
Web and Big Data
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 4-volume set LNCS 14331, 14332, 14333, and 14334 constitutes the refereed proceedings of the 7th International Joint Conference, APWeb-WAIM 2023, which took place in Wuhan, China, in October 2023.
The total of 138 papers included in the proceedings were carefully reviewed and selected from 434 submissions. They focus on innovative ideas, original research findings, case study results, and experienced insights in the areas of the World Wide Web and big data, covering Web technologies, database systems, information management, software engineering, knowledge graph, recommend system and big data.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents - Part II
- Computing Maximal Likelihood Subset Repair for Inconsistent Data
- 1 Introduction
- 2 Problem Statement
- 2.1 Function Dependency
- 2.2 Subset Repair
- 2.3 Problem Definition
- 3 Statistical Learning and Inference
- 3.1 Probability Modeling
- 3.2 Scalable Inference
- 4 Subset Repair with Maximum Likelihood
- 4.1 From Maximum Likelihood to Minimum Cost
- 4.2 Approximate Algorithm
- 5 Experiments
- 5.1 Experimental Steup
- 5.2 Performance Evaluation
- 5.3 Runtime Evaluation
- 6 Related Work
- 7 Conclusions
- References
- Design of Data Management System for Sustainable Development of Urban Agglomerations' Ecological Environment Based on Data Lake Architecture
- 1 Introduction
- 2 Related Work
- 3 System Architecture Design
- 4 System Implementation
- 4.1 Metadata Design
- 4.2 Data Management
- 4.3 Data Product Production
- 4.4 System Presentation
- 5 Future Work
- 6 Conclusion
- References
- P-QALSH+: Exploiting Multiple Cores to Parallelize Query-Aware Locality-Sensitive Hashing on Big Data
- 1 Introduction
- 1.1 Our Contribution
- 2 Preliminaries
- 2.1 c-ANN Search Problem
- 2.2 Framework of QALSH
- 3 Parallel Table Design
- 3.1 Inter-Table Parallel Design
- 3.2 Intra-table Parallel Design
- 4 Parallel Query Design
- 4.1 Overview of Parallel Query
- 4.2 Parallel Collision Counting Technology
- 4.3 Search Radius Estimation Strategy
- 5 Experiments
- 5.1 Experiment Setup
- 5.2 Results and Analysis of the Index Phase
- 5.3 Results and Analysis of the Query Phase
- 6 Conclusion
- References
- Face Super-Resolution via Progressive-Scale Boosting Network
- 1 Introduction
- 2 Face Super-Resolution
- 3 Our Methods
- 3.1 Network Architectures
- 3.2 Attention Feature Fusion Block
- 4 Experimental Results and Analysis
- 4.1 Datasets and Implementation Details
- 4.2 Compared with State-of-the-Arts
- 4.3 Ablation Study
- 4.4 Effectiveness of the Proposed Method
- 5 Conclusion
- References
- An Investigation of the Effectiveness of Template Protection Methods on Protecting Privacy During Iris Spoof Detection
- 1 Introduction
- 2 Related Work
- 2.1 Iris Spoof Detection
- 2.2 Iris Template Protection Methods
- 3 Methodology
- 3.1 TPISD
- 3.2 Image Pre-processing
- 3.3 Iris Template Protection Methods
- 3.4 Spoof Detection Model
- 3.5 Security Analysis
- 4 Experiment
- 4.1 Dataset and Evaluation Metrics
- 4.2 Experimental Setup
- 4.3 Transformation Parameter Experiment
- 5 Conclusion
- References
- Stock Volatility Prediction Based on Transformer Model Using Mixed-Frequency Data
- 1 Introduction
- 2 Related Works
- 3 Methodology
- 3.1 Basic Theory of Volatility
- 3.2 Definition of Indicators
- 3.3 Prediction Method
- 4 Empirical Analysis
- 4.1 Experiment Setup
- 4.2 Experiment Result
- 5 Conclusion
- References
