Note: Intro -- General Chairs' Preface -- PC Chairs' Preface -- Organization Committee -- Contents - Part II -- Foundations -- Text2Chart: A Multi-staged Chart Generator from Natural Language Text -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Stage 1: x-Axis and y-Axis Label Entity Recognition -- 3.2 Stage 2: Mapping of x and y Label Entities -- 3.3 Stage 3: Chart Type Prediction -- 4 Experimental Analysis -- 4.1 Dataset Construction -- 4.2 Performance Evaluation -- 4.3 Axis Label Recognition Task -- 4.4 Mapping Task -- 4.5 Chart Type Prediction Task -- 4.6 Overall Performance -- 5 Conclusion -- A Network Architectures -- References -- ENDASh: Embedding Neighbourhood Dissimilarity with Attribute Shuffling for Graph Anomaly Detection -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 3.1 Problem Formulation -- 3.2 Representation Learning via GraphSAGE -- 4 Proposed Methods -- 4.1 Embedding Neighbourhood Dissimilarity -- 4.2 Augmenting Training via Attribute Shuffling -- 4.3 Two Stage Training -- 4.4 Runtime and Scalability -- 5 Experiments -- 5.1 Empirical Performance -- 5.2 Ablation Study -- 5.3 Parameter Analysis -- 6 Conclusion -- References -- Convergence and Applications of ADMM on the Multi-convex Problems -- 1 Introduction -- 2 Related Work -- 3 ADMM on the Multi-convex Problems -- 3.1 Preliminaries -- 3.2 The ADMM Algorithm -- 3.3 Convergence Analysis -- 4 Applications -- 4.1 Weakly-Constrained Multi-task Learning -- 4.2 Learning with Signed-Network Constraints -- 5 Experiments -- 5.1 Experiment I: Weak-Constrained Multi-task Learning -- 5.2 Experiment II: Event Forecasting with Multi-lingual Indicators -- 6 Conclusions -- References -- Prototypical Classifier for Robust Class-Imbalanced Learning -- 1 Introduction -- 2 Related Work -- 3 Prototypical Classifier with Dynamic Threshold -- 3.1 Motivation. , 3.2 Dynamic Thresholding for Label Noise Detection -- 3.3 Example Reweighting -- 4 Experiments -- 4.1 Results on Simulated Datasets -- 4.2 Results on Real-World Dataset -- 4.3 Ablation Studies -- 5 Conclusion -- A Ablations on Dynamic Threshold -- B Results on Clean Datasets -- References -- Quantum Entanglement Inspired Correlation Learning for Classification -- 1 Introduction -- 2 Theoretical Analysis and Verification by Bell Inequality -- 2.1 The Measurement on Density Matrix -- 2.2 Verification by Bell Inequality -- 2.3 Analysis -- 3 Implement Classification Algorithm by the Framework -- 3.1 Calculate Joint Probability Between Features and Categories -- 3.2 Constructing QECA by Quantum Joint Probability -- 3.3 Parameter Learning -- 4 Experiments -- 4.1 Datasets and Evaluation Metrics -- 4.2 Compared with Classical Classification Algorithms -- 4.3 Comparison with the Training Process of Standard MLP -- 5 Conclusion and Future Work -- References -- Self-paced Safe Co-training for Regression -- 1 Introduction -- 2 Related Work -- 3 The Proposed Algorithm -- 3.1 The Model -- 3.2 The Safe Technique -- 3.3 The Instances Selection Strategy -- 3.4 Algorithm Description -- 4 Experiments -- 4.1 Experiment Settings -- 4.2 The Effectiveness of the Safe Strategy -- 4.3 Comparison with Semi-supervised Methods -- 5 Conclusion and Future Work -- References -- Uniform Evaluation of Properties in Activity Recognition -- 1 Introduction -- 2 Preliminaries and Related Work -- 3 Proposed Metric -- 4 Experimental Results -- 5 Conclusions -- References -- Effect of Different Encodings and Distance Functions on Quantum Instance-Based Classifiers -- 1 Introduction -- 2 Related Works -- 3 Setting the Stage -- 4 Quantum KNN Algorithms -- 5 Experiments -- 6 Conclusion -- References -- Attention-to-Embedding Framework for Multi-instance Learning -- 1 Introduction. , 2 Related Work -- 2.1 MIL Attention Neural Networks -- 2.2 MIL Embedding Methods -- 3 Methodology -- 3.1 The Attention-Net -- 3.2 The Bag-Level Embedding -- 3.3 Scheme Analysis -- 4 Experiments -- 4.1 Data Sets -- 4.2 Comparative Algorithms -- 4.3 Experimental Results -- 5 Conclusion and Further Work -- References -- Multi-instance Embedding Learning Through High-level Instance Selection -- 1 Introduction -- 2 Related Work -- 3 The Proposed Algorithm -- 3.1 Algorithm Description -- 3.2 The Fast Bag-Inside Instance Selection Technique -- 3.3 High-level Instance Selection Technique -- 3.4 Embedding Technique via HI -- 4 Experiments -- 4.1 Comparison Algorithms -- 4.2 Experimental Data Sets -- 4.3 Performance Comparison -- 4.4 Parameter Analysis -- 4.5 Efficiency Comparison -- 5 Conclusion -- References -- High Average-Utility Itemset Sampling Under Length Constraints -- 1 Introduction -- 2 Related Works -- 3 Preliminaries and Problem Formulation -- 4 Two-Phase Sampling of High Average-Utility Itemsets -- 4.1 Basics of Our Sampling Method -- 4.2 HAISampler: High Average-utility Itemset Sampler Algorithm -- 5 Theoretical Analysis of the Method -- 6 Experiments -- 7 Conclusion -- A Appendix (Proof of Theoretical Results) -- References -- Divide and Imitate: Multi-cluster Identification and Mitigation of Selection Bias -- 1 Introduction -- 2 Problem Statement -- 3 Related Work -- 4 Proposed Method -- 5 Experiments and Discussion -- 6 Conclusion -- References -- Hypersphere Neighborhood Rough Set for Rapid Attribute Reduction -- 1 Introduction -- 2 Preliminaries -- 2.1 Neighborhood Rough Set -- 2.2 Hypersphere -- 3 Hypersphere Neighborhood Rough Set -- 3.1 Theory and Mathematical Models -- 3.2 Algorithm Design -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Effectiveness -- 4.3 Efficiency -- 5 Conclusion -- References. , A Novel Clustering Algorithm with Dynamic Boundary Extraction Strategy Based on Local Gravitation -- 1 Introduction -- 2 Natural Neighbor -- 3 Methodology -- 3.1 Dynamic Boundary Extraction -- 3.2 Association Strategy -- 3.3 Core Group Clustering -- 3.4 The Complexity Analysis -- 4 Experimental Evaluation -- 4.1 Experiment on Synthetic Datasets -- 4.2 Experiment on Real-World Datasets -- 5 Conclusions -- References -- Modelling Zeros in Blockmodelling -- 1 Introduction -- 2 Blockmodelling with a Chosen Block Metric -- 2.1 Blockmodelling Metric -- 2.2 Candidate Block Metrics -- 2.3 Effect of Blockmodelling Metric on Real Data -- 3 Simulated Data with Hamming and Jaccard Noise -- 3.1 Simulated Block Structures -- 3.2 Generating Noise -- 3.3 Analysis of Simulated Data -- 4 Discussion -- 5 Conclusion -- References -- Towards Better Generalization for Neural Network-Based SAT Solvers -- 1 Introduction -- 2 Background and Related Works -- 2.1 SAT Problem -- 2.2 Neural Network Based SAT Solvers -- 2.3 SAT Applications -- 3 Method -- 4 Experiments -- 4.1 Setting -- 4.2 Results -- 4.3 Influence of Temperature Scaling Factor -- 5 Case Study-Circuit Design Evaluation -- 6 Conclusion and Discussion -- References -- Robust and Provable Guarantees for Sparse Random Embeddings -- 1 Introduction -- 1.1 Background: Random Embeddings -- 1.2 Contributions -- 1.3 Related Work -- 2 Robust Guarantees for Sparse Random Projections -- 2.1 Preliminaries and Notation -- 2.2 Construction of the Embeddings -- 2.3 Key Techniques for the Analysis -- 2.4 Bounds Based on Error Moments -- 2.5 Discussion -- 3 Empirical Evaluation -- 3.1 Synthetic Benchmark -- 3.2 Real-World Datasets -- 4 Conclusions -- References -- Transferable Interpolated Adversarial Attack with Random-Layer Mixup -- 1 Introduction -- 2 Related Work -- 2.1 Mixup -- 2.2 Adversarial Attack Methods -- 3 Methodology. , 3.1 Random-Layer Mixup Attack Method Without Momentum -- 3.2 Random-Layer Mixup Attack Method -- 4 Experiments -- 4.1 Experiment Setup -- 4.2 Attacking Performance -- 4.3 Analysis of Random-Layer Mixup -- 4.4 Single Iterations vs. Inner-outer Iterations -- 5 Conclusion -- References -- Deep Depression Prediction on Longitudinal Data via Joint Anomaly Ranking and Classification -- 1 Introduction -- 2 Related Work -- 3 Multi-task Recurrent Neural Networks -- 3.1 The Proposed Framework -- 3.2 Primary Task: Depression Classification -- 3.3 Auxiliary Tasks -- 3.4 Data Augmentation -- 3.5 The Algorithm of MTNet -- 4 Experiments -- 4.1 Datasets -- 4.2 Experimental Setup -- 4.3 Implementation Details -- 4.4 Performance Evaluation Measures -- 4.5 Empirical Results -- 5 Conclusions and Future Work -- References -- DeepPAMM: Deep Piecewise Exponential Additive Mixed Models for Complex Hazard Structures in Survival Analysis -- 1 Introduction -- 2 Related Literature -- 2.1 Piecewise Exponential Additive Models and Cox Proportional Hazard Models -- 2.2 Machine Learning Approaches -- 2.3 Deep Learning Approaches -- 3 Piecewise Exponential Additive Models -- 3.1 Data Transformation -- 3.2 Model Estimation -- 4 Deep Piecewise Exponential Additive Mixed Models -- 5 Numerical Experiments -- 5.1 Simulation and Ablation Study -- 5.2 Benchmark Analysis -- 5.3 Extended Case Study -- 6 Concluding Remarks -- References -- Assessing Classifier Fairness with Collider Bias -- 1 Introduction -- 2 Background -- 3 Problem Definition -- 4 Estimating CDE -- 5 Implementing Unbiased Situation Test -- 6 Experiments -- 6.1 Correcting Collider Biases -- 6.2 Simulating an Audit Process Using Adult Data Set -- 6.3 Comparing the Audit Performance of NST and UST -- 6.4 Data Based Audit May Be Biased -- 6.5 Rank Models Based on Fairness -- 7 Related Works -- 8 Conclusions. , A Additional Definition and Theorem.

