
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 44 full papers presented together with 24 short papers, and 6 demonstration papers were carefully reviewed and selected from 184 submissions. The papers are organized around the following topics: Graph Mining; Data Mining; Data Management; Topic Model and Language Model Learning; Text Analysis; Text Classification; Machine Learning; Knowledge Graph; Emerging Data Processing Techniques; Information Extraction and Retrieval; Recommender System; Spatial and Spatio-Temporal Databases; and Demo.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents - Part II
- Contents - Part I
- Machine Learning 2
- Unsupervised Deep Hashing via Adaptive Clustering
- 1 Introduction
- 2 Related Work
- 2.1 Similarity-Preserving Hashing
- 3 Method
- 3.1 Problem Definition
- 3.2 Framework
- 3.3 Discriminative Loss
- 3.4 Classification Loss
- 3.5 Cluster Reassignments
- 4 Experiments
- 4.1 Datasets
- 4.2 Baseline Methods
- 4.3 Evaluation
- 4.4 Implementation Details
- 4.5 Result Analysis
- 4.6 Discussion
- 5 Conclusion
- References
- FedMDR: Federated Model Distillation with Robust Aggregation
- 1 Introduction
- 2 Robust Federated Model Distillation
- 2.1 Problem Statement
- 2.2 The FedMDR Framework
- 2.3 Robust Aggregation Mechanism
- 2.4 FedMDR with Differential Privacy
- 3 Performance Evaluation
- 3.1 Experimental Setup
- 3.2 Experimental Results
- 4 Discussions
- 5 Related Work
- 6 Conclusion
- References
- Data Augmentation for Graph Convolutional Network on Semi-supervised Classification
- 1 Introduction
- 2 Proposed Method
- 2.1 Data Augmentation Strategy
- 2.2 Feature Availability Investigation
- 2.3 Attentional Integration Model
- 2.4 Objective Function
- 3 Experiments
- 3.1 Experiment Setting
- 3.2 Semi-Supervised Classification
- 3.3 Attentional Integration Model Analysis
- 3.4 Parameter Sensitivity
- 4 Related Works
- 5 Conclusion
- References
- Generating Long and Coherent Text with Multi-Level Generative Adversarial Networks
- 1 Introduction
- 2 Preliminaries
- 3 Methodology
- 3.1 Semantic Sketch Generation
- 3.2 Sentence Realization
- 3.3 Discussion and Learning
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Results and Analysis
- 5 Related Work
- 6 Conclusion
- References
- A Reasonable Data Pricing Mechanism for Personal Data Transactions with Privacy Concern
- 1 Introduction
- 2 Related Work
- 3 Personal Data Pricing Mechanism
- 3.1 System Model
- 3.2 Personal Privacy Data Pricing Function
- 4 Experiments
- 4.1 Experimental Data and Setup
- 4.2 Experimental Results
- 5 Conclusion
- References
- Knowledge Graph
- A Probabilistic Inference Based Approach for Querying Associative Entities in Knowledge Graph
- 1 Introduction
- 2 Related Work
- 3 AEBN Construction
- 3.1 Generating Rules for AEBN Construction
- 3.2 Structure Construction
- 3.3 Parameter Learning
- 4 Ranking AEs by Approximate Inferences over AEBN
- 5 Experiments
- 5.1 Experiment Setup
- 5.2 Effectiveness Tests
- 5.3 Efficiency Tests
- 6 Conclusions and Future Work
- References
- BOUNCE: An Efficient Selective Enumeration Approach for Nested Named Entity Recognition
- 1 Introduction
- 2 Related Work
- 3 BOUNCE Approach to Nested NER
- 3.1 Token Representation
- 3.2 Unit Region Classification
- 3.3 Span Region Head Detection
- 3.4 Span Region Classification
- 3.5 Time Complexity Analysis
- 4 Experiments
- 4.1 Datasets and Experimental Settings
- 4.2 Comparison Results
- 4.3 Ablation Study
- 5 Conclusion
- References
- PAIRPQ: An Efficient Path Index for Regular Path Queries on Knowledge Graphs
- 1 Introduction
