Pub Date : 2026-01-19DOI: 10.1016/j.ipm.2026.104638
Zhishuo Zhang , Hu Liu , Tao Shi , Qian Li , Huayong Niu
This study develops a systematic Measurement–Analysis–Prediction framework to evaluate global digital economy efficiency using data from 114 countries over 2006–2023. Efficiency is decomposed into two stages—infrastructure transformation and value creation and international competitiveness—measured via a super-efficiency sequential Slack-Based Measure (SBM) model. Regional disparities are examined with the Dagum Gini coefficient, and machine learning models are employed for prediction, with Random Forest (RF) identified as the optimal predictor. Results show that global digital economy efficiency has shown a fluctuating upward trend, with Stage 1 (infrastructure transformation) consistently outperforms Stage 2 (value creation). Notably, 2021 marked a significant turning point for infrastructure transformation efficiency, with the efficiency value surging to 0.2883 due to pandemic-induced digital demand. Europe achieves the highest efficiency, while Asia and the Americas exhibit strong internal polarization; overall disparities are driven mainly by net inter-regional gaps. Machine learning predictions indicate efficiency will increase from 0.3210 in 2024 to 0.3566 in 2028, though regional imbalances are expected to persist. Overall, this study provides robust empirical evidence and a comprehensive framework for understanding the transmission mechanisms of digital economy efficiency, interpreting global disparity patterns, and guiding policy formulation.
{"title":"Measuring and forecasting global digital economy efficiency: An integrated approach using the super-efficiency sequential SBM model and machine learning algorithms","authors":"Zhishuo Zhang , Hu Liu , Tao Shi , Qian Li , Huayong Niu","doi":"10.1016/j.ipm.2026.104638","DOIUrl":"10.1016/j.ipm.2026.104638","url":null,"abstract":"<div><div>This study develops a systematic <em>Measurement–Analysis–Prediction</em> framework to evaluate global digital economy efficiency using data from 114 countries over 2006–2023. Efficiency is decomposed into two stages—<em>infrastructure transformation</em> and <em>value creation and international competitiveness</em>—measured via a super-efficiency sequential Slack-Based Measure (SBM) model. Regional disparities are examined with the Dagum Gini coefficient, and machine learning models are employed for prediction, with Random Forest (RF) identified as the optimal predictor. Results show that global digital economy efficiency has shown a fluctuating upward trend, with Stage 1 (infrastructure transformation) consistently outperforms Stage 2 (value creation). Notably, 2021 marked a significant turning point for infrastructure transformation efficiency, with the efficiency value surging to 0.2883 due to pandemic-induced digital demand. Europe achieves the highest efficiency, while Asia and the Americas exhibit strong internal polarization; overall disparities are driven mainly by net inter-regional gaps. Machine learning predictions indicate efficiency will increase from 0.3210 in 2024 to 0.3566 in 2028, though regional imbalances are expected to persist. Overall, this study provides robust empirical evidence and a comprehensive framework for understanding the transmission mechanisms of digital economy efficiency, interpreting global disparity patterns, and guiding policy formulation.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104638"},"PeriodicalIF":6.9,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-18DOI: 10.1016/j.ipm.2025.104583
Xiangkun Ban , Guang-Hai Liu , Zhou Lu , Bo-Jian Zhang
Image retrieval based on knowledge distillation has enormous potential for lightweight image retrieval. However, existing methods often transfer redundant or inconsistent knowledge to a single student model, resulting in it still rely on the teacher model during the inference phase. To address this problem, an efficient knowledge distillation method based on the multi-teacher distillation framework is proposed to form the basis for lightweight image retrieval, namely the correlation guided distillation (CGD), where correlation coefficient fusion and Cosine-based product quantization are two novel components. The former effectively mitigates noise and conflicting supervision in multi-teacher fusion, the latter encodes rich directional semantics to enhance structural alignment. The whitened teacher features are fused via using correlation coefficient fusion method, which is used to guide the student model through the structural similarity supervision provided by Cosine-based product quantization. Extensive experiments on several benchmark datasets demonstrate that our distillation framework achieves superior performance compared with the latest teacher-dependent methods under the same settings. In terms of the mAP scores with the M and H protocol setups, the performances are improved by 4.1% and 4.5% on the ROxford dataset, and by 2.1% and 4.4% on the RParis dataset. On the large-scale variants with 1 M distractor images, the respective improvements reach 7.9% and 9.0% on ROxford+1M, and 3.3% and 6.6% on RParis+1M. Furthermore, when using only the student model, our CGD method is up to 48.83 × faster than the teacher-dependent methods, without reducing retrieval performance.
