Big Data: 11th CCF Conference, BigData 2023, Nanjing, China, September 8–10, 2023, Proceedings (Communications in Computer and Information Science)

This book constitutes the refereed proceedings of the 11th CCF Conference on BigData 2023, which took place in Nanjing, China, in September 2023. The 14 full papers presented in this volume were carefully reviewed and selected from 69 submissions. The topics of accepted papers include theories and methods of data science, algorithms and applications of big data. Preface Organization Contents Long-Term and Short-Term Perception in Knowledge Tracing 1 Introduction 2 Related Work 2.1 Knowledge Tracing 2.2 Recent Advances in MLP 3 Question Definition 3.1 Concepts and Data Representation 3.2 Interaction Record Representation 3.3 Objective of Knowledge Tracing 4 Method 4.1 2PL-IRT Based Embedding Layer 4.2 Long-Term and Short-Term Perception Layer 4.3 Response Prediction Layer 5 Experiments 5.1 Datasets 5.2 Baselines 5.3 Experimental Setup 5.4 Experimental Results 5.5 Ablation Study 5.6 Hyper-parameters Analysis 6 Conclusion and Future Work References A Transfer Learning Enhanced Decomposition-Based Hybrid Framework for Forecasting Multiple Time-Series 1 Introduction 2 Method 2.1 Datasets 2.2 The Framework of Proposed Method 2.3 Baselines 2.4 Proposed Transfer Learning Strategy 2.5 Evaluation Metrics 3 Results and Discussion 3.1 Experimental Settings 3.2 Comparison of Time-Series and Its Sub-sequences 3.3 Comparison of Sub-ARIMA Models 3.4 Comparison of MVMD-Hybrid Framework 4 Conclusion References Dataset Search over Integrated Metadata from China's Public Data Open Platforms 1 Introduction 2 Crawling and Integration of Dataset Metadata 2.1 Crawling of Dataset Metadata 2.2 Integration of Dataset Metadata 3 Dataset Search over Integrated Metadata 3.1 Keyword-Based Retrieval 3.2 Diversity-Based Re-ranking 3.3 Attribute-Based Filtering 4 Experiments 4.1 Keyword-Based Retrieval 4.2 Diversity-Based Re-ranking 4.3 Data Catalog Consolidation 5 Related Work 5.1 National PDOPs in Other Countries 5.2 Dataset Search 6 Conclusion and Future Work References Integrating DCNNs with Genetic Algorithm for Diabetic Retinopathy Classification 1 Introduction 2 Related Work 2.1 Single CNN for DR Classification 2.2 Multiple CNNs for DR Classification 3 Methodology 3.1 Overview of GA-DCNN 3.2 GCA-SA Module 3.3 The Strategy of Integrating DCNNs with GA 4 Experiment Results 4.1 Dataset 4.2 Evaluation Metrics 4.3 Results and Analysis 5 Conclusion References The Convolutional Neural Network Combing Feature-Aligned and Attention Pyramid for Fine-Grained Visual Classification 1 Introduction 2 Related Work 2.1 Methods Using Multi-scale Information 2.2 Methods Using Attention Mechanisms 3 The Convolutional Neural Network Combing Feature-Aligned and Attention Pyramid 3.1 Bottom-Up Multi-scale Feature Module 3.2 Top-Down Attention Module 3.3 ROI Feature Refinement 4 Experimental Results and Analysis 4.1 Model Implementation Details 4.2 Comparison with State-of-the-art Methods 4.3 Ablation Studies 4.4 Visualization 5 Conclusion References OCWYOLO: A Road Depression Detection Method 1 Introduction 2 Related Work 2.1 Object Detection Method 2.2 Intersection Over Union 2.3 Dynamic Weight Networks 2.4 Attention Mechanism 3 Methods 3.1 Network Architecture 3.2 Loss Function Optimization 3.3 Attention Mechanism 4 