Database Systems for Advanced Applications. DASFAA 2023 International Workshops: BDMS 2023, BDQM 2023, GDMA 2023, BundleRS 2023, Tianjin, China, April ... (Lecture Notes in Computer Science)

✍ Scribed by Amr El Abbadi (editor), Gillian Dobbie (editor), Zhiyong Feng (editor), Lu Chen (editor), Xiaohui Tao (editor), Yingxia Shao (editor), Hongzhi Yin (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 352
• Category: Library

✦ Synopsis

This volume constitutes the papers of several workshops which were held in conjunction with the 28th International Conference on Database Systems for Advanced Applications, DASFAA 2023, held in Tanjin, China, in April 2023.

The 23 revised full papers presented in this book were carefully reviewed and selected from 40 submissions. DASFAA 2023 presents the following four workshops:
9th International Workshop on Big Data Management and Service (BDMS 2023), 8th International Workshop on Big Data Quality Management (BDQM 2023); 7th International Workshop on Graph Data Management and Analysis (GDMA 2023); 1st International Workshop on Bundle-based Recommendation Systems (BundleRS 2023).

✦ Table of Contents

Preface
Organization
Contents
BDMS
Blood and Blood Products Management System Based on Blockchain, and NFT Technologies
1 Introduction
2 Related Work
3 Approach
3.1 Traditional Model of Blood Donation and Blood Management
3.2 Blood Donation and Blood Management Model Based on Blockchain Technology, Smart Contract and NFT
4 Implementation
4.1 Initialize Data/NFT
4.2 Data Query
4.3 Data Updated
5 Evaluation Scenarios
5.1 Transaction Fee
5.2 Gas Limit
5.3 Gas Used by Transaction
5.4 Gas Price
6 Discussion
7 Conclusion
References
ip2text: A Reasoning-Aware Dataset for Text Generation of Devices on the Internet
1 Introduction
2 Related Work
3 Problem and Dataset
3.1 Problem Definition
3.2 Dataset Construction
4 Experiments
4.1 Settings
4.2 Baselines
4.3 Evaluation
4.4 Results
5 Conclusion
References
Spatio-Textual Group Skyline Query
1 Introduction
2 Related Work
2.1 Skyline Groups Query
2.2 Spatial Keyword Query
3 Problem Definitions and Preliminaries
3.1 Problem Definitions
3.2 Preliminaries
4 Approach
4.1 Basic Spatio-Textual Group Skyline Query
4.2 Index-Based Spatio-Textual Group Skyline Query
4.3 Analysis
5 Experiments
5.1 Experimental Setups
5.2 Experimental Evaluation
6 Conclusion
References
Towards a Cash-on-Delivery Management Solution Based on Blockchain, Smart Contracts, and NFT
1 Introduction
2 Related Work
3 Approach
3.1 The Traditional Model of Freight Transport
3.2 Cargo Transport Model Based on Blockchain Technology, Smart Contract and NFT
4 Implementation
4.1 Initialize Data/NFT
4.2 Data Query
4.3 Data Updated
5 Evaluation
5.1 Transaction Fee
5.2 Gas Limit
5.3 Gas Used by Transaction
5.4 Gas Price
6 Discussion
7 Conclusion
References
EGL: Efficient Graph Learning with Safety Constrains for Heterogeneous Trajectory Prediction
1 Introduction
2 Problem Definition
3 Methodology
3.1 Model Framework
3.2 Feature Extraction of Road Network Information
3.3 Encoder
3.4 Decoder
4 Experiments
4.1 Experimental Setup
4.2 Evaluation of Trajectory Prediction
4.3 Case Study
5 Related Work
5.1 Graph Neural Network
5.2 LSTM for Sequence Prediction
6 Conclusion
References
MeFormer: Generating Radiology Reports via Memory Enhanced Pretraining Transformer
1 Introduction
2 Related Work
2.1 Image Captioning
2.2 Report Generation
2.3 Self-Supervised Methods in Medical Imaging
3 The Proposed Method
3.1 Problem Definition
3.2 Model Architecture
3.3 Memory Updater
4 Experiment