- 2 Related Work
- 2.1 Path Index
- 2.2 RDF Storage Engine
- 3 Preliminaries
- 4 Path Index for Regular Path Queries
- 4.1 Frequent Path Mining
- 4.2 Index Scheme
- 4.3 Query Processing
- 5 Experiments
- 5.1 Experimental Settings
- 5.2 Experimental Results
- 6 Conclusion
- References
- A Hybrid Semantic Matching Model for Neural Collective Entity Linking
- 1 Introduction
- 2 Related Work
- 3 The HSM Model
- 3.1 Local Mention-to-Entity Model
- 3.2 Global Model
- 4 Experiments and Results
- 4.1 Datasets
- 4.2 Settings
- 4.3 Results
- 5 Conclusion
- References
- Multi-space Knowledge Enhanced Question Answering over Knowledge Graph
- 1 Introduction
- 2 Our Approach
- 2.1 Answer Aspect Attention Network
- 2.2 Multi-space Attention Network
- 2.3 Model Training
- 3 Experiments
- 3.1 Performance Comparison
- 4 Conclusion
- References
- Emerging Data Processing Techniques
- A Distribution-Aware Training Scheme for Learned Indexes
- 1 Introduction
- 2 The Learned Index
- 3 The Problem
- 3.1 Query Distribution
- 3.2 Data Distribution
- 4 DATum
- 4.1 Data Stretching
- 4.2 Model Cache
- 5 Experiments
- 5.1 Data Stretching
- 5.2 Model Cache
- 6 Related Works
- 7 Conclusion
- References
- AIR Cache: A Variable-Size Block Cache Based on Fine-Grained Management Method
- 1 Introduction
- 2 Related Work
- 3 Motivation
- 3.1 Internal Fragmentation
- 3.2 False Positives in Identifying Hot Cache Blocks
- 4 AIR Cache Design
- 4.1 Fine-Grained Recorder
- 4.2 Multi-Granularity Writer
- 4.3 Multi-Granularity Eviction
- 5 Experimental Evaluation
- 5.1 Experimental Setup
- 5.2 Performance Results
- 6 Conclusion
- References
- Learning an Index Advisor with Deep Reinforcement Learning
- 1 Introduction
- 2 Problem Formalization
- 3 Learning Index Selection
- 3.1 ISP as a DRL Problem
- 3.2 Index Agent for Indexes
- 3.3 Reward Design
- 3.4 Reinforcement Learning Training
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Reinforcement Learning Training Details
- 4.3 Performance Comparative Evaluation
- 5 Conclusions
- References
- SardineDB: A Distributed Database on the Edge of the Network
- 1 Introduction
- 2 Architecture of SardineDB
- 2.1 Architecture of SardineDB
- 2.2 Architecture of SardineCore
- 3 Experiments
- 3.1 Experimental Setup
- 3.2 Performance of SardineCore
- 3.3 Performance of SardineDB
- 4 Conclusion
- References
- DLSM: Distance Label Based Subgraph Matching on GPU
- 1 Introduction
- 2 Distance Label Based Subgraph Matching (DLSM)
- 2.1 Problem Definition
- 2.2 Distance Label Based Filtering
- 3 DLSM Overview
- 4 Experimental Results
- 4.1 Experimental Setup
- 4.2 Results on Synthetic and Real World Datasets
- 5 Related Work
- 6 Conclusion
- References
- Information Extraction and Retrieval
- Distributed Top-k Pattern Mining
- 1 Introduction
- 2 Graphs, Patterns and Pattern Mining
- 2.1 Graph Pattern Matching
- 2.2 Frequent Pattern Mining
- 2.3 Problem Formalization
- 3 Distributed Top-k Pattern Mining
- 4 Experimental Study
- 5 Conclusion
- References
- SQKT: A Student Attention-Based and Question-Aware Model for Knowledge Tracing
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 4 The SQKT Method
- 4.1 Question Representation
- 4.2 Student Attention Mechanism
- 4.3 Modeling Process of SQKT
- 4.4 Optimization
- 5 Experiments
- 5.1 Datasets
- 5.2 Baselines
- 5.3 Metrics
- 5.4 Model Evaluation
- 5.5 Ablation Studies
- 6 Conclusion
- References
- Comparison Question Generation Based on Potential Compared Attributes Extraction
- 1 Introduction
- 2 Related Work
- 3 Framework
- 3.1 Attribute Extractor
- 3.2 Attribute-Attention Seq2seq Module
