Information Processing & Management最新文献

{"title":"Multi-View disentanglement-based bidirectional generalized distillation for diagnosis of liver cancers with ultrasound images","authors":"","doi":"10.1016/j.ipm.2024.103855","DOIUrl":"10.1016/j.ipm.2024.103855","url":null,"abstract":"<div><p>B-mode ultrasound (BUS) mainly reflects the tissue structural, morphological, and echo characteristics of liver tumors, and contrast-enhanced ultrasound (CEUS) offers supplementary information on the dynamic blood perfusion pattern to promote diagnostic accuracy. Transfer learning (TL) is capable of improving the performance of BUS-based computer-aided diagnosis (CAD) for liver cancer by transferring information from CEUS. However, most multi-view TL algorithms cannot fully capture the view-common together with the view-unique information of three CEUS phase images in the source domain to further promote knowledge transfer. To this end, a multi-view disentanglement-based bidirectional generalized distillation (MD-BGD) algorithm is proposed to explore and learn more potential knowledge from three typical CEUS phase images for multi-view transfer. MD-BGD consists of the multi-view feature disentanglement module and the bidirectional distillation module. The former explores more potential and transferable privileged information by disentangling three CEUS phase image features in the source domain into view-common and view-unique components. The latter develops a bidirectional generalized distillation algorithm to enhance the multi-view knowledge transfer between the source and the target domains, guided by shared labels. Therefore, the BUS-based CAD model is significantly improved by our proposed MD-BGD. MD-BGD is evaluated on the bi-modal ultrasound imaging dataset. It gains the best results of 90.75±2.20 %, 89.50±3.49 %, and 91.89±3.78 %, on accuracy, sensitivity, and specificity, respectively. These results indicate the effectiveness of MD-BGD in the diagnosis of liver cancer.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141944164","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}

{"title":"SCFL: Spatio-temporal consistency federated learning for next POI recommendation","authors":"","doi":"10.1016/j.ipm.2024.103852","DOIUrl":"10.1016/j.ipm.2024.103852","url":null,"abstract":"<div><p>Existing personalized federated learning frameworks fail to significantly improve the personalization of user preference learning in next Point-Of-Interest (POI) recommendations, causing notable performance deficits. These frameworks do not fully consider crucial factors such as: (1) how to thoroughly explore spatial–temporal relationships within user trajectories to deeply understand personalized behavior patterns, and (2) the neglect of collaborative signals among users with similar spatio-temporal distributions, which results in the loss of valuable shared information. To tackle these challenges, this paper introduces the Spatio-temporal Consistency Federated Learning (SCFL) framework, which capitalizes on the spatio-temporal consistency of trajectories to boost the personalized performance of POI recommendation models in FL. Specifically, we have developed the trajectory optimization module SCA for clients in isolation to extract deeper behavioral patterns from the spatio-temporal distribution of sparse trajectories. Additionally, we present a hierarchical aggregation strategy based on distribution consistency, utilizing intermediate entities called Edges to aggregate similar users, thereby enhancing the model’s learning of shared information. Experimental validation across three real-world datasets (NYC, TKY and Gowalla) and two models (SASRec and SSEPT) with six scalability settings shows that SCFL substantially outperforms eight strong baselines. In six experimental configurations, SCFL achieves a personalized performance improvement of 10.65% over the best baselines. Additional experiments have also validated the superiority of SCFL from various perspectives.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141944165","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}

