
Advances in Knowledge Discovery and Data Mining
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This three-volume set, LNAI 10937, 10938, and 10939, constitutes the thoroughly refereed proceedings of the 22nd Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2018, held in Melbourne, VIC, Australia, in June 2018.
The 164 full papers were carefully reviewed and selected from 592 submissions. The volumes present papers focusing on new ideas, original research results and practical development experiences from all KDD related areas, including data mining, data warehousing, machine learning, artificial intelligence, databases, statistics, knowledge engineering, visualization, decision-making systems and the emerging applications.
More details
Other editions
Additional editions

Content
- Intro
- PC Chairs' Preface
- General Chairs' Preface
- Organization
- Contents - Part III
- Feature Learning and Data Mining Process
- Discovering High Utility Itemsets Based on the Artificial Bee Colony Algorithm
- Abstract
- 1 Introduction
- 2 Preliminaries
- 2.1 Problem of HUI Mining
- 2.2 ABC Algorithm
- 3 Mining HUIs Using the ABC
- 3.1 Bitmap Item Information Representation
- 3.2 Modeling HUI Discovery Using the ABC
- 3.3 Direct Nectar Source Generation for Scout Bees
- 3.4 Algorithm Description
- 4 Performance Evaluation
- 4.1 Experimental Environment and Datasets
- 4.2 Running Time
- 4.3 Number of Discovered HUIs
- 4.4 Convergence
- 5 Conclusions
- Acknowledgments
- References
- A Scalable and Efficient Subgroup Blocking Scheme for Multidatabase Record Linkage
- 1 Introduction
- 2 Related Work
- 3 Subgroup Blocking Process
- 3.1 Potential Candidate Grouping
- 3.2 Candidate Graph Construction
- 3.3 Subgroup Candidate Generation
- 4 Analysis of Subgroup Blocking
- 5 Experiments and Discussion
- 6 Conclusions and Future Work
- References
- Efficient Feature Selection Framework for Digital Marketing Applications
- 1 Introduction
- 2 Related Work
- 3 Overall Framework
- 4 Feature Exploration Using Semantic Ranking and Generative Filtering
- 4.1 The Semantic Ranking Guided Feature Selection Algorithm
- 4.2 Combining with Generative Filtering for Better Performance
- 5 Progressive Sampling and Feature Selection Framework
- 5.1 Coarse to Fine Implementation
- 5.2 Time and Space Reduction Through Progressive Sampling
- 6 Experiments and Discussion
- 7 Conclusion
- References
- Dynamic Feature Selection Algorithm Based on Minimum Vertex Cover of Hypergraph
- 1 Introduction
- 2 Preliminaries
- 3 Dynamic Feature Selection Algorithm Based on Minimum Vertex Cover of Hypergraph
- 3.1 The Induced Hypergraph
- 3.2 Updating Minimum Vertex Cover of Hypergraph
- 3.3 Dynamic Feature Selection Algorithm
- 4 Experimental Analysis
- 5 Conclusions
- References
- Feature Selection for Multiclass Binary Data
- 1 Introduction
- 2 Related Work
- 3 Preliminary Concepts
- 4 Problem Formulation
- 5 Our Approach
- 5.1 Measuring the Sparse Value Distribution
- 5.2 New Feature Selection Objective
- 5.3 A Greedy Feature Selection Approach
- 6 Evaluation
- 6.1 Experimental Results
- 6.2 Evaluation Insights
- 7 Conclusion
- References
- Scalable Model-Based Cascaded Imputation of Missing Data
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 4 Methodology
- 5 Discussion of Experimental Results
- 6 Conclusions
- References
- On Reducing Dimensionality of Labeled Data Efficiently
- 1 Introduction
- 2 Related Work
- 2.1 Metric Learning
- 2.2 Nonlinear Algorithms for Collapsing Classes
- 2.3 Parametric Embedding
- 3 Nonlinear Parametric Embedding
- 4 Evaluation
- 4.1 Experiment Settings
- 4.2 Results
- 5 Conclusion
- References
- Using Metric Space Indexing for Complete and Efficient Record Linkage
- 1 Introduction
- 2 Related Work
- 3 Approach
- 4 Experiments and Results
- 4.1 Cora Results
- 4.2 Demographic Dataset Results
- 5 Conclusions and Future Work
- References
- Dimensionality Reduction via Community Detection in Small Sample Datasets
- 1 Introduction
- 2 Related Work
- 3 Proposed Approach
- 4 Experimental Setup and Results
- 4.1 Experimental Setup
- 4.2 Results
- UCI Machine Learning Repository Benchmarks.