{"title":"Correlation guided multi-teacher distillation for lightweight image retrieval","authors":"Xiangkun Ban , Guang-Hai Liu , Zhou Lu , Bo-Jian Zhang","doi":"10.1016/j.ipm.2025.104583","DOIUrl":"10.1016/j.ipm.2025.104583","url":null,"abstract":"<div><div>Image retrieval based on knowledge distillation has enormous potential for lightweight image retrieval. However, existing methods often transfer redundant or inconsistent knowledge to a single student model, resulting in it still rely on the teacher model during the inference phase. To address this problem, an efficient knowledge distillation method based on the multi-teacher distillation framework is proposed to form the basis for lightweight image retrieval, namely the correlation guided distillation (CGD), where correlation coefficient fusion and Cosine-based product quantization are two novel components. The former effectively mitigates noise and conflicting supervision in multi-teacher fusion, the latter encodes rich directional semantics to enhance structural alignment. The whitened teacher features are fused via using correlation coefficient fusion method, which is used to guide the student model through the structural similarity supervision provided by Cosine-based product quantization. Extensive experiments on several benchmark datasets demonstrate that our distillation framework achieves superior performance compared with the latest teacher-dependent methods under the same settings. In terms of the mAP scores with the M and H protocol setups, the performances are improved by 4.1% and 4.5% on the ROxford dataset, and by 2.1% and 4.4% on the RParis dataset. On the large-scale variants with 1 M distractor images, the respective improvements reach 7.9% and 9.0% on ROxford+1M, and 3.3% and 6.6% on RParis+1M. Furthermore, when using only the student model, our CGD method is up to 48.83 × faster than the teacher-dependent methods, without reducing retrieval performance.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104583"},"PeriodicalIF":6.9,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-16DOI: 10.1016/j.ipm.2026.104613
Memoona Saleem , Zahoor Ur Rehman , Raja Hashim Ali , Ujala Akmal , Ali Zeeshan Ijaz , Raja Manzar Abbas
The recent model and conceptual advancements in Artificial Intelligence (AI) and Natural Language Processing (NLP) are changing how knowledge-intensive tasks are giving more reliable and creative decisions. Particularly, the advancements in NLP has completely changed the way human language is processed, is understood, and is then used for generating human language. These updates are useful for the deeper analysis of textual content that support information systems and their management. For example, in the field of education, these technologies offer advanced and more intelligent tools, which enhance education through improved learning experiences, optimized assessments, and other teaching and study mechanisms. In this paper, we have worked on a unified framework for automatic questions generation (AQG) and educational content analysis. For this purpose, we have developed Questify-TheEduBot, which integrates transformer-based models (BERT, GPT), Latent Dirichlet Allocation (LDA), sentiment analysis, and keyword extraction into a single pipeline. Existing tools typically address isolated tasks but our tool generates multiple types of questions, i.e., multiple choice questions (MCQs), cloze, as well as descriptive type of questions. In addition to AQG, Questify-TheEduBot simultaneously validates semantic coherence, topic coverage, and sentiment appropriateness. We have evaluated and compared our model on SQuAD v2.0 and LearningQ datasets, which consists of over 300,000 Question Answer pairs. Questify-TheEduBot demonstrated excellent performance on the test datasets, with cosine similarity above 0.85, keyword overlap of 87%, and topic modeling precision of 89%. Human evaluation further confirms the pedagogical relevance of generated questions, where our study shows significant improvements over template-based and Seq2Seq competing baseline models. The web-based platform of our tool offers instructors and learners with a tested, interpretable, and resource-efficient tool for automated assessment, support in curriculum development, and enables personalized learning. By merging automated question generation and content analytics, Questify-TheEduBot advances the state of NLP in the field of education, where it provides actionable insights for information management in digital learning environments.
