Databases Theory and Applications: 31st Australasian Database Conference, ADC 2020, Melbourne, Vic, Australia, February 3-7, 2020, Proceedings

Description

This book constitutes the refereed proceedings of the 31th Australasian Database Conference, ADC 2019, held in Melbourne, VIC, Australia, in February 2020. The 14 full and 5 short papers presented were carefully reviewed and selected from 30 submissions. The Australasian Database Conference is an annual international forum for sharing the latest research advancements and novel applications of database systems, data driven applications and data analytics between researchers and practitioners from around the globe, particularly Australia, New Zealand and in the World. Preface General Chair’s Welcome Message Organization Contents Full Research Papers Semantic Round-Tripping in Conceptual Modelling Using Restricted Natural Language 1 Introduction 2 Motivation 3 Proposed Approach 3.1 Scenario 4 RNL Specification to DL ALCQI Representation 5 DL ALCQI Representation to SQL Script 6 Conceptual Model Generation 7 Database Schema to DL ALCQI Representation 8 DL ALCQI Representation to RNL verbalisation 9 Evaluation 10 Conclusion References PAIC: Parallelised Attentive Image Captioning 1 Introduction 2 Related Work 2.1 Image Captioning 2.2 Attention Model 3 Methodology 3.1 Problem Formulation 3.2 Preliminaries 3.3 The Attentive Encoder-Decoder 3.4 Visual Feature Encoder 3.5 Language Decoder 4 Experiments 4.1 Experimental Settings 4.2 Quantitative Analysis 4.3 Qualitative Analysis 4.4 Training Efficiency Analysis 4.5 Model Structure Comparison 5 Conclusion References Efficient kNN Search with Occupation in Large-Scale On-demand Ride-Hailing 1 Introduction 2 Related Work 2.1 kNN Queries 2.2 Shortest Path Queries 3 Preliminary 4 AkNN Query Algorithms 4.1 Dijkstra AkNN 4.2 Grid-Based AkNN 5 Experimental Study 5.1 Experiment Setup 5.2 Case Study 5.3 Different Indexes 5.4 AkNN Search Algorithms 6 Conclusion References Trace-Based Approach for Consistent Construction of Activity-Centric Process Models from Data-Centric Process Models 1 Introduction 2 Motivating Example 3 Preliminaries 4 Transformation Approach 4.1 Model Construction 4.2 Extract Model Traces 4.3 Trace-Based Analysis 5 Case Study 6 Related Work and Discussion 7 Conclusion References Approximate Fault Tolerance for Sensor Stream Processing 1 Introduction 2 Preliminaries 2.1 Data Streams 2.2 Estimation Based on a Multivariate Gaussian Distribution 2.3 Aggregation Queries 3 Problem Definition 3.1 Backup Cost 3.2 Confidence Score of Recovery 3.3 Problem Definition 4 Backup Selection for Approximate Fault Tolerance 4.1 Upper Bounds Derivation for Variance of Sensors 4.2 Greedy-Based Backup Selection 5 Experimental Evaluation 5.1 Experimental Settings 5.2 Experimental Results 6 Conclusion References Function Interpolation for Learned Index Structures 1 Introduction 2 Related Work 3 Background 3.1 Range Indexes as Cumulative Distribution Functions 3.2 Polynomial Interpolation 4 Indexes by Function Approximation 4.1 Interpolant Construction 4.2 Query Processing 5 Experimental Results 5.1 Model Creation Time 5.2 Memory Footprint 5.3 Query Accuracy and Time 5.4 Rate of Convergence of Polynomial Models 6 Conclusion References DEFINE: Friendship Detection Based on Node Enhancement 1 Introduction 2 Related Work 2.1 Network Representation Learning 2.2 Friendship Prediction 3 Problem Formulation 4 Design of DEFINE 5 Experiments 5.1 Datasets 5.2 Prediction 6 Conclusion References Semi-supervised Cross-Modal Hashing with Graph Convolutional Networks 1 Introduction 2 Related Work 3 Proposed Method 3.1 Preliminaries 3.2 Problem Formulation 3.3 Dual-Branch Graph Convolutional Network Hashing 3.4 Objective Function 3.5 Learning and Testing 4 Experiments 4.1 Datasets and Features 4.2 Experiment Settings 4.3 Implementation Details 4.4 Experiment Results and Analysis 5 Conclusion References Typical Snapshots Selection for Shortest Path Query in Dynamic Road Networks 1 Introduction 2 Related Work 2.1 Shortest Path Algorithm 2.2 Graph Similarity Measurement 3 Problem Definition 4 Time-Based Typical Snapshot Selection 4.1 Uniform Sampling 4.2 Non-uniform Sampling 5 Graph Representation-Based Selection 5.1 Edge-Based Representation 5.2 Vertex-Based Representation 5.3 Graph Clustering and Snapshot Matching 6 Experiments 6.1 Experimental Setup 6.2 Typical Snapshot Selection 6.3 Snapshot