- A Hierarchy-Based Analysis Approach for Blended Learning: A Case Study with Chinese Students
- 1 Introduction
- 2 Related Work
- 2.1 Elements Regarding Evaluating Blended Learning
- 2.2 Evaluation Frameworks
- 3 Method
- 3.1 Gradient Boosting Regression
- 3.2 Gini Importance and Permutation Importance
- 3.3 Analytic Hierarchy Process
- 4 Experiments and Results
- 4.1 Dataset
- 4.2 Experimental Setup
- 4.3 Results and Analysis
- 5 Conclusion
- References
- A Multi-teacher Knowledge Distillation Framework for Distantly Supervised Relation Extraction with Flexible Temperature
- 1 Introduction
- 2 Related Work
- 2.1 Distantly Supervised Relation Extraction
- 2.2 Knowledge Distillation
- 3 Method
- 3.1 Task Definition
- 3.2 Model Overview
- 3.3 Flexible Temperature Regulation
- 3.4 Multi-view Knowledge Distillation
- 3.5 Total Loss of Student Model
- 4 Experiments
- 4.1 Datasets
- 4.2 Evaluation Metrics and Settings
- 4.3 Baselines
- 4.4 Main Results
- 4.5 Ablation Study
- 5 Conclusion
- References
- PAEE: Parameter-Efficient and Data-Effective Image Captioning Model with Knowledge Prompter and Cross-Modal Representation Aligner
- 1 Introduction
- 2 Related Work
- 2.1 Frozen Parameters Captioning Models
- 2.2 Knowledge Retrieval-Based Prompting
- 2.3 Visual and Language Connection
- 2.4 Prompting Caption Generation
- 3 Method
- 3.1 Architecture
- 3.2 Pre-trained Image Encoder
- 3.3 Pre-trained Language Model
- 3.4 Prompter-Based Caption Generation
- 3.5 Cross-Modal Representation Aligner
- 4 Experiments
- 4.1 Experimental Settings
- 4.2 Performance Comparison
- 4.3 Data Utilization Capabilities
- 4.4 Exploration of Small-Data Learning
- 4.5 Ablation Analysis
- 4.6 Qualitative Analysis
- 5 Conclusion and Future Work
- References
- TSKE: Two-Stream Knowledge Embedding for Cyberspace Security
- 1 Introduction
- 2 Related Work
- 2.1 Knowledge Representation Models
- 2.2 Knowledge Embedding Methods
- 3 Preliminaries
- 3.1 System Model
- 3.2 Problem Definition
- 4 TSKE: A Two-Stream Knowledge Embedding Method Based on the MDATA Model
- 4.1 Static Stream Model
- 4.2 Spatio-Temporal Stream Model
- 4.3 Weighted Fusion
- 4.4 Learning
- 5 Experiment Results
- 5.1 Implementation
- 5.2 Baselines
- 5.3 Attack Link Prediction
- 5.4 Results
- 6 Conclusion and Future Work
- References
- Research on the Impact of Executive Shareholding on New Investment in Enterprises Based on Multivariable Linear Regression Model
- 1 Introduction
- 2 Related Work
- 2.1 Executive Shareholding and Corporate Innovation Investment
- 2.2 Two Types of Agency Costs
- 3 Method
- 3.1 Data Sources and Variable Definition
- 3.2 Research Hypothesis
- 3.3 Research Model Design
- 4 Analysis of Empirical Test Results
- 4.1 Descriptive Statistics
- 4.2 Correlation Analysis
- 4.3 Analysis of Regression Results
- 4.4 Robustness Test
- 5 Conclusion
- References
- MCNet: A Multi-scale and Cascade Network for Semantic Segmentation of Remote Sensing Images
- 1 Introduction
- 2 Methods
- 2.1 Overall
- 2.2 Multi-scale Feature Extraction Module
- 2.3 Channel Activation Module
- 2.4 Cross-Layer Feature Selection Module
- 2.5 Multi-scale Object Guidance Module
- 2.6 Loss Function
- 3 Datasets and Experimental Implementation
- 3.1 Dataset Description
- 3.2 Implementation Details
- 3.3 Evaluation Indicators
- 4 Experimental Results and Analysis
- 4.1 Results
- 4.2 Analysis
- 4.3 Ablation Experiments
- 5 Conclusion
- References
- WikiCPRL: A Weakly Supervised Approach for Wikipedia Concept Prerequisite Relation Learning