4.1 Datasets, Metrics and Settings
4.2 Main Results
4.3 Quantitative Analysis
4.4 Effect of Pretrained ViT
4.5 Effect of Memory
4.6 Effect of Memory Size
5 Conclusion
References
Cache-Enhanced InBatch Sampling with Difficulty-Based Replacement Strategies for Learning Recommenders
1 Introduction
2 Related Work
3 Cache-Enhanced Inbatch Sampling
3.1 Problem Formulation
3.2 Inbatch Sampling and Native Caches
3.3 Inbatch Sampling With Difficulty-Based Replacement Strategies
3.4 Complexity Analysis
4 Experiments
4.1 Experimental Setup
4.2 Comparison with Baselines
4.3 Item Distribution in Cache
4.4 Effect of Including Item Features
4.5 Effect of Cache Size
4.6 Effect of Hyperparameters
5 Conclusion
References
Syndrome-Aware Herb Recommendation with Heterogeneous Graph Neural Network
1 Introduction
2 Related Work
2.1 Graph Based Herb Recommendation
2.2 Heterogeneous Graph Neural Networks-Based Recommender Systems
3 Methodologies
3.1 Problem Definition
3.2 Syndrome Clustering
3.3 Syndrome-Aware Herb Recommendation
4 Experiments
4.1 Dataset
4.2 Evaluation
4.3 Baselines
4.4 Parameter Settings
4.5 Performance Comparison
5 Conclusions
References
BDQM
Fault Prediction Based on Traffic Light Data Cleaning
1 Introduction
2 Problem Formulation
3 Methodology
4 Experiments
4.1 Data Collection Environment
4.2 Experimental Environment
4.3 Performance Indicators
4.4 Pattern Recognition Results
4.5 Fault Prediction Results
5 Conclusion
References
Auto-TSA: An Automatic Time Series Analysis System Based on Meta-learning
1 Introduction
2 Auto-TSA System
2.1 System Architecture and Workflow
2.2 Automated Model Selection
2.3 Sample Demonstrations
3 Conclusion
References
BundleRS
Mobile Application Ranking with Transductive Transfer Learning
1 Introduction
2 Preliminaries
3 ARFT Design
3.1 Generate Candidate Set
3.2 Create Source/Target Domain
3.3 Transfer to Target
4 Experiments and Results
4.1 Evaluation Metrics
4.2 Experiment Setup
4.3 Experiment Results
5 Conclusion
References
Vessel Trajectory Segmentation: A Survey
1 Introduction
2 Vessel Trajectory
2.1 AIS Data
2.2 Vessel Trajectory Segmentation
3 Supervised Vessel Trajectory Segmentation Method
3.1 Threshold-Based Segmentation
3.2 Trajectory Semantic-Based Segmentation
4 Unsupervised Vessel Trajectory Segmentation Method
4.1 Clustering-Based Segmentation
4.2 Heuristic-Based Segmentation
5 Applications
6 Challenges and Future Directions
7 Conclution
References
Deep Normalization Cross-Modal Retrieval for Trajectory and Image Matching
1 Introduction
2 Related Work
2.1 Cross-Modal Hashing
2.2 Trajectory Feature Learning
3 Preliminary
3.1 Notation
3.2 Problem Definition
4 Proposed Model
4.1 Feature Extraction
4.2 Hash Representation Normalization
4.3 Loss Function
4.4 Out-of-Sample Extension
5 Experiment
5.1 Dataset
5.2 Evaluation Metric
5.3 Baselines
5.4 Result Comparison
6 Conclusion
References
C3BR: Category-Aware Cross-View Contrastive Learning Framework for Bundle Recommendation
1 Introduction
2 Methodology
2.1 Problem Definition
2.2 Representation Learning Module
2.3 Cross-View Contrastive Learning
2.4 Predict&Train
3 Experiments
3.1 Experiment Setting
3.2 Results
4 Related Work
5 Conclusion
References
GDMA
Threat Action Extraction Based on Coreference Resolution
1 Introduction
2 Related Work
2.1 Threat Information Extraction
2.2 Coreference Resolution
3 Approach
3.1 Coreference Resolution
3.2 Threat Action Extraction
4 Experiment
4.1 Experiment Setup
4.2 Evaluation Metrics
4.3 Results and Analysis
5 Conclusion
References
An Improved Method for Constructing Domain-Agnostic Knowledge Graphs
