Information Processing & Management最新文献

{"title":"Few-shot multi-hop reasoning via reinforcement learning and path search strategy over temporal knowledge graphs","authors":"Luyi Bai,&nbsp;Han Zhang,&nbsp;Xuanxuan An,&nbsp;Lin Zhu","doi":"10.1016/j.ipm.2024.104001","DOIUrl":"10.1016/j.ipm.2024.104001","url":null,"abstract":"<div><div>Multi-hop reasoning on knowledge graphs is an important way to complete the knowledge graph. However, existing multi-hop reasoning methods often perform poorly in few-shot scenarios and primarily focus on static knowledge graphs, neglecting to model the dynamic changes of events over time in Temporal Knowledge Graphs (TKGs). Therefore, in this paper, we consider the few-shot multi-hop reasoning task on TKGs and propose a few-shot multi-hop reasoning model for TKGs (TFSM), which uses a reinforcement learning framework to improve model interpretability and introduces the one-hop neighbors of the task entity to consider the impact of previous events on the representation of current task entity. In order to reduce the cost of searching complex nodes, our model adopts a strategy based on path search and prunes the search space by considering the correlation between existing paths and the current state. Compared to the baseline method, our model achieved 5-shot Few-shot Temporal Knowledge Graph (FTKG) performance improvements of 1.0% ∼ 18.9% on ICEWS18-few, 0.6% ∼ 22.9% on ICEWS14-few, and 0.7% ∼ 10.5% on GDELT-few. Extensive experiments show that TFSM outperforms existing models on most metrics on the commonly used benchmark datasets ICEWS18-few, ICEWS14-few, and GDELT-few. Furthermore, ablation experiments demonstrated the effectiveness of each part of our model. In addition, we demonstrate the interpretability of the model by performing path analysis with a path search-based strategy.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 3","pages":"Article 104001"},"PeriodicalIF":7.4,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142756610","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":"Basis is also explanation: Interpretable Legal Judgment Reasoning prompted by multi-source knowledge","authors":"Shangyuan Li ,&nbsp;Shiman Zhao ,&nbsp;Zhuoran Zhang ,&nbsp;Zihao Fang ,&nbsp;Wei Chen ,&nbsp;Tengjiao Wang","doi":"10.1016/j.ipm.2024.103996","DOIUrl":"10.1016/j.ipm.2024.103996","url":null,"abstract":"<div><div>The task of Legal Judgment Prediction (LJP) aims to forecast case outcomes by analyzing fact descriptions, playing a pivotal role in enhancing judicial system efficiency and fairness. Existing LJP methods primarily focus on improving representations of fact descriptions to enhance judgment performance. However, these methods typically depend on the superficial case information and neglect the underlying legal basis, resulting in a lack of in-depth reasoning and interpretability in the judgment process of long-tail or confusing cases. Recognizing that the basis for judgments in real-world legal contexts encompasses both factual logic and related legal knowledge, we introduce the interpretable legal judgment reasoning framework with multi-source knowledge prompted. The essence of this framework is to transform the implicit factual logic of cases and external legal knowledge into explicit basis for judgment, aiming to enhance not only the accuracy of judgment predictions but also the interpretability of the reasoning process. Specifically, we design a chain prompt reasoning module that guides a large language model to elucidate factual logic basis through incremental reasoning, aligning the model prior knowledge with task-oriented knowledge in the process. To match the above fact-based information with legal knowledge basis, we propose a contrastive knowledge fusing module to inject external statutes knowledge into the fact description embedding. It pushes away the distance of similar knowledge in the semantic space during the encoding of external knowledge base without manual annotation, thus improving the judgment prediction performance of long-tail and confusing cases. Experimental results on two real datasets indicate that our framework significantly outperforms existing LJP baseline methods in accuracy and interpretability, achieving new state-of-the-art performance. In addition, tests on specially constructed long-tail and confusing case datasets demonstrate that the proposed framework possesses improved generalization abilities for predicting these complex cases.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 3","pages":"Article 103996"},"PeriodicalIF":7.4,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744584","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":"Adaptive CLIP for open-domain 3D model retrieval","authors":"Dan Song ,&nbsp;Zekai Qiang ,&nbsp;Chumeng Zhang ,&nbsp;Lanjun Wang ,&nbsp;Qiong Liu ,&nbsp;You Yang ,&nbsp;An-An Liu","doi":"10.1016/j.ipm.2024.103989","DOIUrl":"10.1016/j.ipm.2024.103989","url":null,"abstract":"<div><div>In order to effectively enhance the practicality of 3D model retrieval, we adopt a single real image as the query sample for retrieving 3D models. However, the significant differences between 2D images and 3D models in terms of lighting conditions, textures and backgrounds, posing a great challenge for accurate retrieval. Existing work on 3D model retrieval mainly focuses on closed-domain research, while the open-domain condition where the category relationship between the query image and the 3D model is unknown is more in line with the