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 4 Proposed Approach
- 4.1 Overview of WikiCPRL
- 4.2 Weak Label Generation
- 4.3 Concept Feature Acquisition
- 4.4 Graph Attentional Layer
- 4.5 Encoding-Decoding Layer
- 4.6 Edge Direction Inferring
- 5 Performance Analysis
- 5.1 Datasets
- 5.2 Compare with Baselines
- 5.3 Case Study
- 6 Conclusion
- References
- An Effective Privacy-Preserving and Enhanced Dummy Location Scheme for Semi-trusted Third Parties
- 1 Introduction
- 2 Model and Design Goal
- 2.1 System Model
- 2.2 Security Model
- 2.3 Design Goal
- 3 EPED Scheme Design
- 3.1 Preliminaries
- 3.2 Location Anonymization Model
- 3.3 Optimization Based on the Stackelberg Game
- 4 Performance Evaluation and Security Analysis
- 4.1 Performance Analysis
- 4.2 Security Analysis
- 5 Related Work
- 6 Conclusion
- References
- W-MRI: A Multi-output Residual Integration Model for Global Weather Forecasting
- 1 Introduction
- 2 Related Work
- 2.1 Numerical Weather Prediction
- 2.2 Deep Learning Weather Forecasting Methods
- 2.3 Residual Network
- 3 Preliminaries
- 3.1 Dataset
- 3.2 Multi-variable Forecasting Problems
- 4 Method
- 4.1 ViT and Residual Model
- 4.2 Integration and Constraint of Residual
- 5 Experiments
- 5.1 Evaluation Metrics
- 5.2 Quantitative Forecasting Performance of W-MRI
- 5.3 Effect of Integration Constraint Module
- 6 Conclusion
- References
- HV-Net: Coarse-to-Fine Feature Guidance for Object Detection in Rainy Weather
- 1 Introduction
- 2 Related Work
- 2.1 Object Detection
- 2.2 Single Image Deraining
- 3 Proposed Method
- 3.1 Generate the Edge Map
- 3.2 From Edge-Attentional Features to Image
- 3.3 Object Detection Stage
- 4 Experimental Results
- 4.1 Datasets
- 4.2 Implementation Details
- 4.3 Qualitative and Quantitative Results
- 4.4 Ablation Study
- 5 Conclusion
- References
- Vehicle Collision Warning System for Blind Zone in Curved Roads Based on the Spatial-Temporal Correlation of Coordinate
- 1 Introduction
- 2 Materials and Methods
- 2.1 Target Tracking Method
- 2.2 Traffic Condition Analysis
- 2.3 Module of Communication
- 3 Results
- 3.1 Software Testing
- 3.2 Field Application
- 4 Conclusions
- References
- Local-Global Cross-Fusion Transformer Network for Facial Expression Recognition
- 1 Introduction
- 2 Related Work
- 2.1 Facial Expression Recognition
- 2.2 Transformer
- 3 Method
- 3.1 Overall Framework
- 3.2 Local Feature Decomposition (LFD)
- 3.3 Cross-Fusion Transformer
- 3.4 Loss Function
- 4 Experiment
- 4.1 Experiment Setup
- 4.2 Comparison with the State-of-the-Art Methods
- 4.3 Param and FLOPs Comparison
- 4.4 Ablation Study
- 5 Conclusions
- References
- Answering Spatial Commonsense Questions by Learning Domain-Invariant Generalization Knowledge
- 1 Introduction
- 2 Approach
- 2.1 Setup
- 2.2 Overall Framework
- 2.3 Spatial Commonsense Knowledge Extraction from KG
- 2.4 MRC Model Pretraining with Spatial Commonsense
- 2.5 Domain Invariant Generalization
- 3 Experiments
- 3.1 Dataset and Knowledge Graph
- 3.2 Baseline Models
- 3.3 Implementation Details
- 3.4 Performance Comparison Result
- 3.5 Ablation Study
- 3.6 Case Study
- 3.7 Error Analysis
- 4 Related Work
- 5 Conclusion
- References
- Global and Local Structure Discrimination for Effective and Robust Outlier Detection
- 1 Introduction
- 2 Related Work
- 3 The Proposed Method
- 3.1 Framework
- 3.2 Global Structure Discrimination
- 3.3 Local Structure Discrimination
- 3.4 Complementary and Competitive Cooperation
- 3.5 Optimization
- 4 Experiments
- 4.1 Evaluation Setup