Note: Intro -- Surface Plasmon Resonance in Bioanalysis -- Copyright -- Contents -- Contributors to Volume 95 -- Preface -- Series editor´s preface -- Chapter One: Surface plasmon resonance sensing in cell biology and drug discovery -- 1. Introduction -- 2. Typical SPR sensing techniques in bioanalysis -- 3. Application of SPR sensing techniques in cell biology and drug discovery -- 3.1. Application of cSPR in cell biology and drug discovery -- 3.1.1. Viral and bacterial detection -- 3.1.2. Stem cells research -- 3.1.3. Cancer research -- 3.1.4. T cell based therapy and diagnosis -- 3.1.5. Drug screening and efficacy evaluation -- 3.1.6. Distribution and interaction kinetics of drug targets -- 3.1.7. Herbal medicine research -- 3.2. Application of SPRi in cell biology and drug discovery -- 3.2.1. Cell morphology study -- 3.2.2. Cell-extracellular matrix (ECM) interactions -- 3.2.3. Cellular mass density measurements -- 3.2.4. Extracellular vesicles detection -- 3.2.5. Stem cells research -- 3.2.6. Cancer research -- 3.2.7. Blood group detection -- 3.2.8. Allergic disease diagnosis -- 3.2.9. Distribution and interaction kinetics of drug targets -- 3.2.10. Drug delivery -- 3.2.11. Other applications -- 3.3. Application of SPRM in cell biology and drug discovery -- 3.3.1. Cell morphology study -- 3.3.2. Cell-ECM interactions -- 3.3.3. Cellular mass density measurements -- 3.3.4. Cell-substrate distance measurement -- 3.3.5. Subcellular activities -- 3.3.6. DNA molecular imaging -- 3.3.7. Binding kinetics detection -- 3.3.8. Extracellular vesicles detection -- 3.3.9. Viral and bacterial detection -- 3.3.10. Drug screening and efficacy evaluation -- 3.4. Other SPR devices and their applications in cell biology and drug discovery -- 3.4.1. Plasmonic scattering microscopy (PSM) -- 3.4.2. Plasmonic-based electrochemical impedance imaging technique (P-EIM). , 3.4.3. Interferometric plasmonic microscopy (iPM) -- 3.4.4. Spatially switched SPM (ssSPM) -- 3.4.5. Wavelength-scanning surface plasmon resonance microscope (WS-SPRM) -- 3.4.6. Surface plasmon resonance with arrays of nanostructures -- 4. Outlook -- References -- Chapter Two: Phase-sensitive surface plasmon resonance sensors for highly sensitive bioanalysis -- 1. Introduction -- 2. Principle of phase-sensitive SPR biosensors -- 2.1. Schematic of the model -- 2.2. Simulation analysis -- 2.2.1. Comparison between amplitude-sensitive and phase-sensitive SPR sensors -- 2.2.2. Effect of model parameters on SPR sensors -- 2.2.3. Sample system analysis -- 2.2.4. Resolution calculation -- 3. Phase interrogation methods for SPR biosensors -- 3.1. Heterodyne detection -- 3.1.1. Optical configurations -- 3.1.2. Bioanalysis applications -- 3.2. Ellipsometry -- 3.2.1. Optical configurations -- 3.2.2. Bioanalysis applications -- 3.3. Interferometry -- 3.3.1. Shear interferometry -- 3.3.2. Spatial phase modulation interferometry -- 3.3.3. Temporal phase modulation interferometry -- 4. Prospects -- 4.1. Sensitivity enhancement -- 4.2. Dynamic range expansion -- 4.3. Spatial resolution improvement -- 4.4. Portable and miniaturized design -- 5. Conclusion -- References -- Chapter Three: Surface plasmon resonance coupled to mass spectrometry in bioanalysis -- 1. Introduction -- 2. Different approaches for coupling SPR to MS -- 2.1. Off-line coupling approaches -- 2.2. On-line coupling approaches -- 3. Applications of SPR-MS for biomolecular interactions analysis -- 3.1. Protein-protein interactions -- 3.2. Enzyme-substrates/inhibitors interactions -- 3.3. Protein-small molecule interactions -- 3.4. Nucleic acids-protein/nucleic acids interactions -- 4. Perspectives -- Acknowledgement -- References -- Chapter Four: Single-cell plasmonic imaging for activity analysis. , 1. Introduction -- 2. Principles of plasmonic imaging -- 2.1. Surface plasmon resonance -- 2.2. Instrumentations for plasmonic imaging -- 2.2.1. Prism-based SPR imaging -- 2.2.2. Surface plasmon resonance microscopy -- 2.2.3. Scanning localized surface plasmon microscopy -- 2.2.4. Plasmonic-based electrochemical impedance microscopy -- 3. Applications of single-cell plasmonic imaging -- 3.1. Plasmonic imaging of single mammalian cells -- 3.1.1. Detection of biomolecular binding -- 3.1.2. Probing cell signalling process -- 3.1.3. Visualization of cellular electrical activity -- 3.1.4. Analysis of cell-substrate interactions -- 3.1.5. Monitoring complex cellular process -- 3.2. Plasmonic imaging of single bacterial cells -- 3.2.1. Quantification of biomolecular binding -- 3.2.2. Vibration-based analysis of bacterial viability -- 3.2.3. Measurement of bacterial adhesion strength -- 4. Conclusions and outlook -- References -- Chapter Five: SPR for water pollutant detection and water process analysis -- 1. Introduction -- 1.1. SPR -- 1.1.1. SPR principle -- 1.1.2. Localized SPR (LSPR) and long-range SPR (LRSPR) -- 1.2. Ligand immobilization -- 1.2.1. Physical adsorption -- 1.2.2. Thiol binding -- 1.2.3. Covalent immobilization -- 1.2.4. Capture method -- 1.2.5. Polymer film deposition -- 2. Pollutant determination -- 2.1. SPR assay formats -- 2.2. Heavy metals determination -- 2.2.1. Alkanethiol SAM-modified chips -- 2.2.2. Biomacromolecule-modified chip -- 2.2.3. Nanomaterial-enhanced chip -- 2.3. Decetion of organic toxic pollutants -- 2.3.1. Pesticides -- 2.3.2. Antibiotics -- 2.3.3. Endocrine disrupting chemicals (EDCs) -- 2.3.4. Polycyclic aromatic hydrocarbons (PAHs) -- 2.4. Counting pathogens -- 2.4.1. Viruses -- 2.4.2. Bacteria -- 3. Monitoring microbial