1) decompose the input graph into tree structures with bags representing local structural contexts; 2) compute bag-level roles via closeness centrality for nodes and local edge betweenness for edges, and aggregate these scores across bags to capture context-dependent importance (e.g., local structural bridges); 3) convert the resulting importance and attribute-stability scores into a context-aware augmentation policy that adaptively perturbs nodes, edges, and features—preserving local bridges, honoring multi-community vertices, and attenuating noisy global hubs; 4) construct a new structural similarity loss for contrastive learning, which fuses traditional graph-based proximity with a novel tree-based similarity derived from node co-occurrence in decomposition bags; 5) demonstrate that our framework achieves superior performance over state-of-the-art baselines on various graph learning benchmarks.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 891-900
Open AccessGraph-to-Tree: Topological Decomposition for Self-Supervised Learning
Every graph hides a tree: through tree decomposition—a foundational tool in modern graph theory with broad applications such as in computational power networks, any network can be unfolded into a hierarchy of overlapping vertex bags whose backbone is a tree. Leveraging this powerful lens, we propose Topological Decomposition for Self-supervised Learning (TopDSL), a framework that injects multi-scale signals into graph representation learning. Concretely, we: 1) decompose the input graph into tree structures with bags representing local structural contexts; 2) compute bag-level roles via closeness centrality for nodes and local edge betweenness for edges, and aggregate these scores across bags to capture context-dependent importance (e.g., local structural bridges); 3) convert the resulting importance and attribute-stability scores into a context-aware augmentation policy that adaptively perturbs nodes, edges, and features—preserving local bridges, honoring multi-community vertices, and attenuating noisy global hubs; 4) construct a new structural similarity loss for contrastive learning, which fuses traditional graph-based proximity with a novel tree-based similarity derived from node co-occurrence in decomposition bags; 5) demonstrate that our framework achieves superior performance over state-of-the-art baselines on various graph learning benchmarks.
- 23 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 341
Multi-faceted contrastive learning with inter-frame difference for traffic video question answering
- 23 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 341
Multi-faceted contrastive learning with inter-frame difference for traffic video question answering
- Top Cited Papers
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (3) , 2839-2852
ComGRL: Comprehensive Graph Representation Learning From Local to Global Bridged by Mixup
Graph neural networks (GNNs) have demonstrated remarkable effectiveness in various graph representation learning tasks. However, most of existing methods achieve the information extraction by the simple fusion of local and global information, which is a coarse-grained and static way. This may hinder the establishment of a dynamic and collaborative interaction between global and local information, which is crucial for comprehensively understanding graph data. To address this challenge, we propose a novel framework called comprehensive graph representation learning (ComGRL). ComGRL integrates local information into global information to derive powerful representations. It achieves this by implicitly smoothing local information through flexible graph contrastive learning, ensuring reliable representations for subsequent global exploration. Then ComGRL transfers the locally derived representations to a multihead self-attention module, enhancing their discriminative ability by uncovering diverse and rich global correlations. To achieve dynamic transformation between global and local information under self-supervision with pseudo-labels, ComGRL employs a triple sampling strategy to construct mixed node pairs and applies reliable Mixup augmentation across attributes and structure for the main frameworks. This approach broadens the receptive field and facilitates coordination between local and global representation learning, enabling them to reinforce each other. Experimental results across six widely used graph datasets demonstrate that ComGRL achieves excellent performance in node classification tasks. The code could be available at https://github.com/JinluWang1002/ComGRL.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (3) , 2839-2852
Top Cited PapersComGRL: Comprehensive Graph Representation Learning From Local to Global Bridged by Mixup
Graph neural networks (GNNs) have demonstrated remarkable effectiveness in various graph representation learning tasks. However, most of existing methods achieve the information extraction by the simple fusion of local and global information, which is a coarse-grained and static way. This may hinder the establishment of a dynamic and collaborative interaction between global and local information, which is crucial for comprehensively understanding graph data. To address this challenge, we propose a novel framework called comprehensive graph representation learning (ComGRL). ComGRL integrates local information into global information to derive powerful representations. It achieves this by implicitly smoothing local information through flexible graph contrastive learning, ensuring reliable representations for subsequent global exploration. Then ComGRL transfers the locally derived representations to a multihead self-attention module, enhancing their discriminative ability by uncovering diverse and rich global correlations. To achieve dynamic transformation between global and local information under self-supervision with pseudo-labels, ComGRL employs a triple sampling strategy to construct mixed node pairs and applies reliable Mixup augmentation across attributes and structure for the main frameworks. This approach broadens the receptive field and facilitates coordination between local and global representation learning, enabling them to reinforce each other. Experimental results across six widely used graph datasets demonstrate that ComGRL achieves excellent performance in node classification tasks. The code could be available at https://github.com/JinluWang1002/ComGRL.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 935-944