{"title":"Edge contrastive learning for link prediction","authors":"","doi":"10.1016/j.ipm.2024.103847","DOIUrl":"10.1016/j.ipm.2024.103847","url":null,"abstract":"<div><p>Link prediction is a critical task within the realm of graph machine learning. While recent advancements mainly emphasize node representation learning, the rich information encapsulated within edges, proven advantageous in various graph-related tasks, has been somewhat overlooked. To bridge the gap, this paper explores the potential of incorporating edge representation learning for link prediction and identifies three inherent challenges associated with this approach. We introduce the Edge Contrastive Learning for Link Prediction (ECLiP) framework to tackle these challenges. ECLiP integrates edge information into node representations through edge-level contrastive learning, with a distinctive perspective on treating edges, rather than nodes, as the units of instance discrimination. We first illustrate the implementation of this framework using an established edge representation learning method. However, it incurs significant additional training overhead when the number of edges is huge. To mitigate this issue, we present a computationally efficient variant employing a multi-layer perceptron (MLP) for direct edge representation learning. Conducting rigorous experiments across eight distinct datasets with node counts spanning from 2k to 235k, we demonstrate a noteworthy improvement of over 10% on certain datasets, validating the efficacy of our proposed methodology.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141944167","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}

{"title":"Structure-aware sign language recognition with spatial–temporal scene graph","authors":"","doi":"10.1016/j.ipm.2024.103850","DOIUrl":"10.1016/j.ipm.2024.103850","url":null,"abstract":"<div><p>Continuous sign language recognition (CSLR) is essential for the social participation of deaf individuals. The structural information of sign language motion units plays a crucial role in semantic representation. However, most existing CSLR methods treat motion units as a whole appearance in the video sequence, neglecting the exploitation and explanation of structural information in the models. This paper proposes a Structure-Aware Graph Convolutional Neural Network (SA-GNN) model for CSLR. This model constructs a spatial–temporal scene graph, explicitly capturing motion units’ spatial structure and temporal variation. Furthermore, to effectively train the SA-GNN, we propose an adaptive bootstrap strategy that enhances weak supervision using dense pseudo labels. This strategy incorporates a confidence cross-entropy loss to adjust the distribution of pseudo labels adaptively. Extensive experiments validate the effectiveness of our proposed method, achieving competitive results on popular CSLR datasets.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141944166","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}

{"title":"TaReT: Temporal knowledge graph reasoning based on topology-aware dynamic relation graph and temporal fusion","authors":"","doi":"10.1016/j.ipm.2024.103848","DOIUrl":"10.1016/j.ipm.2024.103848","url":null,"abstract":"<div><p>Previous temporal knowledge graph (TKG) reasoning methods often focus exclusively on evolving representations. However, these methods suffer from the inadequacy of capturing the structural nuances of concurrent facts, the intricate relations in topological subgraphs, and the fusion of temporal information across timestamps. To address these challenges, this paper proposes a TKG reasoning method based on <u><strong>T</strong></u>opology-<u><strong>a</strong></u>ware dynamic <u><strong>Re</strong></u>lation graph and <u><strong>T</strong></u>emporal fusion (<strong>TaReT</strong>). First, TaReT proposes an innovative attention-based relational graph model, serving as a structural information encoder that captures the intricate structure of concurrent facts. Then, TaReT designs a topology-aware relational correlation unit to discern topological relation graphs of various patterns via an edge-level correlation network, yielding relation representations. Furthermore, TaReT introduces an inter-timestamp temporal information encoder which applies a dual-gate mechanism to integrate structural and relational information for temporal fusion. Finally, the temporal decoder is applied to output entity and relation predictions. Extensive experiments on four benchmark datasets establish TaReT’s superiority over leading TKG reasoning methods. On the ICEWS14 dataset, the MRR value of TaReT exceeds the reasoning baseline RE-GCN by 14.6%.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141954631","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}