- Empirical Evaluation of FeatureNet in the
- Why We Achieve Performance Gains?
- Computational Sustainability - A Case Study and New AI Datasets.
- Note on Scalability.
- 5 Conclusion and Future Work
- References
- An Interaction-Enhanced Feature Selection Algorithm
- 1 Introduction
- 2 Proposed Method for Feature Selection
- 2.1 An Information Measure for Feature Interaction
- 2.2 An Interaction Based Feature Selection Method
- 2.3 Complexity Analysis
- 3 Experiments
- 3.1 Overall Performance
- 3.2 Performance with Respect to the Number of Features
- 4 Discussion and Conclusion
- References
- An Extended Random-Sets Model for Fusion-Based Text Feature Selection
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation and Background
- 3.1 Latent Dirichlet Allocation and Limitations
- 3.2 Extending Random-Sets
- 4 The Proposed SIF2 Model
- 4.1 Fusing Hierarchical Features
- 5 Evaluation
- 5.1 Dataset and Evaluation Measures
- 5.2 Baseline Models and Settings
- 5.3 Experimental Design
- 5.4 Results
- 5.5 Discussion
- 6 Conclusions
- References
- Attribute Reduction Algorithm Based on Improved Information Gain Rate and Ant Colony Optimization
- Abstract
- 1 Introduction
- 2 Preliminary
- 2.1 Rough Set Theory
- 2.2 Information Representation in Decision Table
- 3 Ant Colony Optimization for Attribute Reduction
- 3.1 Ant Colony Optimization Principle
- 3.2 Local Solution
- 3.3 Pheromone Updating
- 3.4 The Proposed Algorithm
- 4 Experimental Analysis
- 4.1 Comparison with Other Methods
- 4.2 Analysis of Convergence Rate
- 5 Conclusion
- Acknowledgements
- References
- Efficient Approximate Algorithms for the Closest Pair Problem in High Dimensional Spaces
- 1 Introduction
- 2 Proposed Approximate Algorithms
- 2.1 ACP-D
- 2.2 ACP-P
- 3 Experiments
- 4 Conclusions
- 4.1 Proof of Theorem1
- 4.2 Proof of Corollary1
- 4.3 Proof of Theorem2
- 4.4 Proof of Corollary2
- References
- Efficient Compression Technique for Sparse Sets
- 1 Introduction
- 1.1 Revisiting Compression Scheme of KulkarniP16
- 1.2 Our Result
- 1.3 Comparison Between BCS and Minhash and Its Variants
- 1.4 Applications of Our Result
- 2 Analysis
- 3 Experimental Evaluation
- 3.1 Results on Synthetic Data
- 3.2 Results on Real-World Data
- 4 Concluding Remarks and Open Questions
- References
- It Pays to Be Certain: Unsupervised Record Linkage via Ambiguity Minimization
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 3.1 Evaluating Record Linkage Scoring
- 4 Our Method
- 4.1 The Scoring Formulation
- 4.2 Developing the Objective Function
- 4.3 Optimization Formulation
- 4.4 Overall Approach
- 5 Experiments and Results
- 5.1 Experimental Setup
- 5.2 Comparative Evaluation of Record Pairs Ordering
- 5.3 Further Analysis of Our Method
- 6 Conclusions
- References
- Community Detection and Network Science
- Consensus Community Detection in Multilayer Networks Using Parameter-Free Graph Pruning
- 1 Introduction
- 2 Background
- 2.1 Generative Models for Graph Pruning
- 2.2 Ensemble-Based Multilayer Community Detection
- 3 EMCD and Parameter-Free Graph Pruning
- 4 Evaluation Methodology
- 5 Results
- 5.1 Impact of Model-Filters on M-EMCD*
- 5.2 Evaluation with Competing Methods
- 6 Conclusion
- References
- Community Discovery Based on Social Relations and Temporal-Spatial Topics in LBSNs
- 1 Introduction
- 2 Related Works
- 3 Community Discovery Model
- 3.1 Preliminaries
- 3.2 Basic Idea of SRTST Model
- 3.3 Model Construction
- 4 Parameter Estimation
- 5 Experiments
- 5.1 LBSN Datasets and Evaluation Metrics