{"title":"An information processing framework for education: Supporting automatic question generation with NLP to minimize human intervention","authors":"Memoona Saleem , Zahoor Ur Rehman , Raja Hashim Ali , Ujala Akmal , Ali Zeeshan Ijaz , Raja Manzar Abbas","doi":"10.1016/j.ipm.2026.104613","DOIUrl":"10.1016/j.ipm.2026.104613","url":null,"abstract":"<div><div>The recent model and conceptual advancements in Artificial Intelligence (AI) and Natural Language Processing (NLP) are changing how knowledge-intensive tasks are giving more reliable and creative decisions. Particularly, the advancements in NLP has completely changed the way human language is processed, is understood, and is then used for generating human language. These updates are useful for the deeper analysis of textual content that support information systems and their management. For example, in the field of education, these technologies offer advanced and more intelligent tools, which enhance education through improved learning experiences, optimized assessments, and other teaching and study mechanisms. In this paper, we have worked on a unified framework for automatic questions generation (AQG) and educational content analysis. For this purpose, we have developed Questify-TheEduBot, which integrates transformer-based models (BERT, GPT), Latent Dirichlet Allocation (LDA), sentiment analysis, and keyword extraction into a single pipeline. Existing tools typically address isolated tasks but our tool generates multiple types of questions, i.e., multiple choice questions (MCQs), cloze, as well as descriptive type of questions. In addition to AQG, Questify-TheEduBot simultaneously validates semantic coherence, topic coverage, and sentiment appropriateness. We have evaluated and compared our model on SQuAD v2.0 and LearningQ datasets, which consists of over 300,000 Question Answer pairs. Questify-TheEduBot demonstrated excellent performance on the test datasets, with cosine similarity above 0.85, keyword overlap of 87%, and topic modeling precision of 89%. Human evaluation further confirms the pedagogical relevance of generated questions, where our study shows significant improvements over template-based and Seq2Seq competing baseline models. The web-based platform of our tool offers instructors and learners with a tested, interpretable, and resource-efficient tool for automated assessment, support in curriculum development, and enables personalized learning. By merging automated question generation and content analytics, Questify-TheEduBot advances the state of NLP in the field of education, where it provides actionable insights for information management in digital learning environments.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104613"},"PeriodicalIF":6.9,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-15DOI: 10.1016/j.ipm.2025.104607
Min Tang , Lixin Zou , Shujie Cui , Weiqing Wang , Zhe Jin , Chengliang Li , Shiuan-Ni Liang
Translating natural language queries into executable SQL queries (Text-to-SQL) is essential for human-database interaction but remains a challenging task, especially for complex queries. Existing methods based on large language models (LLMs) often rely on supervised fine-tuning or iterative refinement based on execution success. However, these methods overlook errors that occur during the generation process, leading to error propagation issues. To address this, we propose the Q-value guided Text-to-SQL, which trains a Q-value network to evaluate SQL potential and avoid generation errors. Specifically, QSQL decomposes the complex SQL generation process into simpler and helpful intermediate steps, such as selection, schema linking, sub-query generation, and combination. Then, we adopt Monte Carlo Tree Search (MCTS) to estimate Q-values of each step and incorporate rule-based consensus filtering to eliminate inconsistent/low-quality data, removing the need for extra human annotations. Finally, a Q-value probe network approximates the estimated values for efficient generation. Experimental results on the Spider and Bird benchmarks show that QSQL achieves a superior balance between execution accuracy and inference efficiency. Compared to a baseline MCTS approach, QSQL improves execution accuracy by 9% while reducing inference time to just 11.9%.