needs of real scenarios. CLIP shows significant promise in comprehending open-world visual concepts, facilitating effective zero-shot image recognition. Based on this multimodal pre-training large language model, we introduce Adaptive Open-domain Semantic Nearest-neighbor Contrast (AOSNC), a method for learning and aligning multi-modal text, image, and 3D model. In order to solve the issue of inconsistent cross-domain categories and difficult sample correlation in open-domain, we construct a cross-modal bridge using CLIP. This model utilizes textual features to bridge the gap between 2D images and 3D model views. Additionally, we design an adaptive network layer to address the limitations of the pre-training model for 3D model views and enhance cross-modal alignment. We propose a mutual nearest-neighbor semantic alignment loss to address the challenge of aligning features from disparate modalities (text, images, and 3D models). This loss function enhances cross-modal learning by effectively associating and distinguishing features, improving retrieval accuracy. We conducted comprehensive experiments using the image-based 3D model retrieval dataset MI3DOR and the cross-domain 3D model retrieval dataset NTU-PSB to validate the superiority of the proposed method. Our results show significant improvements in several evaluation metrics, underscoring the efficacy of our method in augmenting cross-modal feature alignment and retrieval performance.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 103989"},"PeriodicalIF":7.4,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747458","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":"DCIB: Dual contrastive information bottleneck for knowledge-aware recommendation","authors":"Qiang Guo ,&nbsp;Jialong Hai ,&nbsp;Zhongchuan Sun ,&nbsp;Bin Wu ,&nbsp;Yangdong Ye","doi":"10.1016/j.ipm.2024.103980","DOIUrl":"10.1016/j.ipm.2024.103980","url":null,"abstract":"<div><div>Knowledge-aware recommendations effectively enhance model performance by integrating rich external information from the knowledge graphs. Graph contrastive learning methods have recently demonstrated superior results in such recommendations. However, they still face two limitations: (1) the disruption of intrinsic semantic structures caused by stochastic or predefined augmentations for constructing contrastive views, and (2) the neglect of the extrinsic semantic gap arising from the different semantic information in the user-item bipartite graph and the knowledge graph during their incorporation. To address these issues, we propose a novel Dual Contrastive Information Bottleneck (DCIB) method for the knowledge-aware recommendation, which can well preserve the intrinsic semantic structures and bridge the semantic gap to obtain complementary conducive information for learning enhanced representations. Specifically, DCIB implements contrastive learning with the information bottleneck principle (CIB) upon a collaborative view and a knowledge view. View-specific CIB is formalized to suppress the noise and distill high-quality information within each view using a devised learnable denoising module. Cross-view CIB is developed to bridge the semantic gap and fully leverage the different semantics of both views, thereby obtaining complementary information to enrich the representations. Extensive experimental results on the Last.FM, Book-Crossing, and MovieLens-1M show that DCIB outperforms existing state-of-the-art methods. Specifically, in terms of the NDCG@10 metric, DCIB obtains performance improvements of 5.78%, 7.67%, and 5.67% over the second-best methods across the three benchmarks, respectively.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 103980"},"PeriodicalIF":7.4,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747457","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":"Advancing rule learning in knowledge graphs with structure-aware graph transformer","authors":"Kang Xu,&nbsp;Miqi Chen,&nbsp;Yifan Feng,&nbsp;Zhenjiang Dong","doi":"10.1016/j.ipm.2024.103976","DOIUrl":"10.1016/j.ipm.2024.103976","url":null,"abstract":"<div><div>In knowledge graphs (KGs), logic rules offer interpretable explanations for predictions and are essential for reasoning on downstream tasks, such as question answering. However, a key challenge remains unresolved: how to effectively encode and utilize the structural features around the head entity to generate the most applicable rules. This paper proposes a structure-aware graph transformer for rule learning, namely Structure-Aware Rule Learning (SARL), which leverages both local and global structural information of the subgraph around the head entity to generate the most suitable rule path. SARL employs a generalized attention mechanism combined with replaceable feature extractors to aggregate local structural information of entities. It then incorporates global structural and relational information to further model the subgraph structure. Finally, a rule decoder utilizes the comprehensive subgraph representation to generate the most appropriate rules. Comprehensive experiments on four real-world knowledge graph datasets reveal that SARL significantly enhances performance and surpasses existing methods in the link prediction task on large-scale KGs, with Hits@1 improvements of 6.5% on UMLS and 4.5% on FB15K-237.