- 5.2 Parameter Configuration
- 5.3 Comparison Algorithms
- 5.4 Experimental Results
- 6 Conclusion
- References
- A Unified Weakly Supervised Framework for Community Detection and Semantic Matching
- 1 Introduction
- 2 Proposed WSCDSM Framework
- 2.1 Modeling TC Communities
- 2.2 Modeling SC Communities
- 2.3 The Unified Model: Matching TC with SC Communities
- 3 Optimization
- 4 Experimental Results
- 4.1 The Performance of Community Detection
- 4.2 The Matching Between Semantic and Communities
- 5 Conclusion
- References
- Tapping Community Memberships and Devising a Novel Homophily Modeling Approach for Trust Prediction
- 1 Introduction
- 2 Related Work
- 3 Inferring Trust Using Community Memberships and Novel Homophily Modeling
- 3.1 Problem Setting
- 3.2 Encoding Community Membership Information for Trust Prediction
- 3.3 Proposed Homophily Modeling Using Users' Item Ratings
- 4 The Overall Optimization Framework
- 4.1 Trust Inference Using the Community-Based Factor
- 4.2 Trust Inference Through Homophily Modeling Using Users' Item Ratings
- 4.3 The chTrust Algorithm
- 5 Experiments
- 5.1 Datasets
- 5.2 Evaluation Metric and Experiment Settings
- 5.3 Baselines
- 5.4 Results
- 6 Conclusion
- References
- Deep Learning Theory and Applications in KDD
- Text-Visualizing Neural Network Model: Understanding Online Financial Textual Data
- 1 Introduction
- 1.1 Motivation and Purpose
- 1.2 Main Approach and Problem Settings
- 2 Importance of Infiltration (II) Algorithm
- 2.1 Setup of NN Model
- 2.2 Initialization and Learning of Parameters
- 2.3 Proposed and Baseline Models
- 3 Text Visualization Demonstration Using Real Data
- 3.1 Dataset and Model Development
- 3.2 Interpretability Evaluation
- 3.3 Clustering Interpretability Evaluation
- 3.4 Market Mood Predictability Evaluation
- 3.5 Text Visualization
- 4 Related Work
- 5 Conclusion
- A Theoretical Analysis of the II Algorithm
- References
- MIDA: Multiple Imputation Using Denoising Autoencoders
- 1 Introduction
- 2 Background
- 2.1 Missing Data
- 2.2 Autoencoders and Denoising Autoencoders
- 3 Models
- 3.1 Our Model
- 3.2 Competitors and Comparison
- 4 Experiments
- 4.1 Datasets
- 4.2 Inducing Missingness
- 4.3 Main Results
- 4.4 Increased Missingness Proportion
- 4.5 Impact on Final Analysis
- 5 Conclusion
- References
- Dual Control Memory Augmented Neural Networks for Treatment Recommendations
- 1 Introduction
- 2 Methods
- 2.1 Problem Formulation
- 2.2 DNC Overview
- 2.3 Proposed Model
- 3 Results
- 3.1 Synthetic Task: Odd-Even Sequence Prediction
- 3.2 Treatment Recommendation Tasks
- 4 Related Works
- 5 Conclusion
- References
- Denoising Time Series Data Using Asymmetric Generative Adversarial Networks
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 4 Asymmetric Generative Adversarial Network
- 4.1 Generator and Discriminator Network Architecture
- 5 Experimental Setup and Results
- 5.1 Synthetic Dataset
- 5.2 EEG Dataset
- 6 Conclusion
- References
- Shared Deep Kernel Learning for Dimensionality Reduction
- 1 Introduction
- 2 Related Works
- 2.1 GP and GPLVM
- 2.2 DKL
- 3 The Proposed Model
- 4 Experiments
- 5 Conclusion
- References
- CDSSD: Refreshing Single Shot Object Detection Using a Conv-Deconv Network
- 1 Introduction
- 2 Limitations of Related Work
- 3 CDSSD Architecture
- 3.1 SSD
- 3.2 Unsupervised Pretraining
- 3.3 Combining Feature Maps
- 3.4 Box Pooling: Reducing the Number of Default Boxes
- 4 Results
- 4.1 Training
- 4.2 PASCAL VOC
- 4.3 Ablation Study