Large-Small Model Synergy with Multimodal Fine-Grained Heuristics for Knowledge-Based Visual Question Answering
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 935-944
Open AccessLarge-Small Model Synergy with Multimodal Fine-Grained Heuristics for Knowledge-Based Visual Question Answering
- 11 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (12) , 6959-6972
Atomic Fact Decomposition Helps Attributed Question Answering
Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a given question. Retrieval is a widely adopted approach, including two general paradigms: Retrieval-Then-Read (RTR) and post-hoc retrieval. Recently, Large Language Models (LLMs) have shown remarkable proficiency, prompting growing interest in AQA among researchers. However, RTR-based AQA often suffers from irrelevant knowledge and rapidly changing information, even when LLMs are adopted, while post-hoc retrieval-based AQA struggles with comprehending long-form answers with complex logic, and precisely identifying the content needing revision and preserving the original intent. To tackle these problems, this paper proposes an Atomic fact decomposition-based Retrieval and Editing (ARE) framework, which decomposes the generated long-form answers into molecular clauses and atomic facts by the instruction-tuned LLMs. Notably, the instruction-tuned LLMs are fine-tuned using a well-constructed dataset, generated from large scale Knowledge Graphs (KGs). This process involves extracting one-hop neighbors from a given set of entities and transforming the result into coherent long-form text. Subsequently, ARE leverages a search engine to retrieve evidences related to atomic facts, inputting these evidences into an LLM-based verifier to determine whether the facts require expansion for re-retrieval or editing. Furthermore, the edited facts are backtracked into the original answer, with evidence aggregated based on the relationship between molecular clauses and atomic facts. Extensive evaluations demonstrate the superior performance of our proposed method over the state-of-the-arts on several datasets, with an additionally proposed new metric$Attr_{p}$ for evaluating the precision of evidence attribution.- 11 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (12) , 6959-6972
Atomic Fact Decomposition Helps Attributed Question Answering
Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a given question. Retrieval is a widely adopted approach, including two general paradigms: Retrieval-Then-Read (RTR) and post-hoc retrieval. Recently, Large Language Models (LLMs) have shown remarkable proficiency, prompting growing interest in AQA among researchers. However, RTR-based AQA often suffers from irrelevant knowledge and rapidly changing information, even when LLMs are adopted, while post-hoc retrieval-based AQA struggles with comprehending long-form answers with complex logic, and precisely identifying the content needing revision and preserving the original intent. To tackle these problems, this paper proposes an Atomic fact decomposition-based Retrieval and Editing (ARE) framework, which decomposes the generated long-form answers into molecular clauses and atomic facts by the instruction-tuned LLMs. Notably, the instruction-tuned LLMs are fine-tuned using a well-constructed dataset, generated from large scale Knowledge Graphs (KGs). This process involves extracting one-hop neighbors from a given set of entities and transforming the result into coherent long-form text. Subsequently, ARE leverages a search engine to retrieve evidences related to atomic facts, inputting these evidences into an LLM-based verifier to determine whether the facts require expansion for re-retrieval or editing. Furthermore, the edited facts are backtracked into the original answer, with evidence aggregated based on the relationship between molecular clauses and atomic facts. Extensive evaluations demonstrate the superior performance of our proposed method over the state-of-the-arts on several datasets, with an additionally proposed new metric$Attr_{p}$ for evaluating the precision of evidence attribution.- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4780-4792
Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4780-4792
Open AccessEffective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs
- 21 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (10) , 5818-5831
MADE: Multicurvature Adaptive Embedding for Temporal Knowledge Graph Completion
Temporal knowledge graphs (TKGs) are receiving increased attention due to their time-dependent properties and the evolving nature of knowledge over time. TKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, which can often be mixed together. However, embedding TKGs into Euclidean space, as is typically done with TKG completion (TKGC) models, presents a challenge when dealing with high-dimensional nonlinear data and complex geometric structures. To address this issue, we propose a novel TKGC model called multicurvature adaptive embedding (MADE). MADE models TKGs in multicurvature spaces, including flat Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature), to handle multiple geometric structures. We assign different weights to different curvature spaces in a data-driven manner to strengthen the ideal curvature spaces for modeling and weaken the inappropriate ones. Additionally, we introduce the quadruplet distributor (QD) to assist the information interaction in each geometric space. Ultimately, we develop an innovative temporal regularization to enhance the smoothness of timestamp embeddings by strengthening the correlation of neighboring timestamps. Experimental results show that MADE outperforms the existing state-of-the-art TKGC models.