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 103976"},"PeriodicalIF":7.4,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747456","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":"Extracting key insights from earnings call transcript via information-theoretic contrastive learning","authors":"Yanlong Huang ,&nbsp;Wenxin Tai ,&nbsp;Fan Zhou ,&nbsp;Qiang Gao ,&nbsp;Ting Zhong ,&nbsp;Kunpeng Zhang","doi":"10.1016/j.ipm.2024.103998","DOIUrl":"10.1016/j.ipm.2024.103998","url":null,"abstract":"<div><div>Earnings conference calls provide critical insights into a company’s financial health, future outlook, and strategic direction. Traditionally, analysts manually analyze these lengthy transcripts to extract key information, a process that is both time-consuming and prone to bias and error. To address this, text mining tools, particularly extractive summarization, are increasingly being used to automatically extract key insights, aiming to standardize the analysis process and improve efficiency. Extractive summarization automates the selection of the most informative sentences, offering a promising solution for transcript analysis. However, existing extractive summarization techniques face several challenges, such as the lack of labeled training data, difficulties in incorporating domain-specific knowledge, and inefficiencies in handling large-scale datasets. In this work, we introduce ECT-SKIE, an information-theoretic, self-supervised approach for extracting key insights from earnings call transcripts. We leverage variational information bottleneck theory to extract insights in parallel, significantly accelerating the process. In addition, we propose a structure-aware contrastive learning strategy that enables model training without the need for labeled data. We further develop a novel container-based key sentence extractor to alleviate sentence redundancy. Using a large-scale dataset of U.S. market earnings call transcripts, we evaluate our method against nine representative baselines across three downstream tasks. Experimental results show that ECT-SKIE can consistently extract high-quality key sentences. The code is publicly available at: <span><span>https://github.com/MongoTap/ECT-SKIE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 3","pages":"Article 103998"},"PeriodicalIF":7.4,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744585","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":"Let long-term interests talk: An disentangled learning model for recommendation based on short-term interests generation","authors":"Sirui Duan,&nbsp;Mengya Ouyang,&nbsp;Rong Wang,&nbsp;Qian Li,&nbsp;Yunpeng Xiao","doi":"10.1016/j.ipm.2024.103997","DOIUrl":"10.1016/j.ipm.2024.103997","url":null,"abstract":"<div><div>In e-commerce recommendation systems, users’ long-term and short-term interests jointly influence product selection. However, the behavioral conformity phenomenon tends to be more prominent in short-term sequences, and the entanglement of true preference and popularity conformity data confuses the user’s real interest needs. To address this issue, we propose a sequential recommendation model called DFRec to disentangle short-term interests from popularity bias. By leveraging long-term interest trends, the model promotes the separation of short-term interests from popularity-driven deviations, thereby reducing the impact of popularity interference in short-term sequences. Firstly, we propose a Disentangled Frequency Attention Network(DFAN) to address the entanglement between real sequence features and conformity data in users’ short-term behavioral sequences. The approach clarify the non-entangled representation of the user’s short-term interest and conformity on the basis of long-term interest trends. Secondly, in order to capture the real long-term interest characteristics of users, this paper suggests using a Learnable Filter(LF) to filter the noise frequencies in long-term sequence. The method decouples the horizontal and vertical directions of the sequence and filters out the noise in both directions. Finally, consider the importance of the two interests characteristics is dynamic, we propose a joint learning framework with dual embeddings to balance and fusion these two features of users’ interests. Experimental results on three public datasets demonstrate that our model effectively captures dynamic user interests and outperforms six baseline models.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 103997"},"PeriodicalIF":7.4,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747460","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":"Trust driven On-Demand scheme for client deployment in Federated Learning","authors":"Mario Chahoud ,&nbsp;Azzam Mourad ,&nbsp;Hadi Otrok ,&nbsp;Jamal Bentahar ,&nbsp;Mohsen Guizani","doi":"10.1016/j.ipm.2024.103991","DOIUrl":"10.1016/j.ipm.2024.103991","url":null,"abstract":"<div><div>Containerization technology plays a crucial role in Federated Learning (FL) setups, expanding the pool of potential clients and ensuring the availability of specific subsets for each learning iteration. However, doubts arise about the trustworthiness of devices deployed as clients in FL scenarios, especially when container deployment processes are involved. Addressing these challenges is important, particularly in managing potentially malicious clients capable of disrupting the learning process or compromising the entire model. In our research, we are motivated to integrate a trust element into the client selection and model deployment processes within our system architecture. This is a feature lacking in the initial client selection and deployment mechanism of the