- 4.4 MSCOCO
- 5 Conclusion
- References
- Binary Classification of Sequences Possessing Unilateral Common Factor with AMS and APR
- 1 Introduction
- 2 Related Work
- 3 Our Proposals
- 3.1 Network Architecture and Notations
- 3.2 Adaptive Multi-scale Sampling (AMS)
- 3.3 Activation Pattern Regularization (APR)
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Experiments on Dataset 1
- 4.3 Experiments on Dataset 2
- 4.4 Analyzing AMS and APR
- 5 Conclusion
- References
- Automating Reading Comprehension by Generating Question and Answer Pairs
- 1 Introduction
- 2 Problem Formulation
- 3 Related Work
- 4 Approach and Contributions
- 5 Answer Selection and Encoding
- 5.1 Named Entity Selection
- 5.2 Answer Selection Using Pointer Networks
- 6 Question Generation
- 6.1 Sequence to Sequence Model
- Question Decoder:
- 6.2 Linguistic Features
- 7 Implementation Details
- 8 Experiments and Results
- 8.1 Results and Analysis
- 9 Conclusion
- References
- Emotion Classification with Data Augmentation Using Generative Adversarial Networks
- 1 Introduction
- 2 Related Work
- 2.1 Generative Adversarial Networks
- 2.2 Data Augmentation
- 3 Data Augmentation Using CycleGAN
- 3.1 Cycle-Consistent Adversarial Networks
- 3.2 Class Imbalance and Data Manifold
- 4 Experimental Studies
- 4.1 Benchmark Datasets
- 4.2 Experimental Results
- 5 Conclusions and Discussions
- References
- Trans2Vec: Learning Transaction Embedding via Items and Frequent Itemsets
- 1 Introduction
- 2 Related Work
- 3 Framework
- 3.1 Problem Definition
- 3.2 Learning Transaction Embeddings Based on Items
- 3.3 Learning Transaction Embeddings Based on Frequent Itemsets
- 3.4 Trans2Vec Method for Learning Transaction Embeddings
- 4 Experiments
- 4.1 Datasets
- 4.2 Baselines
- 4.3 Evaluation Metrics
- 4.4 Parameter Settings
- 4.5 Results and Discussion
- 4.6 Parameter Sensitivity
- 5 Conclusion
- References
- Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks
- 1 Introduction
- 2 Complex Sensitive Information Detection
- 3 SPR - Sensitive Phrase Based RNN Model
- 3.1 Phrase Structure
- 3.2 Recursive Neural Networks with Phrase Structure
- 3.3 Training SPR
- 4 Evaluation
- 4.1 Evaluation Methodology and Data
- 4.2 Performance Evaluation for Complex Sensitive Information
- 4.3 Qualitative Analysis
- 5 Related Work
- 6 Conclusion
- References
- Clustering and Unsupervised Learning
- A Distance Scaling Method to Improve Density-Based Clustering
- 1 Introduction
- 2 Related Work
- 3 The Problem of Varied Densities
- 4 A Distance Scaling Method for Density-Ratio Estimation
- 5 Empirical Evaluation
- 5.1 Clustering Performance
- 6 Conclusion
- References
- Neighbourhood Contrast: A Better Means to Detect Clusters Than Density
- 1 Introduction
- 2 Neighbourhood Contrast
- 2.1 Property of Neighbourhood Contrast
- 2.2 Estimating Neighbourhood Contrast
- 3 Improving DP with Neighbourhood Contrast
- 4 Neighbourhood Contrast Clustering
- 4.1 Core Points and Cluster Nexuses
- 4.2 Assigning Non-core Points
- 5 Experiments
- 6 Conclusions
- References
- Clustering of Multiple Density Peaks
- 1 Introduction
- 2 Preliminary Knowledge and Problem Definition
- 2.1 The Algorithm of DPC
- 2.2 The Problems and Related Approaches
- 3 The MDPC Approach
- 3.1 Find Seed Clusters
- 3.2 Merge Seed Clusters
- 3.3 Algorithm Complexity
- 4 Experiments
- 4.1 Synthetic Datasets
- 4.2 Real Datasets
- 5 Conclusion
- References
- A New Local Density for Density Peak Clustering
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 A New Local Density