- 4 Experiment
- 4.1 Dataset
- 4.2 Experimental Details
- 4.3 Evaluation
- 4.4 Comparative Models for Generation Task
- 5 Results and Analysis
- 5.1 Additional Features
- 5.2 Case Study
- 6 Conclusions
- References
- Multimodal Encoders for Food-Oriented Cross-Modal Retrieval
- 1 Introduction
- 2 Related Work
- 3 Model Framework
- 3.1 Overview of the Overall Framework
- 3.2 Initial Embedding Generation
- 3.3 Multimodal Encoders
- 3.4 Modality Alignment
- 3.5 Cross-Modal Learning
- 3.6 Training and Inference
- 4 Experiments
- 4.1 Dataset and Evaluation Metrics
- 4.2 Baselines
- 4.3 Implementation
- 4.4 Main Results
- 4.5 Ablation Studies
- 5 Conclusion
- References
- Data Cleaning for Indoor Crowdsourced RSSI Sequences
- 1 Introduction
- 2 Preliminaries and Problem Statement
- 3 Cleaning the Received Signal Strength Values
- 3.1 Alignment and Matching of RSSIs in Different RSSI Sequences
- 3.2 Cleaning Missing Values in Continuous Multiple RSSIs
- 4 Cleaning the Location Labels
- 4.1 Logical Graph Gl: Topology and Constraints of Indoor Space
- 4.2 Repair of False and Missing Location Label for Single RSSI
- 4.3 Repair of False and Missing Location Labels for Continuous Multiple RSSIs
- 5 Experimentation and Evaluation
- 5.1 Accuracy of Location Labels Cleaning
- 5.2 Accuracy of Localization
- 5.3 Average Error Distance
- 6 Conclusion
- References
- Recommender System
- A Behavior-Aware Graph Convolution Network Model for Video Recommendation
- 1 Introduction
- 2 Related Work
- 3 Sagittarius Model
- 3.1 Problem Formulation
- 3.2 Model Architecture
- 3.3 Learning Objectives
- 3.4 Recommendation Acceleration
- 4 Evaluation
- 4.1 Experimental Setup
- 4.2 Competitors
- 4.3 Performance Comparison
- 4.4 Ablation Analyses
- 4.5 Impact of Hyper-parameters
- 4.6 Online A/B Test
- 5 Conclusion
- References
- GRHAM: Towards Group Recommendation Using Hierarchical Attention Mechanism
- 1 Introduction
- 2 Related Work
- 2.1 Group Recommendation
- 2.2 Attention Mechanism for Recommendation
- 3 GRHAM Model
- 3.1 Notations and Problem Formulation
- 3.2 Model Framework
- 3.3 Model Optimization
- 4 Experiments
- 4.1 Datasets
- 4.2 Evaluation
- 4.3 Baselines
- 4.4 Overall Performance Comparison(RQ1)
- 4.5 Model Performances for Different Hyper-Parameters (RQ2)
- 5 Conclusion and Future Work
- References
- Multi-interest Network Based on Double Attention for Click-Through Rate Prediction
- 1 Introduction
- 2 Related Work
- 3 Model of This Paper
- 3.1 Embedded Layer
- 3.2 Users' Dynamic Interest Features Extraction Layer
- 3.3 Multi-interest Extraction Layer
- 3.4 Loss Function
- 4 Experiments
- 4.1 Datasets and Experiment Setup
- 4.2 Competitors
- 4.3 Evaluation Metrics
- 4.4 Comparative Experimental Results
- 4.5 Ablation Experimental Results
- 5 Conclusion
- References
- Self-residual Embedding for Click-Through Rate Prediction
- 1 Introduction
- 2 Problem Definition
- 3 Methodology
- 3.1 Input and Embedding Layer
- 3.2 Self-residual Embedding Layer
- 3.3 Second-Order Feature Interaction
- 3.4 Hidden Layer
- 3.5 Output Layer
- 3.6 Model Training
- 4 Experiments
- 4.1 Experimental Settings
- 4.2 Experimental Results
- 4.3 Influence of the Network Structure
- 5 Conclusion
- References
- GCNNIRec: Graph Convolutional Networks with Neighbor Complex Interactions for Recommendation
- 1 Introduction
- 2 Related Works
- 3 Our Approach
- 3.1 Raw Input and Embedding Initialization
- 3.2 Linear-Aggregator Module
- 3.3 Interaction-Aggregator Module
- 3.4 Final Embedding
- 3.5 Rating Prediction
- 4 Experiments
- 4.1 Experimental Settings