{"title":"Q-value guided Text-to-SQL generation: Structured reasoning meets efficient inference exploration","authors":"Min Tang , Lixin Zou , Shujie Cui , Weiqing Wang , Zhe Jin , Chengliang Li , Shiuan-Ni Liang","doi":"10.1016/j.ipm.2025.104607","DOIUrl":"10.1016/j.ipm.2025.104607","url":null,"abstract":"<div><div>Translating natural language queries into executable SQL queries (Text-to-SQL) is essential for human-database interaction but remains a challenging task, especially for complex queries. Existing methods based on large language models (LLMs) often rely on supervised fine-tuning or iterative refinement based on execution success. However, these methods overlook errors that occur during the generation process, leading to error propagation issues. To address this, we propose the <em>Q</em>-value guided Text-to-SQL, which trains a <em>Q</em>-value network to evaluate SQL potential and avoid generation errors. Specifically, QSQL decomposes the complex SQL generation process into simpler and helpful intermediate steps, such as selection, schema linking, sub-query generation, and combination. Then, we adopt Monte Carlo Tree Search (MCTS) to estimate <em>Q</em>-values of each step and incorporate rule-based consensus filtering to eliminate inconsistent/low-quality data, removing the need for extra human annotations. Finally, a <em>Q</em>-value probe network approximates the estimated values for efficient generation. Experimental results on the <span>Spider</span> and <span>Bird</span> benchmarks show that QSQL achieves a superior balance between execution accuracy and inference efficiency. Compared to a baseline MCTS approach, QSQL improves execution accuracy by <strong>9%</strong> while reducing inference time to just <strong>11.9%</strong>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104607"},"PeriodicalIF":6.9,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-15DOI: 10.1016/j.ipm.2025.104602
Jiapei Hu , Yifan Lyu , Yifan Chen , Kuntao Li , Yun Xue , Jinghua Liang
Chinese harmful memes convey toxicity on social media through varied semantic complexity and diverse modality combinations. However, existing detection methods typically adopt static architectures with fixed interaction patterns, which lack the flexibility to accurately identify harmful cues embedded in heterogeneous semantic and modal content across different memes, hindering a comprehensive understanding of toxic intent. To address this limitation, we propose the Multi-View Dynamic Perception (MDP) framework, a dynamic interaction paradigm specifically designed for Chinese harmful meme detection. Specifically, we develop five types of semantic perception nodes to synchronously extract features from diverse views. These nodes are densely stacked to form two perception branches, respectively guided by textual and visual features, to effectively capture modality-specific cues. To enhance adaptability, each node is equipped with an independent soft router that dynamically regulates information flow and enables flexible interaction patterns tailored to different memes. Furthermore, we introduce a Hierarchical Mutual Learning module to promote complementary representation learning between the two branches via mutual information maximization. Extensive experiments on the publicly available dataset TOXICN MM, comprising 12,000 samples, demonstrate the effectiveness of the proposed framework, with F1 score improvements of 1.06% in harmful meme detection and 2.77% in harmful type identification over the previous state-of-the-art method. We further evaluate the generalization of the MDP framework on a Chinese multimodal sarcasm detection dataset, where the proposed method also achieves competitive results.