- 3.2 NDPC Algorithm
- 3.3 NDPC-AC Algorithm
- 4 Experiments
- 4.1 Comparison Scheme
- 4.2 Experimental Results on Benchmark Datasets
- 4.3 Visualization of Experimental Results on ORL Dataset
- 5 Conclusion
- References
- An Efficient Ranking-Centered Density-Based Document Clustering Method
- Abstract
- 1 Introduction
- 2 Ranking-Centered Density Document Clustering (RDDC)
- 2.1 Obtaining Nearest Neighbors as Relevant Documents
- 2.2 Graph Based Clustering
- 2.3 Relevancy Based Clustering
- 3 Empirical Analysis
- 3.1 Accuracy Analysis
- 3.2 Scalability and Complexity Analysis
- 3.3 Sensitivity Analysis
- 4 Conclusion
- References
- Fast Manifold Landmarking Using Locality-Sensitive Hashing
- 1 Introduction
- 2 Background
- 2.1 Landmarking Manifolds with Gaussian Processes
- 2.2 Locality-Sensitive Hashing
- 2.3 Distance-Based Hashing
- 3 LSH for Finding Manifold Landmarks
- 3.1 Manifold Assumption and Locality-Sensitive Hashing
- 3.2 Supervised LSH (LSH-SC)
- 3.3 Supervised DBH (DBH-SC)
- 3.4 Landmark Selection Methods
- 3.5 Complexity Analysis
- 4 Experimental Results
- 4.1 Classification Using Landmark-Based Transformed Features
- 4.2 Impact of Approach Improvements
- 4.3 Qualitative Evaluation
- 4.4 Quantitative Evaluation of Landmark Quality
- 5 Conclusion
- References
- Equitable Conceptual Clustering Using OWA Operator
- 1 Introduction
- 2 Background
- 2.1 Formal Concepts and Conceptual Clustering
- 2.2 Equitable Multiagent Optimization
- 2.3 Equitable Aggregation Functions
- 2.4 Ordered Weighted Averages (OWA)
- 3 ILP Models
- 3.1 OWA ILP Models
- 3.2 Other ILP Models
- 4 Related Work
- 5 Experiments and Results
- 6 Conclusion
- References
- Unsupervised Extremely Randomized Trees
- 1 Introduction and Preliminaries
- 2 Unsupervised Extremely Randomized Trees
- 3 Empirical Evaluation
- 3.1 Optimization of Parameters
- 3.2 Comparative Evaluation of UET
- 4 Conclusion and Perspectives
- References
- Local Graph Clustering by Multi-network Random Walk with Restart
- 1 Introduction
- 2 Related Work
- 3 Problem Definitions
- 4 Methods
- 4.1 Random Walk on Single Network
- 4.2 Random Walk on Multi-network
- 4.3 Localized Algorithm for MRWR
- 5 Experiment
- 5.1 Datasets and Baseline Methods
- 5.2 Effectiveness Evaluation
- 5.3 Efficiency Evaluation
- 6 Conclusion
- References
- Scalable Approximation Algorithm for Graph Summarization
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 4 Algorithm
- 5 Evaluation
- 6 Conclusion
- References
- Privacy-Preserving and Security
- RIPEx: Extracting Malicious IP Addresses from Security Forums Using Cross-Forum Learning
- 1 Introduction
- 2 Our Forums and Datasets
- 3 Overview of RIPEx
- 3.1 The IP Identification Module
- 3.2 The IP Characterization Module
- 3.3 Transfer Learning with Cross-Seeding
- 4 Evaluation of Our Approach
- 5 Related Work
- 6 Conclusion
- References
- Pattern-Mining Based Cryptanalysis of Bloom Filters for Privacy-Preserving Record Linkage
- 1 Introduction
- 2 Background and Related Work
- 3 Pattern-Mining Based Cryptanalysis Attack
- 3.1 Identifying Co-occurring Bit Positions in Bloom Filters
- 3.2 Plain-Text Value Re-identification
- 4 Experiments and Results
- 5 Conclusions and Future Work
- References
- A Privacy Preserving Bayesian Optimization with High Efficiency
- 1 Introduction
- 2 Background
- 2.1 Bayesian Optimization
- 2.2 Differential Privacy
- 3 The Proposed Framework
- 3.1 Error Preserving Privacy Framework
- 3.2 The Proposed Algorithm