- 4.2 Performance Comparison
- 4.3 Hyper-Parameter Analysis of GCNNIRec
- 5 Conclusion
- References
- Spatial and Spatio-Temporal Databases
- Velocity-Dependent Nearest Neighbor Query
- 1 Introduction
- 2 Velocity-Dependent Nearest Neighbors
- 2.1 Baseline Algorithm
- 3 R-Tree Based Algorithm
- 3.1 Useful MBRs
- 3.2 Search Algorithm
- 4 Tile-Based Algorithms
- 4.1 Queries on Adaptive Tiles
- 5 Experiment
- 5.1 Query Performances
- 5.2 Efficiencies of Tile-Based Structures
- 6 Conclusions
- References
- Finding Geo-Social Cohorts in Location-Based Social Networks
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 3.1 Preliminary Concepts
- 3.2 Objective
- 3.3 Maximizing Activity Density
- 4 COVER Algorithm
- 5 Experimental Study
- 5.1 Brute-Force Convoy Retrieval
- 5.2 Use Case: Convoy Prediction
- 5.3 Revalidating the Social Clique Constraint
- 5.4 Prediction Without Input Categories
- 5.5 Prediction with Input Categories
- 5.6 Effect of Surplus Parameter
- 5.7 Scalability and Prediction Quality
- 5.8 Analysis on Retrieved Groups
- 6 Conclusion
- References
- Modeling Dynamic Spatial Influence for Air Quality Prediction with Atmospheric Prior
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 4 Proposed Method
- 4.1 Feature Representation
- 4.2 Dynamic Spatial Graph Construction
- 4.3 Dynamic Spatial Graph Embedding
- 4.4 Encoder-Decoder Based Spatio-Temporal Fusion
- 4.5 Model Learning
- 5 Experiments
- 5.1 Datasets
- 5.2 Experimental Settings
- 5.3 Compared Methods
- 5.4 Experimental Results
- 6 Conclusion and Future Work
- References
- Learning Cooperative Max-Pressure Control by Leveraging Downstream Intersections Information for Traffic Signal Control
- 1 Introduction
- 2 Related Work
- 3 Preliminary
- 4 Our Approach
- 4.1 Agent Design
- 4.2 Learning Process
- 5 Stability Analysis
- 6 Experiments
- 6.1 Datasets and Baselines
- 6.2 Experimental Settings
- 6.3 Experimental Results
- 7 Conclusion and Future Work
- References
- Privacy-Preserving Healthcare Analytics of Trajectory Data
- 1 Introduction and Related Works
- 2 Our Differential-Privacy Framework for Analytics of Spatio-Temporal Trajectory
- 3 Evaluation
- 4 Conclusions
- References
- Demo
- PARROT: An Adaptive Online Shopping Guidance System
- 1 Introduction
- 2 System Implementation
- 3 Demo Scenarios
- 3.1 Scenario 1: Products' Descriptions with Basic Attributes
- 3.2 Scenario 2: Products' Descriptions with Functional Attributes
- 3.3 Scenario 3: Products' Descriptions with Experience Attributes
- 4 Conclusion
- References
- gStore-C: A Transactional RDF Store with Light-Weight Optimistic Lock
- 1 Introduction
- 2 System Overview
- 3 Lightweight Optimistic Lock
- 4 Demonstration
- References
- Deep-gAnswer: A Knowledge Based Question Answering System
- 1 Introduction
- 2 System Architecture
- 3 Techniques
- 4 Demonstration
- References
- ALMSS: Automatic Learned Index Model Selection System
- 1 Introduction
- 2 System Overview
- 3 Key Technologies
- 3.1 Automatic Model Selection Module
- 3.2 Learned Index with Automatic Model Selection Module
- 4 Demonstration Scenarios
- References
- GPKRS: A GPU-Enhanced Product Knowledge Retrieval System
- 1 Introduction
- 2 System Overview
- 3 Demonstration
- References
- Standard-Oriented Standard Knowledge Graph Construction and Applications System
- 1 Introduction
- 2 Architecture of Standard Knowledge Graph
- 3 Standard-Oriented Knowledge Graph Based Algorithms
- 3.1 Standard Template Recommendation
- 3.2 Standard Conflict Detection
- 4 Visualization and Case Study
- 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.