{"title":"Multi-view dynamic perception framework for Chinese harmful meme detection","authors":"Jiapei Hu , Yifan Lyu , Yifan Chen , Kuntao Li , Yun Xue , Jinghua Liang","doi":"10.1016/j.ipm.2025.104602","DOIUrl":"10.1016/j.ipm.2025.104602","url":null,"abstract":"<div><div>Chinese harmful memes convey toxicity on social media through varied semantic complexity and diverse modality combinations. However, existing detection methods typically adopt static architectures with fixed interaction patterns, which lack the flexibility to accurately identify harmful cues embedded in heterogeneous semantic and modal content across different memes, hindering a comprehensive understanding of toxic intent. To address this limitation, we propose the Multi-View Dynamic Perception (MDP) framework, a dynamic interaction paradigm specifically designed for Chinese harmful meme detection. Specifically, we develop five types of semantic perception nodes to synchronously extract features from diverse views. These nodes are densely stacked to form two perception branches, respectively guided by textual and visual features, to effectively capture modality-specific cues. To enhance adaptability, each node is equipped with an independent soft router that dynamically regulates information flow and enables flexible interaction patterns tailored to different memes. Furthermore, we introduce a Hierarchical Mutual Learning module to promote complementary representation learning between the two branches via mutual information maximization. Extensive experiments on the publicly available dataset TOXICN MM, comprising 12,000 samples, demonstrate the effectiveness of the proposed framework, with F1 score improvements of 1.06% in harmful meme detection and 2.77% in harmful type identification over the previous state-of-the-art method. We further evaluate the generalization of the MDP framework on a Chinese multimodal sarcasm detection dataset, where the proposed method also achieves competitive results.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104602"},"PeriodicalIF":6.9,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-14DOI: 10.1016/j.ipm.2026.104615
Yingying Gao , Tianle Pu , Qingqing Yang , Zhiwei Yang , Kewei Yang , Changjun Fan
Search operations play a vital role in humanitarian emergencies, where maximizing the probability of finding survivors requires highly efficient solutions. A key challenge lies in the limitations of existing methods, which often struggle with high-dimensional constraints and sparse decision spaces, particularly in large-scale scenarios. To address this, we propose NeuPath, a hybrid learning-based optimization framework that accelerates the discovery of high-quality solutions. NeuPath first formulates the optimal search problem (OSP) as a bipartite graph representation to enhance feature extraction and scalability. It then predicts an initial solution using a graph neural network (GNN) augmented with a two-stage aggregation mechanism, followed by refinement via a block-wise trust-region scheme. Extensive experiments on OSP static scenarios (500 instances) demonstrate that NeuPath achieves significant speedups over exact solvers, with performance gains of 2.48 × (Gurobi) and 2.74 × (SCIP) across varying problem sizes. For large-scale random scenarios (500 instances), the solution quality of this method also significantly exceeds that of the exact solver in a finite time (3600s). Moreover, the framework exhibits strong generalization capabilities by learning meaningful problem structure features. Ablation studies further validate the effectiveness of each module.
{"title":"NeuPath: A hybrid learning-based optimization approach for emergency search path planning","authors":"Yingying Gao , Tianle Pu , Qingqing Yang , Zhiwei Yang , Kewei Yang , Changjun Fan","doi":"10.1016/j.ipm.2026.104615","DOIUrl":"10.1016/j.ipm.2026.104615","url":null,"abstract":"<div><div>Search operations play a vital role in humanitarian emergencies, where maximizing the probability of finding survivors requires highly efficient solutions. A key challenge lies in the limitations of existing methods, which often struggle with high-dimensional constraints and sparse decision spaces, particularly in large-scale scenarios. To address this, we propose NeuPath, a hybrid learning-based optimization framework that accelerates the discovery of high-quality solutions. NeuPath first formulates the optimal search problem (OSP) as a bipartite graph representation to enhance feature extraction and scalability. It then predicts an initial solution using a graph neural network (GNN) augmented with a two-stage aggregation mechanism, followed by refinement via a block-wise trust-region scheme. Extensive experiments on OSP static scenarios (500 instances) demonstrate that NeuPath achieves significant speedups over exact solvers, with performance gains of 2.48 × (Gurobi) and 2.74 × (SCIP) across varying problem sizes. For large-scale random scenarios (500 instances), the solution quality of this method also significantly exceeds that of the exact solver in a finite time (3600s). Moreover, the framework exhibits strong generalization capabilities by learning meaningful problem structure features. Ablation studies further validate the effectiveness of each module.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104615"},"PeriodicalIF":6.9,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-13DOI: 10.1016/j.ipm.2026.104618