{"title":"A Multifaceted Reasoning Network for Explainable Fake News Detection","authors":"","doi":"10.1016/j.ipm.2024.103822","DOIUrl":"10.1016/j.ipm.2024.103822","url":null,"abstract":"<div><p>Fake news detection involves developing techniques to identify and flag misleading or false information disseminated through media sources. Current efforts often use limited information for categorization, lacking comprehensive data integration and explanation of results. Additionally, the substantial noise generated by multi-source data presents extra challenges to fake news detection. To address these problems, we propose a novel <strong><u>M</u>ultifaceted <u>R</u>easoning Network for <u>E</u>xplainable <u>F</u>ake <u>N</u>ews <u>D</u>etection</strong> (MRE-FND). This model constructs two heterogeneous graphs to learn about social network information and news content knowledge, including news content, social networks, knowledge graphs, and external news data. Utilizing graph information bottleneck theory, it eliminates noise from multifaceted data and extracts key information for fake news detection. An interpretable reasoning module is designed to provide clear explanations for the classification results. Our proposition undergoes extensive evaluation on three popular datasets, Politifact, Gossipcop and Pheme, which consist of 495, 15707 and 2189 news, respectively. Our model achieved state-of-the-art results across all metrics on three datasets. Specifically, our model achieved accuracy rates of 92.9%, 83.4% and 84.7% on the Politifact, Gossipcop and Pheme datasets, respectively, demonstrating improvements of 2.0, 0.8 and 1.1 percentage points over the baseline, thus establishing the superiority of our model. Further analysis indicates that our model can effectively handle redundant information in multi-faceted data, enhancing the performance of fake news detection while also providing multifaceted explanations for the classification results.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141960509","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}

{"title":"Why leave items in the shopping cart? The impact of consumer filtering behavior","authors":"","doi":"10.1016/j.ipm.2024.103854","DOIUrl":"10.1016/j.ipm.2024.103854","url":null,"abstract":"<div><p>Online product information provides crucial cues for consumer shopping behavior; however, the impact of consumer-side information manipulation on non-purchase behavior (e.g., shopping cart abandonment) remains unclear. Filtering, a common manipulation strategy, was initially considered synonymous with searching, both of which contribute to consumer purchase behavior. However, recent research suggests significant differences, particularly in terms of cost and product matching. This study explores how such differences affect information manipulation and subsequently shape shopping cart abandonment, drawing on information foraging theory. Based on the premise that a forager's interaction with the environment is mediated by cognition, we find that consumer filtering behavior influences perceptions of serendipity (i.e., discovering unexpected items) and similarity (i.e., encountering similar items), thereby influencing shopping cart abandonment. Mediation analyses reveal that perceived serendipity and similarity are equally potent mediators. Marginal effects analyses demonstrate that a one standard deviation increase in consumer perceptions of serendipity (similarity) in filtering results increases the likelihood of shopping cart abandonment by 32.2% (22.1%). Theoretical contributions and practical insights for information behavior researchers and digital marketers are also provided.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141960508","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}

{"title":"Unveiling the loss of exceptional women in science","authors":"","doi":"10.1016/j.ipm.2024.103829","DOIUrl":"10.1016/j.ipm.2024.103829","url":null,"abstract":"<div><p>The slower career advancement of women hampers diversity and jeopardizes female leadership, resulting in significant setbacks for the academic community. Our study constructed a more comprehensive dataset than previous studies, encompassing 24,292,991 complete careers of scholars across 19 scientific disciplines from 1950 to 2015. By employing a combination of survival model and relative dropout rate calculations, we identified unified career stages across fields: rapid decrease (RD), stable decrease (SD), and unstable increase (UI). Through gender comparison under meticulous matching within each career stage, our analysis revealed that women in the RD stage, characterized by higher dropout rates, demonstrated a significantly higher or comparable impact than men in most fields. Conversely, persistent women exhibited a comparable impact to men. These findings highlight a more nuanced gender-based phenomenon, extending beyond the commonly observed lower proportion of female scholars or higher female dropout rates. In contrast to the static analyses employed in previous studies on dropout rates, our research introduced intergenerational relationships between dropout rates and scholars' scientific performance. The results demonstrate that, over generations, a minimum of four publications within their ten years become necessary to decrease dropout rates, accompanied by a gradual reduction in gender differences. In fact, early-career female dropouts are now approaching or even surpassing the impact of their male counterparts in most fields. Notably, the significance of research quality is particularly pronounced for junior scholars in the soft sciences compared to those in the hard sciences. We believe the outcomes of this research offer a fresh perspective that deepens our understanding of the challenges faced by female scholars in the scientific community.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141731798","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}