- 4.2 Robustness Test w.r.t. Training Epochs
- 4.3 Effectiveness Test on Diverse Datasets
- 4.4 Ablation Study
- 4.5 Visualization
- 5 Conclusion
- References
- A Situation Knowledge Graph Construction Mechanism with Context-Aware Services for Smart Cockpit
- 1 Introduction
- 2 Related Work
- 2.1 Ontology Model
- 2.2 Contextual Definitions
- 2.3 Contextual Services
- 3 Smart Cockpit Situation Model
- 3.1 Situational Components
- 3.2 Situational Element Relationships
- 3.3 Situational Model
- 4 Smart Cockpit Situation Ontology
- 4.1 User Class Design
- 4.2 Contextual Class Design
- 4.3 Service Class Design
- 4.4 Ontology Construction
- 5 Case Study
- 5.1 Scenario Reasoning
- 5.2 Service Effectiveness Analysis
- 5.3 Situation Knowledge Graph Example
- 6 Conclusions and Future Work
- References
- A Task-Oriented Multi-turn Dialogue Mechanism for the Smart Cockpit
- 1 Introduction
- 2 Data Construction
- 2.1 Knowledge Graphs Construction
- 2.2 Dialogue Collection and Construction
- 2.3 Dialogue Annotation
- 3 Model Architecture
- 3.1 Model Design
- 4 Experiment and Evaluation
- 4.1 Implementation Details
- 4.2 Baseline
- 4.3 Automatic Evaluation
- 4.4 Manual Evaluation
- 4.5 Real Time Label
- 5 Related Work
- 6 Conclusion and Future Work
- A Appendix: Figure from ``A Situation Knowledge Graph Construction Mechanism with Context-Aware Services for Smart Cockpit (submit to APWEB-WAIM2023)''
- References
- MEOM: Memory-Efficient Online Meta-recommender for Cold-Start Recommendation
- 1 Introduction
- 2 Related Work
- 2.1 Online Recommendation
- 2.2 Cold-Start Recommendation
- 3 Problem Definition
- 3.1 Problem Formulation
- 3.2 Meta-learning Setting
- 4 Our Proposed Method
- 4.1 Overview of MEOM
- 4.2 Base Recommender Model
- 4.3 Memory-Efficient Update for Online Meta-Recommender
- 4.4 Dual-Level Adaptive Learning Rate for Meta-recommender
- 4.5 Cluster-Based Preference Modelling
- 5 Experiments
- 5.1 Datasets
- 5.2 Evaluation Settings
- 5.3 Baseline Methods
- 5.4 Experimental Results
- 6 Conclusion
- References
- A Social Bot Detection Method Using Multi-features Fusion and Model Optimization Strategy
- 1 Introduction
- 2 Related Work
- 2.1 Feature Engineering-Based Approaches
- 2.2 Machine Learning-Based Approaches
- 3 Proposed Approach
- 3.1 Feature Engineering
- 3.2 Model Construction
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Performance Evaluation Results
- 4.3 Results on Different Ratio of Social Bots and Benign Users
- 4.4 Comparison with Previous Methods
- 5 Conclusions
- References
- Benefit from AMR: Image Captioning with Explicit Relations and Endogenous Knowledge
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Feature Extraction
- 3.2 AMR-Based Captioning
- 4 Experiments
- 4.1 Dataset, Preprocess, and Metrics
- 4.2 Comparison with State-of-the-art Methods
- 4.3 Ablation Studies
- 4.4 Case Study
- 5 Conclusion
- References
- SSCAN:Structural Graph Clustering on Signed Networks
- 1 Introduction
- 2 Problem Definition
- 3 Our SSCAN-Basic Approach
- 3.1 Balanced Triangles Counting
- 3.2 SSCAN-Basic
- 4 An Index-Based Approach
- 4.1 SSCAN Indexing
- 5 Experiments
- 6 Conclusion
- References
- ANSWER: Automatic Index Selector for Knowledge Graphs
- 1 Introduction
- 2 Related Work
- 3 Framework Overview
- 3.1 Predicate Filter
- 3.2 Encoder
- 3.3 ANSWER
- 4 ANSWER
- 5 Experimental Evaluation
- 5.1 Settings
- 5.2 Comparisons of Index Selectors
- 5.3 Comparisons of Replacement Strategies
- 5.4 Parameter Tuning
- 6 Conclusion
- References