Yirun Ruan , Xinghua Qin , Sizheng Liu , Mengmeng Zhang , Jun Tang , Yanming Guo , Tianyuan Yu
Identifying influential spreaders is critical for applications like disease control and information dissemination. Existing methods often face trade-offs among accuracy, resolution, and computational cost. To achieve a more balanced and accurate identification, we propose GRAIN (Gravity-Resistance Adaptive Influential Node identification framework), a novel approach that effectively combines multi-order structural diversity and topological cohesion for influence assessment. Specifically, GRAIN introduces two key innovations: (1) A node-adaptive propagation diversity metric based on k-shell entropy. This metric dynamically balances the contributions of a node's direct (1-hop) and indirect (2-hop) neighbors to its diversity through an adaptive weighting parameter λ(v). (2) Resistance distance Ωij to quantify the topological cohesion between nodes i and j, capturing the "multiple-route distance diminishment" effect observed in networks. We integrate these components within a physics-inspired gravity model: A node's "mass" combines its core position (k-shell) and neighborhood propagation diversity, while "distance" uses Ωij with exponential attenuation for farther neighbors. A node’s total influence is the sum of gravitational forces from its 1-hop and 2-hop neighbors. Evaluations on 20 real-world and 15 synthetic networks using the Susceptible-Infected-Recovered (SIR) model show that GRAIN significantly outperforms a range of benchmarks in the majority of cases, achieving higher kendall’s tau correlation across a wide range of transmission rates and network topologies.
{"title":"GRAIN: Gravity-resistance adaptive framework for identifying influential nodes using multi-order structural diversity","authors":"Yirun Ruan , Xinghua Qin , Sizheng Liu , Mengmeng Zhang , Jun Tang , Yanming Guo , Tianyuan Yu","doi":"10.1016/j.ipm.2026.104618","DOIUrl":"10.1016/j.ipm.2026.104618","url":null,"abstract":"<div><div>Identifying influential spreaders is critical for applications like disease control and information dissemination. Existing methods often face trade-offs among accuracy, resolution, and computational cost. To achieve a more balanced and accurate identification, we propose GRAIN (Gravity-Resistance Adaptive Influential Node identification framework), a novel approach that effectively combines multi-order structural diversity and topological cohesion for influence assessment. Specifically, GRAIN introduces two key innovations: (1) A node-adaptive propagation diversity metric based on k-shell entropy. This metric dynamically balances the contributions of a node's direct (1-hop) and indirect (2-hop) neighbors to its diversity through an adaptive weighting parameter <em>λ</em>(<em>v</em>). (2) Resistance distance Ω<em><sub>ij</sub></em> to quantify the topological cohesion between nodes <em>i</em> and <em>j</em>, capturing the \"multiple-route distance diminishment\" effect observed in networks. We integrate these components within a physics-inspired gravity model: A node's \"mass\" combines its core position (k-shell) and neighborhood propagation diversity, while \"distance\" uses Ω<em><sub>ij</sub></em> with exponential attenuation for farther neighbors. A node’s total influence is the sum of gravitational forces from its 1-hop and 2-hop neighbors. Evaluations on 20 real-world and 15 synthetic networks using the Susceptible-Infected-Recovered (SIR) model show that GRAIN significantly outperforms a range of benchmarks in the majority of cases, achieving higher kendall’s tau correlation across a wide range of transmission rates and network topologies.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104618"},"PeriodicalIF":6.9,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-13DOI: 10.1016/j.ipm.2025.104591
Jing Wang , Duantengchuan Li , Xu Du , Hao Li , Zhuang Hu
Visual questions are an important means to evaluate students’ knowledge. Knowledge-based visual question classification can effectively excavate the knowledge intention of the question, and realize the effective organization and management of online question resources at the knowledge level. The existing methods simply regard it as a multimodal classification task, ignoring the capture of implicit knowledge information and the fine-grained interactions between multimodal and multi-granularity features. To mitigate this, we propose a quaternion hypergraph consistent network (QHCN). This approach can not only extract explicit semantic features and implicit knowledge features from text and images simultaneously, but also considers three key properties among explicit-implicit features: modality complementation, modality independence, and knowledge consistency. Specifically, a visual question is represented as a quaternion vector consisting of two modalities and four-dimensional features. To achieve multimodal complementation, the consistency of vision and language guides the construction of a quaternion hypergraph, and a quaternion convolution operator deeply fuses explicit-implicit features. To capture inter-dependencies between explicit-implicit features, the independence loss and knowledge consistency loss are designed to optimize hypergraph network parameters and enhance the hypergraph structure. Extensive experiments on visual question sets verify that our QHCN achieved an accuracy of 94.82% and an F1 score of 94.76%, outperforming the optimal baseline by +1.46% and +1.53%, respectively.