On-Demand architecture. We introduce a trust mechanism, named “Trusted-On-Demand-FL”, which establishes a relationship of trust between the server and the pool of eligible clients. Utilizing Docker in our deployment strategy enables us to monitor and validate participant actions effectively, ensuring strict adherence to agreed-upon protocols while strengthening defenses against unauthorized data access or tampering. Our simulations rely on continuous user behavior datasets, deploying an optimization model powered by a genetic algorithm to efficiently select clients for participation. By assigning trust values to individual clients and dynamically adjusting these values, combined with penalizing malicious clients through decreased trust scores, our proposed framework identifies and isolates harmful clients. This approach not only reduces disruptions to regular rounds but also minimizes instances of round dismissal, Consequently enhancing both system stability and security.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 103991"},"PeriodicalIF":7.4,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747459","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":"Integration of public libraries and cultural tourism in China: An analysis of library attractiveness components based on tourist review mining","authors":"Tingting Jiang ,&nbsp;Yanrun Xu ,&nbsp;Yao Li ,&nbsp;Yikun Xia","doi":"10.1016/j.ipm.2024.104000","DOIUrl":"10.1016/j.ipm.2024.104000","url":null,"abstract":"<div><div>The integration of public libraries and tourism represents an emerging trend in China, aiming to foster sustainable development of libraries. However, there still lacks an accurate understanding of the attractiveness and performance of library tourism. Targeting all the national first-tier public libraries in China, this study collected a total of 70,301 online reviews provided by library tourists from popular online travel platforms. Text mining on 41,255 valid reviews, based on topic modeling and sentiment analysis, revealed seven primary components of library tourism attractiveness. Chinese public libraries demonstrated a satisfactory overall performance as tourist attractions (<span><math><mover><mi>a</mi><mo>¯</mo></mover></math></span>= 0.732609), though variations were observed across different components: performance was excellent (<span><math><mrow><msub><mover><mi>a</mi><mo>¯</mo></mover><mi>i</mi></msub><mspace></mspace></mrow></math></span>&gt; 0.8) in <em>environment &amp; atmosphere, architectural &amp; interior design</em>, and <em>location &amp; transportation</em>, adequate (0.6 &lt; <span><math><mrow><msub><mover><mi>a</mi><mo>¯</mo></mover><mi>i</mi></msub><mspace></mspace></mrow></math></span>&lt;0.8) in <em>online popularity, library collections</em>, and <em>cultural events</em>, and just acceptable (<span><math><mrow><msub><mover><mi>a</mi><mo>¯</mo></mover><mi>i</mi></msub><mspace></mspace></mrow></math></span>&gt; 0.5) in <em>personnel &amp; services</em>. A thematic analysis on 883 negative opinions extracted from the reviews further identified 22 major challenges negatively impacting the performance of each component. Additionally, an asymmetric impact-performance analysis recognized <em>architectural &amp; interior design</em> as the basic component and <em>location &amp; transportation</em> as the linear component, suggesting that visually aesthetic and conveniently located public libraries hold the highest potential for tourism. This study establishes a mixed-methods analytical framework and provides empirical evidence about the success of library tourism in China. In addition, it offers valuable insights for the global development of this burgeoning tourism trend.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 104000"},"PeriodicalIF":7.4,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721385","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":"Bias-guided margin loss for robust Visual Question Answering","authors":"Yanhan Sun ,&nbsp;Jiangtao Qi ,&nbsp;Zhenfang Zhu ,&nbsp;Kefeng Li ,&nbsp;Liang Zhao ,&nbsp;Lei Lv","doi":"10.1016/j.ipm.2024.103988","DOIUrl":"10.1016/j.ipm.2024.103988","url":null,"abstract":"<div><div>Visual Question Answering (VQA) suffers from language prior issue, where models tend to rely on dataset biases to answer the questions while ignoring the image information. Existing studies have been devoted to mitigating language bias by using extra question-only models or balancing the dataset. However, these works fail to comprehensively identify the bias, despite the fact that some methods utilizing margin loss to separate the biased answer embeddings. In this paper, we propose a bias-guided debiasing architecture with margin loss named as BGML, which utilizes a bias model to guide the margin loss for explicitly locating biases of different question types in the answer space. This distinction of bias prompts the model to avoid the adverse effects of language priors. Additionally, we encourage the bias model to comprehensively learn biases by integrating the adversarial training, knowledge distillation, and contrastive learning. The experimental results show that BGML achieved the state-of-the-art results with 62.28% on VQA-CP v2, while retaining competitive results with 60.84% on VQA v2.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 2","pages":"Article 103988"},"PeriodicalIF":7.4,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721384","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}