attachment and biofilm development -- 4. Probing of antifouling. , 4.1. Inhibiting macromolecules adsorption -- 4.2. Restraining microbial cell attachment and biofilm growth -- 4.3. Inducing biofilm dispersal -- 5. Exploration of the interaction of microorganisms with toxic substances -- 6. Future work needs -- 6.1. Characterizing pollutant removal -- 6.1.1. Biosorbents development -- 6.1.2. Biosorption and metabolism -- 6.2. SPR imaging -- 6.2.1. Observation of microbial motion -- 6.2.2. High-throughput detection of pollutant -- 6.3. SPR combination with other techniques -- 6.3.1. Improving detection level -- 6.3.2. Investigating composition and morphology changes -- 6.3.3. Extending sensing depth -- 7. Conclusions -- References -- Chapter Six: SPR imaging for cellular analysis and detection -- 1. Introduction -- 2. Mammalian cell analysis -- 2.1. Monitoring of cell behaviours -- 2.1.1. Dynamic interactions of cells on substratum -- 2.1.2. Cellular secretion of molecules -- 2.2. Monitoring of intracellular processes -- 2.2.1. Monitoring of intracellular signal transduction -- 2.2.2. Tracking of single organelle transportation in cells -- 2.3. Detection of allergenic response -- 2.4. Cell surface protein expression and binding kinetics analysis -- 2.4.1. Analysis of cell surface antigens expression -- 2.4.2. Quantification of receptor expression level and receptor-induced response in single living cells -- 2.4.3. Measuring binding kinetics of membrane proteins of single cells -- 2.4.4. Quantitative analysis of drug binding in single cells -- 2.4.5. Measuring binding kinetics of nanoconjugates with intact cells -- 2.5. Direct detection and quantification of cells -- 2.6. Monitoring capture and release of cells -- 2.7. Monitoring, characterization, and analysis of exosomes -- 2.8. Rapid ABO blood typing -- 2.9. Multi-parametric analysis of living cell -- 3. Bacterial cell analysis. , 3.1. Detection and/or identification of bacteria and virus -- 3.1.1. Acidovorax avenae detection in plant samples -- 3.1.2. Detection of Candida albicans from mixed microbes -- 3.1.3. New probes for the identification of closely related bacteria strains -- 3.1.4. On-chip culture for specific detection of low-level bacteria -- 3.1.5. Early detection of Listeria monocytogenes and Listeria innocua based on event counting -- 3.1.6. Detection of Salmonella enteritidis growth under AgNPs -- 3.1.7. Detection of stressed E. coli in food matrices -- 3.1.8. Detection of Cronobacter and Salmonella in powdered infant formula -- 3.1.9. Detection of single viruses -- 3.1.10. Detection of E. coli O157:H7 by a hybrid SPR and molecular imaging device -- 3.1.11. Detection of Legionella pneumophila -- 3.2. Evaluation of biofilm growth and adhesion -- 3.2.1. Imaging of biofilm formation and removal -- 3.2.2. Multiplexed evaluation of bacterial adhesion onto surface coatings -- 3.2.3. Study of Lubricin as a coating to decrease bacterial adhesion and proliferation -- 3.3. Studies of single bacterial cells -- 3.3.1. Imaging of protein interactions with single bacterial cells -- 3.3.2. Antimicrobial susceptibility test and tracking of single bacterial motions -- 3.3.3. Rapid assessment of water toxicity by direct readout of single bacterial activity -- 3.4. Characterization of nanocompartments of bacteria -- 4. Summary -- References -- Chapter Seven: Progress in the applications of surface plasmon resonance for food safety -- 1. Introduction -- 2. SPR for the detection of food allergen -- 2.1. Applications of SPR on detecting food allergen -- 2.1.1. Seafood allergens -- 2.1.2. Peanut allergens -- 2.1.3. Milk allergens -- 2.1.3.1. Detection of casein -- 2.1.3.2. Detection of α-Lac -- 2.1.3.3. Detection of β-lac -- 2.1.3.4. Detection of BSA. , 2.1.3.5. Detection of multiple milk allergens simultaneously.

Note: Intro -- General Chairs' Preface -- PC Chairs' Preface -- Organization Committee -- Contents - Part III -- Applications -- NewsKVQA: Knowledge-Aware News Video Question Answering -- 1 Introduction -- 2 Related Work -- 3 NewsKVQA Dataset Curation -- 3.1 Initial Data Collection -- 3.2 Question Generation -- 3.3 Option Generation -- 3.4 Dataset Analysis -- 4 Knowledge-Aware Video QA Methodology -- 5 Experiments and Results -- 6 Conclusions and Future Work -- References -- Multicommunity Graph Convolution Networks with Decision Fusion for Personalized Recommendation -- 1 Introduction -- 2 Related Work -- 3 The MultiGCN Model -- 3.1 Community Exploration -- 3.2 Local Recommendation -- 3.3 Decision Fusion -- 3.4 Optimization -- 4 Experiments -- 4.1 Experiment Datasets -- 4.2 Experimental Settings -- 4.3 Experiment Results -- 5 Conclusion -- References -- Deep Learning for Prawn Farming -- 1 Introduction -- 2 Related Work -- 3 System Architecture and Overview -- 4 Methods -- 4.1 Forecasting -- 4.2 Anomaly Detection -- 5 Dataset, Preprocessing, and Evaluation -- 6 Forecasting Results -- 7 Anomaly Detection Case Studies -- 7.1 DO Crash Case Study -- 7.2 Sensor Biofouling Case Study -- 8 Summary and Conclusion -- References -- Input Enhanced Logarithmic Factorization Network for CTR Prediction -- 1 Introduction -- 2 Related Work -- 3 Our Approach -- 3.1 Input and Embedding Layer -- 3.2 Input Enhanced Component -- 3.3 Hidden Layers -- 3.4 Prediction Score and Learning -- 3.5 Relationship with FM and HOFM -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Performance Comparison -- 4.3 Hyper-parameter Study -- 4.4 Ablation Study -- 4.5 Component Comparison -- 5 Conclusion -- References -- A Novel Bayesian