{"title":"Knowledge-based visual question classification using quaternion hypergraph consistent network","authors":"Jing Wang , Duantengchuan Li , Xu Du , Hao Li , Zhuang Hu","doi":"10.1016/j.ipm.2025.104591","DOIUrl":"10.1016/j.ipm.2025.104591","url":null,"abstract":"<div><div>Visual questions are an important means to evaluate students’ knowledge. Knowledge-based visual question classification can effectively excavate the knowledge intention of the question, and realize the effective organization and management of online question resources at the knowledge level. The existing methods simply regard it as a multimodal classification task, ignoring the capture of implicit knowledge information and the fine-grained interactions between multimodal and multi-granularity features. To mitigate this, we propose a quaternion hypergraph consistent network (QHCN). This approach can not only extract explicit semantic features and implicit knowledge features from text and images simultaneously, but also considers three key properties among explicit-implicit features: modality complementation, modality independence, and knowledge consistency. Specifically, a visual question is represented as a quaternion vector consisting of two modalities and four-dimensional features. To achieve multimodal complementation, the consistency of vision and language guides the construction of a quaternion hypergraph, and a quaternion convolution operator deeply fuses explicit-implicit features. To capture inter-dependencies between explicit-implicit features, the independence loss and knowledge consistency loss are designed to optimize hypergraph network parameters and enhance the hypergraph structure. Extensive experiments on visual question sets verify that our QHCN achieved an accuracy of 94.82% and an F1 score of 94.76%, outperforming the optimal baseline by +1.46% and +1.53%, respectively.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104591"},"PeriodicalIF":6.9,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-13DOI: 10.1016/j.ipm.2026.104614
Chuanyang Gong , Zhihua Wei , Wenhao Tao , Duoqian Miao
Large language models (LLMs) often exhibit factual errors when handling complex knowledge reasoning. To address this issue, we propose MGPrompt, a novel knowledge graph question answering (KGQA) framework that enhances LLM performance by integrating multi-granularity knowledge with structured reasoning path-augmented prompting. MGPrompt consists of three core modules-knowledge refinement, semantic association, and information fusion-to dynamically filter and integrate entity-level, relation-level, and subgraph-level knowledge retrieved from the knowledge graph. Subsequently, we inject these refined semantic representations as prefix vectors into the LLM and fine-tune the model using Low-Rank Adaptation (LoRA) to guide it in generating accurate reasoning paths. We conducted extensive experiments on two benchmark datasets, WebQSP and CWQ. The results show that MGPrompt achieves highly competitive performance compared to 30 baseline methods. Experimental results show that MGPrompt achieves highly competitive performance on both WebQSP and CWQ; in particular, it improves the Hits@1 score on WebQSP by 1.1% over the strongest baseline (85.7%), thereby clearly demonstrating the effectiveness of the proposed framework for complex KGQA tasks.