Matching 7 Conclusion References A Survey on Map-Matching Algorithms 1 Introduction 2 Preliminaries 2.1 Problem Definition 2.2 Related Work 3 Survey of Map-Matching Algorithm 3.1 Similarity Model 3.2 State-Transition Model 3.3 Candidate-Evolving Model 3.4 Scoring Model 4 Challenges and Evaluations 4.1 Experimental Settings 4.2 Data Quality Challenges 5 Conclusion References Gaussian Embedding of Large-Scale Attributed Graphs 1 Introduction 2 Related Work 3 GLACE Methodology 3.1 Notations and Problem Definition 3.2 Overall Architecture 3.3 Node Attribute Encoding 3.4 Graph Structure Encoding 3.5 Model Optimization 3.6 Complexity Analysis 4 Experiments 4.1 Datasets 4.2 Compared Algorithms and Setup 4.3 Link Prediction 4.4 Multi-class Node Classification 4.5 Inductive Learning 4.6 Scalability 4.7 Visualization 5 Conclusion References Geo-Social Temporal Top-k Queries in Location-Based Social Networks 1 Introduction 2 Related Work 3 Preliminaries 3.1 Problem Definition 3.2 Framework Overview 4 Proposed Techniques 4.1 Social-First Based Approach 4.2 Spatial-First Based Approach 4.3 Hybrid Approach 5 Experiments 5.1 Experimental Setup 5.2 Performance Evaluation 5.3 Conclusions References Effective and Efficient Community Search in Directed Graphs Across Heterogeneous Social Networks 1 Introduction 2 Related Work 2.1 Community Search 2.2 User Identity Linkage 3 Problem Definition 4 Our User Identity Linkage Approach 4.1 Retrieval of Valid User Sets 4.2 Comparisons of Users 4.3 Matching Users 4.4 Combination of Social Networks 5 Our Community Search Approach 5.1 Cores Decomposition 5.2 Index Construction 6 Cost Analysis 7 Experiment Evaluation 7.1 Experimental Setup 7.2 Evaluation Methodology 7.3 Effectiveness Evaluation 7.4 Efficiency Comparison 8 Conclusion References Entity Extraction with Knowledge from Web Scale Corpora 1 Introduction 2 Related Work 3 The 2ED Algorithm 3.1 Features of the 2ED Algorithm 3.2 Drawbacks of the 2ED Algorithm 4 Improvement on 2ED 4.1 Distinguishing a Typo from an Intended Token 4.2 Using Language Models 4.3 Estimating Word Similarity 4.4 Other Improvements 5 Implementation 5.1 Obtain Candidate Pairs 5.2 Rescore Candiadte Pairs 6 Experimental Studies 7 Conclusion and Future Work References Short Papers Graph-Based Relation-Aware Representation Learning for Clothing Matching 1 Introduction 2 Related Work 2.1 Fashion Compatibility Learning 2.2 Graph Neural Networks 3 Proposed Approach 3.1 Problem Formulation 3.2 Part 1: Item Representation Generation 3.3 Part 2: Type-Aware Compatibility Prediction 3.4 Training Strategy 4 Experiments 4.1 Dataset 4.2 Baselines 4.3 Implementation Details 4.4 Task Description 4.5 Performance Comparison 5 Conclusion References Evaluating Random Walk-Based Network Embeddings for Web Service Applications 1 Introduction 2 Web Service Networks and Their Properties 2.1 Composition - Service Network 2.2 Popularity and Fitness-Based Service Evolving Networks 3 Analysis and Results 4 Conclusion and Future Work References Query-Oriented Temporal Active Intimate Community Search 1 Introduction 2 Related Work 3 Preliminary and Problem Definition 4 AIC Detection Algorithm 4.1 Baseline Solution 4.2 Improved Greedy Algorithm 5 Experiment and Result 5.1 Efficiency 5.2 Community Quality Evaluation 6 Conclusion References A Contextual Semantic-Based Approach for Domain-Centric Lexicon Expansion 1 Introduction 2 Proposed Approach 2.1 Candidate Words Extraction 2.2 Contextual Semantic-Based Graph Construction 2.3 Words Ranking and Lexicon Expansion 3 Experimental Setup and Results 3.1 Dataset and Embedding Learning 3.2 Evaluation Results 3.3 Comparative Analysis 4 Conclusion References Data-Driven Hierarchical Neural Network Modeling for High-Pressure Feedwater Heater Group 1 Introduction 2 Industrial Background 2.1 Thermal Power Plant Regenerative System 2.2 High-Pressure Feedwater Heater Group 3 Data-Driven Hierarchical Neural Network Modeling 3.1 Architecture of the Proposed Model 3.2 Model Training Process 4 Experiments 4.1 Experimental Data 4.2 Performance Evaluation Criteria 4.3 Experimental Setting and Results 5 Conclusion References Early Detection of Diabetic Eye Disease from Fundus Images with Deep Learning 1 Introduction 2 Literature Review 3 Research Challenges 4 Contribution to Knowledge 4.1 Analysis of Diabetic Eye Disease Using Deep Learning 4.2 Statement of Significance 5 Conclusions References Author Index