- A Long-Tail Relation Extraction Model Based on Dependency Path and Relation Graph Embedding
- 1 Introduction
- 2 Approach
- 2.1 Task Definition
- 2.2 Sentence Encoder
- 2.3 Dependency Path Encoder
- 2.4 Relational Encoder
- 2.5 Aggregators
- 2.6 Classifier
- 3 Experiments
- 3.1 Experimental Setup
- 3.2 Analysis of Noise Experiment
- 3.3 Analysis of the Results of the Long-Tail Experiment
- 3.4 Ablation Experiment
- 3.5 Case Study
- 4 Related Work
- 5 Conclusion
- References
- Multi-token Fusion Framework for Multimodal Sentiment Analysis
- 1 Introduction
- 2 Related Work
- 2.1 Multimodal Sentiment Analysis
- 2.2 Attention Mechanisms in Multimodal Fusion
- 3 Proposed Method
- 3.1 Tri-token Transformer (TT) Module
- 3.2 Hierarchical Element-Wise Self-Attention (HESA) Module
- 3.3 Objective Function
- 4 Experiments
- 4.1 Datasets
- 4.2 Evaluation Metrics
- 4.3 Experimental Details
- 4.4 Baselines
- 4.5 Results and Discussions
- 4.6 Ablation Study
- 4.7 Case Study
- 5 Conclusions
- References
- Generative Adversarial Networks Based on Contrastive Learning for Sequential Recommendation
- 1 Introduction
- 2 Preliminaries
- 2.1 Sequential Recommendation
- 2.2 GAN
- 3 CtrGAN
- 3.1 Generative Model(G)
- 3.2 Adversarial Nets(D)
- 3.3 Training
- 4 Experiments and Analysis
- 4.1 Datasets
- 4.2 Implementation Details and Metrics
- 4.3 Performance Comparison with Baselines
- 4.4 The Different Loss Function of CtrGAN
- 4.5 Ablation Study
- 4.6 Stability of CtrGAN
- 5 Conclusion
- References
- Multimodal Stock Price Forecasting Using Attention Mechanism Based on Multi-Task Learning
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 MTASPM Architecture
- 3.2 Stock Correlation Graph Construction
- 3.3 Main Task
- 3.4 Auxiliary Task
- 3.5 Loss Function
- 4 Experiments
- 4.1 Datasets and Data Processing
- 4.2 Stock Correlation Graph Visualization
- 4.3 Baseline Models and Metrics
- 4.4 Comparative Analysis of MTASPM
- 4.5 Parameter Sensitivity Analysis
- 4.6 Ablation Studies
- 4.7 Computation Cost
- 5 Conclusion and Future Work
- References
- Federated Trajectory Search via a Lightweight Similarity Computation Framework
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 3.1 Problem Model
- 3.2 Lightweight Trajectory Similarity Measure
- 4 Fetra Framework
- 4.1 Local Processing on Devices
- 4.2 Federated Indexing on Server
- 4.3 Period Temporal Index
- 5 Federated Top-k Search
- 5.1 Algorithm Overview
- 5.2 Pruning for LCTS
- 5.3 Local Boost for LCTS
- 6 Experiments
- 6.1 Experimental Setup
- 6.2 Efficiency Evaluation of Search Algorithms
- 6.3 Efficiency Evaluation of LCTS
- 6.4 Effectiveness Evaluation
- 7 Conclusion and Future Work
- References
- Central Similarity Multi-view Hashing for Multimedia Retrieval
- 1 Introduction
- 2 Related Work
- 3 The Proposed Methodology
- 3.1 Deep Multi-view Hashing Network
- 3.2 Central Similarity Learning
- 4 Experiments
- 4.1 Evaluation Datasets
- 4.2 Evaluation Metrics
- 4.3 Implementation Details
- 4.4 Baseline
- 4.5 Analysis of Experimental Results
- 4.6 Ablation Studies
- 4.7 Convergence Analysis
- 4.8 mAP@K and Recall@K
- 5 Conclusion and Future Work
- References
- Entity Alignment Based on Multi-view Interaction Model in Vulnerability Knowledge Graphs
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 4 Methodology
- 4.1 QuatAE
- 4.2 Text and Graph Interaction Model
- 4.3 Entity Alignment
- 5 Experiments
- 5.1 Datasets and Implementation
- 5.2 Experiments
- 6 Conclusion
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.