{"title":"Enhancing large language models for knowledge graph question answering via multi-granularity knowledge injection and structured reasoning path-augmented prompting","authors":"Chuanyang Gong , Zhihua Wei , Wenhao Tao , Duoqian Miao","doi":"10.1016/j.ipm.2026.104614","DOIUrl":"10.1016/j.ipm.2026.104614","url":null,"abstract":"<div><div>Large language models (LLMs) often exhibit factual errors when handling complex knowledge reasoning. To address this issue, we propose MGPrompt, a novel knowledge graph question answering (KGQA) framework that enhances LLM performance by integrating multi-granularity knowledge with structured reasoning path-augmented prompting. MGPrompt consists of three core modules-knowledge refinement, semantic association, and information fusion-to dynamically filter and integrate entity-level, relation-level, and subgraph-level knowledge retrieved from the knowledge graph. Subsequently, we inject these refined semantic representations as prefix vectors into the LLM and fine-tune the model using Low-Rank Adaptation (LoRA) to guide it in generating accurate reasoning paths. We conducted extensive experiments on two benchmark datasets, WebQSP and CWQ. The results show that MGPrompt achieves highly competitive performance compared to 30 baseline methods. Experimental results show that MGPrompt achieves highly competitive performance on both WebQSP and CWQ; in particular, it improves the Hits@1 score on WebQSP by 1.1% over the strongest baseline (85.7%), thereby clearly demonstrating the effectiveness of the proposed framework for complex KGQA tasks.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104614"},"PeriodicalIF":6.9,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-13DOI: 10.1016/j.ipm.2026.104616
Dandan Wang , Stephanie Jean Tsang , Yadong Zhou
Large language models (LLMs) are increasingly used for automated fact-checking, yet their performance often varies across languages, raising global fairness concerns. This study evaluated cross-language inequality in LLM-based fact-checking using 4,500 claims spanning nine languages across six language families. Besides building a systematic performance-evaluation pipeline covering instruction following, authenticity classification, evidence generation, and checking-worthiness scoring, we quantified inequality using standard deviation, coefficient of variation, Gini coefficient, and Theil index. Results showed substantial cross-language disparities, with higher performance on claims from rich-resource languages. To mitigate inequality, we tested two interventions, role-restricted prompt engineering and model fine-tuning. Both approaches reduced disparities, with fine-tuning achieving the largest and most consistent improvement across languages, particularly in checking-worthiness scoring. This study provides a reproducible framework for quantifying multilingual performance and fairness in LLM-based fact-checking and offers practical guidance for developing more equitable verification systems across diverse linguistic contexts.
{"title":"Performance unfairness of large language models in cross-language fact-checking","authors":"Dandan Wang , Stephanie Jean Tsang , Yadong Zhou","doi":"10.1016/j.ipm.2026.104616","DOIUrl":"10.1016/j.ipm.2026.104616","url":null,"abstract":"<div><div>Large language models (LLMs) are increasingly used for automated fact-checking, yet their performance often varies across languages, raising global fairness concerns. This study evaluated cross-language inequality in LLM-based fact-checking using 4,500 claims spanning nine languages across six language families. Besides building a systematic performance-evaluation pipeline covering instruction following, authenticity classification, evidence generation, and checking-worthiness scoring, we quantified inequality using standard deviation, coefficient of variation, Gini coefficient, and Theil index. Results showed substantial cross-language disparities, with higher performance on claims from rich-resource languages. To mitigate inequality, we tested two interventions, role-restricted prompt engineering and model fine-tuning. Both approaches reduced disparities, with fine-tuning achieving the largest and most consistent improvement across languages, particularly in checking-worthiness scoring. This study provides a reproducible framework for quantifying multilingual performance and fairness in LLM-based fact-checking and offers practical guidance for developing more equitable verification systems across diverse linguistic contexts.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 4","pages":"Article 104616"},"PeriodicalIF":6.9,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号