1 Introduction
2 Related Work
2.1 Pipeline-Based Approaches for KGC
2.2 Joint Learning-Based Approaches for KGC
3 Proposed Method
3.1 Overview
3.2 Coreference Resolution
3.3 End-to-End Model
4 Experiments
4.1 Experimental Settings
4.2 Evaluation Metrics
4.3 Results and Analysis
5 Conclusion
References
Zero-Shot Entity Typing in Knowledge Graphs
1 Introduction
2 Related Work
2.1 Entity Typing
2.2 Zero-Shot KG Completion
3 Background
4 Our Method
4.1 Feature Encoder
4.2 Semantic Encoder
4.3 Generative Adversarial Model
5 Experiments
5.1 Datasets
5.2 Ontological Knowledge
5.3 Baselines
5.4 Main Results
5.5 Long-Tail Results
6 Conclusion
References
Causal MRC: Mitigating Position Bias Based on Causal Graph
1 Introduction
2 Related Work
2.1 Extractive Machine Reading Comprehension
2.2 Causal Inference
3 Causal Inference for MRC
3.1 Causal Graph
3.2 Counterfactual Explanations
3.3 Causal Effects
4 Causal MRC Model
4.1 Parameterization
4.2 Ensemble Strategies
4.3 Training
4.4 Inference
5 Experiments
5.1 Datasets and Settings
5.2 Effects of Debiasing Methods
5.3 Visualization Analysis
5.4 Generalization Experiments
6 Conclusion
References
Construct Fine-Grained Geospatial Knowledge Graph
1 Introduction
2 Related Work
3 Problem Definitions
4 Constructing Fine-Grained Geospatial Knowledge Graph
4.1 Baseline Geospatial Interlinking Algorithms
4.2 Fast Geospatial Interlinking Algorithm
5 Experiments
5.1 Experiments of Geospatial Interlinking Algorithms
5.2 Experiments of Spatial Queries on FineGeoKG
6 Conclusions
References
A Multi-view Graph Learning Approach for Host-Based Malicious Behavior Detection
1 Introduction
2 Related Work
3 Motivation and Definition
4 Model
4.1 Overall Architecture
4.2 Host-Based Behavior Dependency Graph
4.3 Multi-view Graph Learning Approach
5 Experiments
5.1 Datasets
5.2 Metric
5.3 Baseline
5.4 Experimental Results
6 Conclusion
References
CECR: Collaborative Semantic Reasoning on the Cloud and Edge
1 Introduction
2 System Overview
2.1 System Architecture
2.2 Cloud Center
2.3 Edge Node
2.4 Query-Driven Backward Reasoning Optimization Algorithm
3 Experiment
3.1 Experimental Setup
3.2 Evaluation Metrics
3.3 Competing Models
3.4 Experiment Results
4 Conclusion
References
Data-Augmented Counterfactual Learning for Bundle Recommendation
1 Introduction
2 Related Works
3 Preliminary
3.1 Task Definition
3.2 A Unified Framework
4 Methodology
4.1 Counterfactual Data Augmentation
4.2 Counterfactual Constraint
5 Further Discussion
6 Experiments
6.1 Experimental Setup
6.2 Overall Comparison (RQ1)
6.3 Ablation Study (RQ2)
6.4 Hyper-Parameters Study (RQ3)
6.5 Visualization and Analysis
7 Conclusion
References
Multi-domain Fake News Detection with Fuzzy Labels
1 Introduction
2 Related Work
2.1 Fake News Detection
2.2 Multi-domain (Multi-task) Learning
3 Approach
3.1 BERT Encoder
3.2 Fuzzy Mechanism
3.3 Domain-Wise Attention
3.4 Mixture-of-Expert Part
3.5 Attention Gate
3.6 Combination
3.7 Prediction
4 Experiment Design
4.1 Dataset
4.2 Metric
4.3 Experiment Setting
4.4 Baselines
4.5 Implementation and Availability
5 Experimental Result
5.1 Compared with Baselines
5.2 Ablation Study
6 Conclusion
References
Correction to: Auto-TSA: An Automatic Time Series Analysis System Based on  Meta-learning
Correction to: Chapter “Auto-TSA: An Automatic Time Series Analysis System Based on Meta-learning” in: A. El Abbadi et al. (Eds.): Database Systems for Advanced Applications. DASFAA 2023 International Workshops, LNCS 13922, https://doi.org/10.1007/978-3-031-35415-1_10
Author Index