Deep Learning Approach to the Downscaling of Wind Speed with Uncertainty Quantification -- 1 Introduction -- 2 Problem Formulation and Data Selection. , 2.1 Problem Formulation -- 2.2 Local Wind Data -- 2.3 Reanalysis Data -- 3 Method -- 3.1 Attention-Based Input Grouping -- 3.2 Transformer -- 3.3 Uncertainty Quantification -- 4 Experiments and Results -- 4.1 Experiment Setup -- 4.2 Ablation Studies -- 4.3 Comparative Results -- 5 Conclusions -- References -- Bribery in Rating Systems: A Game-Theoretic Perspective -- 1 Introduction -- 2 Profit Modeling on Data Observation -- 3 Static Game -- 3.1 Best Response -- 4 Conclusion -- References -- IDSGAN: Generative Adversarial Networks for Attack Generation Against Intrusion Detection -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Dataset: NSL-KDD Dataset Description -- 3.2 Data Preprocessing -- 3.3 Structure of IDSGAN -- 4 Empirical Evaluation -- 4.1 Experimental Setup -- 4.2 Effectiveness in Different Attack Categories -- 4.3 Robustness with Different Numbers of Modified Features -- 4.4 Baseline Comparisons -- 5 Conclusion and Future Work -- References -- Recommending Personalized Interventions to Increase Employability of Disabled Jobseekers -- 1 Introduction -- 2 Problem Setup -- 2.1 Preliminaries -- 2.2 Problem Statement -- 3 Method -- 3.1 Overview of the Proposed Method (PIR) -- 3.2 Building a Population Causal Graph -- 3.3 Reverse Engineering Using Linear Interpolation -- 3.4 Building the Prediction Model -- 4 Setup for Empirical Evaluation -- 5 Australian Disability Employment Case Study -- 6 Experiments with Public Datasets -- 7 Practical Implication -- 8 Related Work -- 9 Conclusion and Future Work -- References -- Estimating Skill Proficiency from Resumes -- 1 Introduction -- 2 Related Work -- 3 Problem Definition -- 3.1 Resume Information Model -- 3.2 Skill Proficiency Function -- 4 Skill Proficiency Estimation Techniques -- 4.1 B1: Ordinal Regression Clustering -- 4.2 B2: Supervised Linear Model. , 4.3 M1: Supervised Model with Constraints -- 4.4 M2: Weak Supervision Using Clustering -- 4.5 Handling New Skills -- 5 Resume Information Extraction -- 6 Experimental Analysis -- 6.1 Dataset -- 6.2 Evaluation Metrics and Results -- 7 Conclusions and Further Work -- References -- Causal Enhanced Uplift Model -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 4 Proposed Method -- 5 Experiment -- 5.1 Datasets -- 5.2 Experiment Settings -- 5.3 Experimental Result Analysis -- 6 Conclusion -- References -- An Incentive Dispatch Algorithm for Utilization-Perfect EV Charging Management -- 1 Introduction -- 2 Problem Definition -- 3 The POSIT Framework -- 3.1 Optimal Charging Capacity Estimation -- 3.2 Online Charging Scheduling -- 3.3 Interactive Arrangement Recommendation -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experimental Results -- 5 Related Works -- 6 Conclusions -- References -- A Two-Stage Self-adaptive Model for Passenger Flow Prediction on Schedule-Based Railway System -- 1 Introduction -- 2 Preliminaries -- 3 Stage 1: Next-Day Passenger Flow Prediction Model -- 3.1 Model Inputs Decomposing Component (DC1) -- 3.2 Self-attention-Based Prediction Component -- 3.3 Passenger Flow Reallocation Decomposing Component (DC2) -- 4 Stage 2: Real-Time Fine-Tuning Model -- 4.1 Fast Short-Term Fine-Tuning -- 4.2 Real-Time Adjustment for Interchange and Crowdedness -- 5 Experiments -- 5.1 Experimental Dataset and Setting -- 5.2 Benchmark Methods -- 5.3 The Evaluation of Next-Day Passenger Flow Prediction -- 5.4 The Evaluation of Real-Time Fine-Tuning -- 6 Conclusion -- References -- ToothCR: A Two-Stage Completion and Reconstruction Approach on 3D Dental Model -- 1 Introduction -- 2 Related Work -- 3 Our Approach -- 3.1 Incomplete Dental Model Completion -- 3.2 Surface Reconstruction -- 4 Experiments. , 4.1 Incomplete Dental Model Completion Results -- 4.2 Surface Reconstruction Results -- 5 Conclusion -- References -- BaDumTss: Multi-task Learning for Beatbox Transcription -- 1 Introduction -- 2 Related Work -- 2.1 Automatic Music Transcription -- 2.2 Input Audio Representation -- 2.3 Datasets for AMT -- 3 Proposed Dataset -- 3.1 Beatbox Sample Collection -- 3.2 Data Augmentation -- 3.3 Audio Sequence Generation -- 3.4 User Study on the Generated Audio Sequences -- 4 Proposed Methodology -- 4.1 Pretraining Unit -- 4.2 Bottled Sequence Traversal Unit -- 4.3 Multi-task Autoencoder Unit -- 4.4 Inference-Time MIDI Generation -- 5 Experimental Results -- 6 Error Analysis: BaDumTss vs. BaDumTss-NM -- 7 Conclusion -- References -- Detail Perception Network for Semantic Segmentation in Water Scenes -- 1 Introduction -- 2 Related Work -- 3 Distance Field Loss for Imbalance Problem -- 4 Detail Perception Network -- 4.1 Model Structure -- 4.2 Category Edge Perception Attention Module -- 4.3 Total Loss of DPNet -- 5 Experiments -- 5.1 Datasets -- 5.2 Ablation Study -- 5.3 Comparison with State-of-the-Arts -- 6 Conclusion -- References -- Learning Discriminative Representation Base on Attention for Uplift -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 4 Proposed Method -- 4.1 Input Representation -- 4.2 Attention Network -- 4.3 Outcome Prediction Network -- 5 Experiments -- 5.1 Experimental Data -- 5.2 Implementation Details -- 5.3 Comparison Methods -- 5.4 Experimental Results -- 5.5 Effect of Attention Mechanism -- 6 Conclusion -- References -- Mental Health Treatments Using an Explainable Adaptive Clustering Model -- 1 Introduction -- 2 Related Work -- 3 Deep Adaptive Clustering Based