{"title":"Towards long-term depolarized interactive recommendations","authors":"","doi":"10.1016/j.ipm.2024.103833","DOIUrl":"10.1016/j.ipm.2024.103833","url":null,"abstract":"<div><p>Personalization is a prominent process in today’s recommender systems (RS) that enhances user satisfaction and platform profitability. However, recent studies suggest that over-personalization may lead to polarized user preferences, which can result in filter bubbles and echo-chamber effects. These effects have usually been mitigated by focusing on short-term recommendation goals using immediate polarization solutions in static RS settings. In this work, we explore the problem of long-term user polarization resulting from over-personalized multi-step interactive recommendations. We propose a framework to measure and limit the polarization of user preferences, based on item categories consumed over continuous <span><math><mrow><mi>T</mi><mo>−</mo></mrow></math></span>step recommendations. In this framework, we developed three recommendation approaches based on Deep Q-Networks (DQN), each one incorporating distinct polarization constraining and training techniques. First, we proposed I-CDQN, an instantaneously constrained DQN algorithm in which user polarization is forced to remain below a certain threshold at each recommendation step. Second, we proposed RP-DQN, a DQN-based method that incorporates polarization penalization terms into the reward and DQN loss function. Third, we introduced RC-DQN with a double DQN architecture, which constrains user polarization at the category-level using the first DQN, then trains the second unconstrained DQN using items from restricted category-related action spaces. The proposed methods differ in the way they apply polarization constraints, which can significantly impact their performance and suitability for specific application use cases. We conducted extensive experiments on real world datasets using cold- and warm-start scenarios for <span><math><mrow><mi>T</mi><mo>−</mo></mrow></math></span>step interactive recommendations. Interestingly, RC-DQN outperforms both I-CDQN and RP-DQN, demonstrating the best balance between user polarization and personalization, and achieving significant improvement in personalization results when compared to the best performing baseline methods across all experiments, e.g., about 3.6% for <span><math><mrow><mi>T</mi><mo>=</mo><mn>30</mn></mrow></math></span> steps.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141729155","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}

{"title":"Den-ML: Multi-source cross-lingual transfer via denoising mutual learning","authors":"","doi":"10.1016/j.ipm.2024.103834","DOIUrl":"10.1016/j.ipm.2024.103834","url":null,"abstract":"<div><p>Multi-source cross-lingual transfer aims to acquire task knowledge from multiple labelled source languages and transfer it to an unlabelled target language, enabling effective performance in this target language. The existing methods mainly focus on weighting predictions of language-specific classifiers trained in source languages to derive final results for target samples. However, we argue that, due to the language gap, language-specific classifiers inevitably generate many noisy predictions for target samples. Furthermore, these methods disregard the mutual guidance and utilization of knowledge among multiple source languages. To address these issues, we propose a novel model, Den-ML, which improves the model’s performance in multi-source scenarios through two perspectives: reducing prediction noise of language-specific classifiers and prompting mutual learning among these classifiers. Firstly, Den-ML devises a discrepancy-guided denoising learning method to learn discriminative representations for the target language, thus mitigating the noise prediction of classifiers. Secondly, Den-ML develops a pseudo-label-supervised mutual learning method, which relies on forcing probability distribution interactions among multiple language-specific classifiers for knowledge transfer, thus achieving mutual learning among classifiers. We conduct experiments on three different tasks, named entity recognition, paraphrase identification and natural language inference, with two different multi-source combination settings (same- and different-family settings) covering 39 languages. Our approach outperforms the benchmark and the SOTA model in most metrics for all three tasks in different settings. In addition, we perform ablation, visualization and analysis experiments on three different tasks, and the experimental results validate the effectiveness of our approach.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141636883","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}