Experiments 4.1 Datasets and Implementation Details 4.2 Comparative Experiments 4.3 Ablation Experiments 4.4 Visualize Results 5 Conclusion References Explicit Exploring Geometric Modality for Shape-Enhanced Single-View 3D Face Reconstruction 1 Introduction 2 Method 2.1 Preliminary: 3DMM and Projection 3 Network 4 Loss Criteria 5 Experiments 5.1 Training Details 5.2 3D Face Reconstruction 5.3 3D Face Alignment Results 5.4 Ablation Study 6 Conclusion References Fine Edge and Texture Prior Guided Super Resolution Reconstruction Network 1 Introduction 2 Related Works 2.1 Single Image Super-Resolution 2.2 Prior Information Assisted Image Reconstruction 3 Methodology 3.1 Architecture 3.2 Shallow Feature Extraction Network (SFEN) 3.3 Fine Texture Reconstruction Network (FTRN) 3.4 Fine Edge Reconstruction Network (FERN) 3.5 Image Refinement Network (IRN) 4 Experiments 4.1 Datasets 4.2 Implements Details 4.3 Qualitative Comparisons and Discussion 4.4 Quantitative Comparisons and Discussion 5 Analysis and Discussion 5.1 Effectiveness of the Prior Information 5.2 Study of 6 Conclusion References UD-GCN: Uncertainty-Based Semi-supervised Deep GCN for Imbalanced Node Classification 1 Introduction 1.1 Introduction 2 Methodology 2.1 Adaptive Under-Sampling 2.2 Recursive Optimization for Deep GCN 2.3 Algorithm Formalization 3 Experiments 3.1 Experimental Setup 3.2 Performance Comparison 3.3 Sensitivity to the Number of Model Layers 4 Conclusion References Twin Support Vector Regression with Privileged Information 1 Introduction 2 Related Works 2.1 Support Vector Regression 2.2 Twin Support Vector Regression 3 Twin Support Vector Regression with Privileged Information 4 Experiment 4.1 Datasets and Setting 4.2 Experiments Analysis 4.3 Computing Time 5 Conclusions References Detecting Social Robots Based on Multi-view Graph Transformer 1 Introduction 2 Related Work 3 Methodology 3.1 Topic Graph Construction 3.2 Graph Augmentation 3.3 Mult-view Graph Transformer 3.4 Mult-view Attention 3.5 Training and Optimization 4 Experiments 4.1 Dataset 4.2 Baselines 4.3 Model Architecture Study 5 Conclusion References Scheduling Containerized Workflow in Multi-cluster Kubernetes 1 Introduction 2 Related Work 3 Design 3.1 Scientific Workflow 3.2 Two-Level Scheduling Scheme 3.3 CWC Architecture 3.4 CWS Architecture 3.5 Workflow Injection Module 4 Experimental Evaluation 4.1 Experimental Setup 4.2 Workflow Example 4.3 Results and Analysis 5 Conclusion References A Study of Electricity Theft Detection Method Based on Anomaly Transformer 1 Introduction 2 Characteristic Analysis and Data Expansion 2.1 Data Analysis 2.2 Data Expansion Mechanism 2.3 Feature Analysis 3 Electricity Theft Detection Model 3.1 Electricity Theft Detection Methods 3.2 Electricity Theft Detection Specific Process 4 Experimental Evaluation 4.1 Data Expansion Performance Evaluation 4.2 Dataset Preparation 4.3 Evaluation Metrics 4.4 Model Parameters 4.5 Analysis of Results 5 Conclusion References Application and Research on a Large Model Training Method Based on Instruction Fine-Tuning in Domain-Specific Tasks 1 Introduction 2 Related Work 2.1 LoRA 2.2 P-Tuning 2.3 Freeze Fine-Tuning 3 Methodology 4 Experiment 4.1 Objective 4.2 Dataset 4.3 Fine-Tuning Pre-trained Models 4.4 Experimental Environment 4.5 Experimental Process 5 Experimental Result and Analysis 6 Conclusion References Author Index