on an Explainable Attention Network (EAN) -- 3.1 Psychometric Questionnaires (PQ) -- 3.2 Emotional Lexicon Used to Embed Words in Sentences -- 3.3 Dataset. , 3.4 Developed EANDC Model -- 4 Experimental Analytics -- 5 Conclusion -- References -- S2QL: Retrieval Augmented Zero-Shot Question Answering over Knowledge Graph -- 1 Introduction -- 2 Preliminaries -- 3 Method -- 3.1 The General Pipeline of the KGQA Model -- 3.2 S2QL -- 4 Experiments and Results -- 4.1 Setup -- 4.2 Results -- 4.3 Ablation Study -- 4.4 Case Study -- 5 Related Work -- 6 Conclusions and Future Works -- References -- Improve Chinese Spelling Check by Reevaluation -- 1 Introduction -- 2 Related Work -- 3 The Proposed Approach -- 3.1 Problem -- 3.2 The Pinyin Enhanced BERT -- 3.3 The Reevaluation Strategy -- 3.4 The Filter Guided by the Extended Confusion Set -- 4 Experiments -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Baselines -- 4.4 Main Results -- 5 Ablation Study -- 6 Case Study -- 7 Conclusion -- References -- Extreme Multi-label Classification with Hierarchical Multi-task for Product Attribute Identification -- 1 Introduction -- 2 Related Works -- 2.1 Multi-task Learning -- 2.2 Extreme Multi-label Classification -- 3 Problem Formulation -- 4 The Proposed Model -- 4.1 Contextualized Term Representation -- 4.2 Coarse-Grained Product Classification -- 4.3 Fine-Grained Product Classification -- 4.4 Brand Classification -- 4.5 Loss Function -- 4.6 Online Inference -- 5 Experiments -- 5.1 Dateset -- 5.2 Evaluation Metrics -- 5.3 Main Results -- 5.4 Online A/B Tests -- 5.5 Ablation Studies -- 5.6 Visualization -- 6 Conclusion -- References -- Exploiting Spatial Attention and Contextual Information for Document Image Segmentation -- 1 Introduction -- 2 Related Works -- 3 New Framework for Document Image Segmentation -- 3.1 Feature Extraction Network -- 3.2 Pixel-wise Spatial Attention Module -- 3.3 Contextual Information Integration -- 4 Experimental Results -- 4.1 Implementation Details -- 4.2 Ablation Study. , 4.3 Comparisons Against State-of-the Art Methods.

Note: Intro -- Preface -- Organization -- Contents -- Searching Similar Trajectories Based on Shape -- 1 Introduction -- 2 Preliminaries -- 3 Align-Based Trajectory Match -- 3.1 Trajectory Preprocessing -- 3.2 Align-Based Trajectory Match -- 3.3 Distance Calculation -- 4 Symbolic Trajectory Match -- 4.1 Symbolic Representation for Trajectory -- 4.2 Symbol Distance Calculation -- 4.3 Multiple Balanced Symbol Trajectory -- 4.4 Query Processing -- 5 Experimental Study -- 5.1 Experiment Setup -- 5.2 Experiment Results -- 6 Related Work -- 6.1 Trajectory Similarity Measurement -- 6.2 Symbolic Representation -- 7 Conclusion -- References -- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN -- 1 Introduction -- 2 Related Works -- 2.1 Generative Adversarial Networks -- 2.2 Semantic Discovery for GANs -- 2.3 Disentanglement Learning with Orthogonal Regularization -- 3 Methods -- 3.1 Overview -- 3.2 Layer-Wise Semantic Discovering Model -- 3.3 Orthogonal Jacobian Regularization -- 4 Experiments -- 4.1 Experiment Settings -- 4.2 Non-trivial Visual Effects -- 4.3 Comparison -- 4.4 Ablation Studies -- 5 Conclusion -- References -- ASNN: Accelerated Searching for Natural Neighbors -- 1 Introduction -- 2 Related Work -- 2.1 K-Nearest Neighbor -- 2.2 Reverse k-Nearest Neighbor -- 2.3 Natural Neighbor -- 3 Proposed Method -- 3.1 Motivation and Theory -- 3.2 Accelerated Search of Natural Neighbors Algorithm -- 3.3 Complexity Analysis -- 4 Experimental Evaluation -- 4.1 Results on Synthetic Datasets -- 4.2 Results on Real-World Datasets -- 5 Conclusions -- References -- A Recommendation Algorithm for Auto Parts Based on Knowledge Graph and Convolutional Neural Network -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Knowledge Graph -- 3.2 KGCNUI Layer -- 3.3 Learning Algorithm -- 4 Experiment -- 4.1 Datasets. , 4.2 Baselines -- 4.3 Experiments Setup -- 4.4 Results -- 5 Conclusion -- References -- Identifying Urban Functional Regions by LDA Topic Model with POI Data -- 1 Introduction -- 2 Related Works -- 3 Region Functions Based on LDA Topic Model -- 3.1 Problem Statement -- 3.2 Embedded Representation of Blocks -- 3.3 Functional Region Identification -- 4 Experiment -- 4.1 Experimental Settings -- 4.2 Experimental Results and Analysis -- 5 Conclusion -- References -- A Data-to-Text Generation Model with Deduplicated Content Planning -- 1 Introduction -- 2 Related Work -- 3 Proposed Model -- 3.1 Word Embedding -- 3.2 Content Planning -- 3.3 Text Generation -- 3.4 Training and Inference -- 4 Experiment -- 4.1 Dataset -- 4.2 Training Configuration -- 5 Conclusion -- References -- Clustering-Enhanced Knowledge Graph Embedding -- 1 Introduction -- 2 Related Work -- 3 Problem Description -- 4 Methodology -- 4.1 KGE Models with Shared Cluster Embeddings -- 4.2 Loss Function -- 5 Experiment -- 5.1 Data Sets -- 5.2 Baseline -- 5.3 Link Prediction -- 5.4 Triplet Classification -- 6 Conclusion -- Appendix A Model parameters -- References -- FCI: Feature Cross and User Interest Network -- 1 Introduction -- 2 Related Work -- 2.1 Feature Cross Mining -- 2.2 User Behavior Sequence Mining -- 3 Our Approach -- 3.1 Problem Statement -- 3.2 Input and Output -- 3.3 Model Structure -- 3.4 Output Layer -- 3.5 Complexity Analysis -- 4 Experiment -- 4.1 Data Set -- 4.2 Evaluation Metrics -- 4.3 Model Training Details -- 4.4 Hyperparameter Settings -- 4.5 Experimental Comparison -- 4.6 Ablation Experiment -- 5 Conclusion -- References -- Author Index.