- 21 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (10) , 5818-5831
MADE: Multicurvature Adaptive Embedding for Temporal Knowledge Graph Completion
Temporal knowledge graphs (TKGs) are receiving increased attention due to their time-dependent properties and the evolving nature of knowledge over time. TKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, which can often be mixed together. However, embedding TKGs into Euclidean space, as is typically done with TKG completion (TKGC) models, presents a challenge when dealing with high-dimensional nonlinear data and complex geometric structures. To address this issue, we propose a novel TKGC model called multicurvature adaptive embedding (MADE). MADE models TKGs in multicurvature spaces, including flat Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature), to handle multiple geometric structures. We assign different weights to different curvature spaces in a data-driven manner to strengthen the ideal curvature spaces for modeling and weaken the inappropriate ones. Additionally, we introduce the quadruplet distributor (QD) to assist the information interaction in each geometric space. Ultimately, we develop an innovative temporal regularization to enhance the smoothness of timestamp embeddings by strengthening the correlation of neighboring timestamps. Experimental results show that MADE outperforms the existing state-of-the-art TKGC models.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1954-1962
IME: Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completion
Temporal Knowledge Graphs (TKGs) incorporate a temporal dimension, allowing for a precise capture of the evolution of knowledge and reflecting the dynamic nature of the real world. Typically, TKGs contain complex geometric structures, with various geometric structures interwoven. However, existing Temporal Knowledge Graph Completion (TKGC) methods either model TKGs in a single space or neglect the heterogeneity of different curvature spaces, thus constraining their capacity to capture these intricate geometric structures. In this paper, we propose a novel Integrating Multi-curvature shared and specific Embedding (IME) model for TKGC tasks. Concretely, IME models TKGs into multi-curvature spaces, including hyperspherical, hyperbolic, and Euclidean spaces. Subsequently, IME incorporates two key properties, namely space-shared property and space-specific property. The space-shared property facilitates the learning of commonalities across different curvature spaces and alleviates the spatial gap caused by the heterogeneous nature of multi-curvature spaces, while the space-specific property captures characteristic features. Meanwhile, IME proposes an Adjustable Multi-curvature Pooling (AMP) approach to effectively retain important information. Furthermore, IME innovatively designs similarity, difference, and structure loss functions to attain the stated objective. Experimental results clearly demonstrate the superior performance of IME over existing state-of-the-art TKGC models.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1954-1962
Open AccessIME: Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completion
Temporal Knowledge Graphs (TKGs) incorporate a temporal dimension, allowing for a precise capture of the evolution of knowledge and reflecting the dynamic nature of the real world. Typically, TKGs contain complex geometric structures, with various geometric structures interwoven. However, existing Temporal Knowledge Graph Completion (TKGC) methods either model TKGs in a single space or neglect the heterogeneity of different curvature spaces, thus constraining their capacity to capture these intricate geometric structures. In this paper, we propose a novel Integrating Multi-curvature shared and specific Embedding (IME) model for TKGC tasks. Concretely, IME models TKGs into multi-curvature spaces, including hyperspherical, hyperbolic, and Euclidean spaces. Subsequently, IME incorporates two key properties, namely space-shared property and space-specific property. The space-shared property facilitates the learning of commonalities across different curvature spaces and alleviates the spatial gap caused by the heterogeneous nature of multi-curvature spaces, while the space-specific property captures characteristic features. Meanwhile, IME proposes an Adjustable Multi-curvature Pooling (AMP) approach to effectively retain important information. Furthermore, IME innovatively designs similarity, difference, and structure loss functions to attain the stated objective. Experimental results clearly demonstrate the superior performance of IME over existing state-of-the-art TKGC models.