Note: Intro -- General Chairs' Preface -- PC Chairs' Preface -- Organization Committee -- Contents - Part I -- Contents - Part II -- Contents - Part III -- Data Science -- PGADA: Perturbation-Guided Adversarial Alignment for Few-Shot Learning Under the Support-Query Shift -- 1 Introduction -- 2 Preliminary -- 2.1 Few-shot Learning -- 2.2 The Support-Query Shift and Optimal Transportation -- 3 Methodology -- 3.1 Motivation -- 3.2 Perturbation-Guided Adversarial Alignment (PGADA) -- 3.3 Regularized Optimal Transportation -- 4 Experiment -- 4.1 Experiment Setup -- 4.2 Quantitative Analysis -- 4.3 Ablation Studies -- 5 Related Work -- 6 Conclusion -- References -- Auxiliary Local Variables for Improving Regularization/Prior Approach in Continual Learning -- 1 Introduction -- 2 Related Work and Backgrounds -- 2.1 Related Work -- 2.2 Background -- 3 Improving Regularization/Prior-Based Methods with Auxiliary Local Variables in Continual Learning -- 3.1 Auxiliary Local Variables in Each Neural Network Layer -- 3.2 ALV for Regularization/Prior-Based Methods -- 3.3 Theoretical Analyses -- 4 Experiments -- 4.1 Effectiveness of ALV on Split and Permuted MNIST Datasets -- 4.2 Effectiveness of ALV on Split CIFAR-100 and Split CIFAR-10/100 -- 5 Conclusion -- References -- Emerging Scientific Topic Discovery by Finding Infrequent Synonymous Biterms -- 1 Introduction -- 2 Problem Statement -- 3 Related Work -- 4 The Proposed Method -- 4.1 Document-Level Clustering -- 4.2 Corpus-Level Clustering -- 4.3 The Search Expression Extraction -- 5 Experiments -- 6 Conclusions -- References -- Predicting Abnormal Events in Urban Rail Transit Systems with Multivariate Point Process -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 4 Methodology -- 4.1 Problem Definition -- 4.2 Categorization of Event Pairs -- 4.3 Multivariate Hawkes Process -- 5 Experiments. , 5.1 Experimental Setup -- 5.2 Experimental Results -- 6 Conclusion -- References -- Are Edge Weights in Summary Graphs Useful? - A Comparative Study -- 1 Introduction and Related Works -- 2 Graph Summarization Models -- 2.1 Weighted Graph Summarization Model -- 2.2 Unweighted Graph Summarization Model -- 3 Problem Formulation and Algorithms -- 3.1 Optimization Problem Formulation -- 3.2 Weighted Graph Summarization Algorithms -- 3.3 Unweighted Graph Summarization Algorithms -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Results -- 5 Discussion: Why Can Edge Weights Be Harmful? -- 6 Conclusion and Future Directions -- A Appendix: Graph Algorithms on Summary Graphs -- References -- Mu2ReST: Multi-resolution Recursive Spatio-Temporal Transformer for Long-Term Prediction -- 1 Introduction -- 2 Related Works -- 3 The Proposed Method -- 3.1 Multi-resolution Recursive Prediction -- 3.2 Spatio-Temporal Transformer -- 4 Experiments -- 4.1 Results and Analysis -- 4.2 Ablation Study -- 4.3 Further Discussions -- 5 Conclusion -- References -- LCAN: Light Cross-Attention Network for Collaborative Filtering Recommendation -- 1 Introduction -- 2 Related Work -- 2.1 Collaborative Filtering -- 2.2 Graph Neural Networks -- 3 Approach -- 3.1 Embedding Layer -- 3.2 Cross-Attention Layer -- 3.3 Preference Extractor -- 3.4 Fusion Layer -- 3.5 Prediction Layer -- 4 Experiments -- 4.1 Performance Comparison -- 4.2 Ablation Experiments -- 4.3 Hyper-Parameter Studies -- 5 Conclusion -- References -- Coded Hate Speech Detection via Contextual Information -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Coded Word Representation -- 3.2 Transformation Layers -- 3.3 Coded Hate Speech Detection -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experimental Results -- 5 Conclusion -- References. , Reducing Catastrophic Forgetting in Neural Networks via Gaussian Mixture Approximation -- 1 Introduction -- 2 Backgrounds -- 2.1 Bayesian Inference -- 2.2 Bayesian Approach in Continual Learning -- 2.3 Gumbel Softmax and Categorical Reparameterization -- 3 Gaussian Mixture Approximation in Bayesian Inference for Continual Learning -- 3.1 Proposed Method -- 3.2 Dimension Reduction via Neural Matrix Factorization -- 4 Experiments -- 4.1 Task-Incremental with Multi-head Architecture -- 4.2 Task-Incremental with Single-Head Architecture -- 4.3 Task-Incremental with Data Overlapping -- 4.4 Additional Experiments About Dimension Reduction -- 5 Conclusion and Future Work -- References -- A Novel Semi-supervised Neural Network for Recognizing Parkinson's Disease -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 The Addition of Classifier -- 3.2 Progressive Network -- 3.3 Manifold Regularization and Use of Generated Samples -- 4 Experiments and Results -- 4.1 Dataset -- 4.2 Experimental Settings -- 4.3 Comparison Methods -- 4.4 Experimental Results and Analysis -- 4.5 Parameters Sensitivity Analysis -- 5 Conclusion and Future Work -- References -- ADAM: An Attentional Data Augmentation Method for Extreme Multi-label Text Classification -- 1 Introduction -- 2 Related Work -- 2.1 Extreme Multi-label Text Classification -- 2.2 Data Augmentation in NLP -- 3 Method -- 3.1 Notations -- 3.2 Relevance Learning -- 3.3 Segments Memory Construction -- 3.4 Segments Replacement -- 4 Experiment -- 4.1 Datasets -- 4.2 Evaluation Measures -- 4.3 Baseline -- 4.4 Experiment Details -- 4.5 Comparison Results and Discussion -- 4.6 Analysis of Different Segment Numbers -- 4.7 Analysis of Maximum Number of Replacements -- 4.8 Analysis of Long Tail Labels -- 4.9 Effectiveness of Data Augmentaion -- 5 Conclusion -- References. , AutoTransformer: Automatic Transformer Architecture Design for Time Series Classification -- 1 Introduction -- 2 Relate Work -- 3 Methodology -- 3.1 Time Series Classification Search Space -- 3.2 Optimization Procedure -- 4 Experiments -- 4.1 Experiment Setup and Details -- 4.2 Overall Results -- 4.3 Case Study -- 4.4 Ablation Studies -- 5 Conclusion -- References -- Aspect-Based Sentiment Analysis Through EDU-Level Attentions -- 1 Introduction -- 2 Related Work -- 3 The Proposed Model: EDU-Attention -- 3.1 Model Overview -- 3.2 EDU Representation -- 3.3 Sentence Representation and Learning Objective -- 4 Experiments -- 4.1 Datasets and Baselines -- 4.2 Implementation and Parameter Setting -- 4.3 Comparison with Baselines -- 4.4 Ablation Study -- 4.5 Analysis of Sparse Attention -- 4.6 Model Size and Inference Time -- 5 Conclusion -- References -- Interconnected Neural Linear Contextual Bandits with UCB Exploration -- 1 Introduction -- 2 Related Work -- 3 Problem Formulation and Background -- 4 The Interconnected Neural-Linear UCB Framework -- 5 Regret Analysis -- 6 Experiments -- 6.1 Experimental Setting -- 6.2 Results -- 7 Conclusion -- References -- Node Information Awareness Pooling for Graph Representation Learning -- 1 Introduction -- 2 Preliminaries -- 2.1 Notations and Problem Formulation -- 2.2 Graph Convolutional Neural Network -- 2.3 Self-attention Mechanism -- 3 NIAPool (Proposed Method) -- 3.1 Local Node Information Enhancement -- 3.2 Global Node Scoring Using NFAConv -- 3.3 Graph Coarsening -- 3.4 Model Architecture -- 4 Experiments -- 4.1 Experimental Setting -- 4.2 Q1: Comparison with Baseline Models -- 4.3 Q2: Effectiveness of D2T Attention -- 4.4 Q3: Effectiveness of NFAConv -- 5 Conclusion -- References -- dK-Personalization: Publishing Network Statistics with Personalized Differential Privacy -- 1 Introduction -- 2 Related Work. , 3 Problem Formulation -- 4 Sensitivity Analysis -- 5 Proposed Approaches -- 5.1 Local Least Based Personalized Perturbation -- 5.2 Threshold Projection Based Personalized Perturbation -- 5.3 Sampling Based Personalized Perturbation -- 5.4 Aggregation Based Personalized Perturbation -- 6 Experiments -- 6.1 Experimental Setup -- 6.2 Results and Discussion -- 7 Conclusions and Future Work -- References -- Residual Vector Product Quantization for Approximate Nearest Neighbor Search -- 1 Introduction -- 2 Related Work -- 3 Residual Vector Product Quantization -- 3.1 Learning for Residual Hierarchy Structure -- 3.2 Encoding Algorithm -- 3.3 Learning for Transformation Matrix R -- 4 Experiment Results and Analysis -- 4.1 Parameters Setting for RVPQ -- 4.2 Comparison of Encoding Algorithms -- 4.3 Exhaustive ANN Search -- 4.4 Non Exhaustive Search Based on Inverted Multi-index -- 5 Conclusion -- References -- Data Removal from an AUC Optimization Model -- 1 Introduction -- 2 Preliminaries -- 3 Data Removal for AUC Optimization -- 3.1 Deal with High Dimension -- 4 Theoretical Results -- 5 Experiment -- 5.1 Benchmark Results -- 5.2 High-Dimensional Results -- 6 Conclusion -- A Analysis of DRAUC with High-Dimensional Data -- References -- Distributed Differentially Private Ranking Aggregation -- 1 Introduction -- 2 Preliminaries -- 2.1 Ranking Aggregation -- 2.2 Differential Privacy -- 2.3 Shuffle Model -- 3 Ranking Aggregation Algorithm Under DDP -- 3.1 Ranking Preference Collection -- 3.2 Shuffling -- 3.3 Ranking Aggregation -- 3.4 Privacy Guarantee -- 4 Experiments -- 4.1 Experiment Settings -- 4.2 Performance of DDP-Helnaksort -- 5 Conclusions -- References -- Semantics-Guided Disentangled Learning for Recommendation -- 1 Introduction -- 2 Preliminary and Related Work -- 3 Methodology -- 3.1 Graph Disentangling for Users Intents. , 3.2 Semantic-Aware Intent Representation Learning.