- 3.3 Discussion of Differentially Private Bayesian Optimization
- 4 Experiments
- 4.1 Experiment with Benchmark Functions
- 4.2 Experiment with Real Datasets
- 5 Conclusion
- References
- Randomizing SVM Against Adversarial Attacks Under Uncertainty
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 4 Attack Model Design
- 4.1 Restrained Range Attack with Uncertainty
- 4.2 Distributional Range Attack with Uncertainty
- 5 Randomized SVMs Learning
- 5.1 Randomized SVM Against RRA
- 5.2 Randomized SVM Against RRAU
- 5.3 Randomized SVM Against DRAU
- 6 Experimental Evaluation
- 6.1 Comparison with Deterministic SVM-RRA
- 6.2 Comparative Study with Standard SVMs
- 6.3 SVM-DRAU with Different Norms
- 7 Conclusion
- References
- Recommendation and Data Factorization
- One for the Road: Recommending Male Street Attire
- 1 Introduction
- 2 Data Collection
- 2.1 Surveys
- 2.2 Data Statistics and Analysis
- 3 Prediction Model
- 4 Recommendation Model - MalOutRec
- 4.1 Construction of Bipartite Graph
- 4.2 Traversal of the Graph
- 4.3 Refining Recommendation Using Positive Influence Factor
- 5 Experiments
- 5.1 Prediction Accuracy
- 5.2 MalOutRec - Performance Assessment
- 6 Conclusion
- References
- Context-Aware Location Annotation on Mobility Records Through User Grouping
- 1 Introduction
- 2 Preliminary
- 3 Method
- 3.1 Overview of CAUG
- 3.2 User Grouping
- 3.3 Feature Extraction
- 3.4 Venue Ranking
- 4 Experimental Study
- 4.1 Setup
- 4.2 Results
- 5 Related Work
- 6 Conclusion
- References
- A Joint Optimization Approach for Personalized Recommendation Diversification
- 1 Introduction
- 2 Problem Formulation
- 3 Personalized Diversification Algorithms
- 3.1 Personalized Diversification Algorithm by Greedy Re-ranking
- 3.2 Personalized Diversification Algorithm by Joint Optimization
- 4 Personalized Diversity Measure
- 4.1 Limitations of Existing Diversity Measures
- 4.2 Formulation of Personalized Diversity Measure
- 5 Experiments
- 5.1 Experiments on Algorithms
- 5.2 Experiments on Measures
- 6 Related Work
- 7 Conclusion
- References
- Personalized Item-of-Interest Recommendation on Storage Constrained Smartphone Based on Word Embedding Quantization
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 4 The WEQ Framework
- 4.1 Word Embedding Quantization
- 4.2 Bounding Angle Checking Mechanism
- 5 Experiment and Evaluation
- 5.1 Experimental Settings
- 5.2 Performance Results
- 6 Conclusion
- References
- Social Network, Ubiquitous Data and Graph Mining
- Topic-Specific Retweet Count Ranking for Weibo
- 1 Introduction
- 2 Related Work
- 3 TSTR Framework
- 3.1 Consideration and Design
- 3.2 Candidate Tweet Filter
- 3.3 LSTM-AE
- 3.4 DAE
- 3.5 Tweet Ranker
- 3.6 Chinese Word Embedding
- 4 Experiments
- 5 Conclusion
- References
- Motif-Aware Diffusion Network Inference
- 1 Introduction
- 2 Related Work
- 3 Motif-Aware Diffusion Network Inference
- 3.1 Notations and Problem Formulation
- 3.2 Estimating Motif Pattern from Cascade Data
- 3.3 Motif Prior Regularization
- 3.4 Learning
- 3.5 Computational Complexity Analysis
- 4 Validations
- 4.1 Experiments on Synthetic Networks
- 4.2 Experiment on a Real-World Network
- 4.3 Experiment on Real-World Cascades
- 5 Conclusion
- References
- Tri-Fly: Distributed Estimation of Global and Local Triangle Counts in Graph Streams
- 1 Introduction
- 2 Related Work
- 3 Notations and Problem Definition
- 3.1 Notations (Table2)
- 3.2 Problem Definition
- 4 Proposed Method: Tri-Fly
- 4.1 Overview (Fig.1)
- 4.2 Detailed Algorithm (Algorithm1)
- 4.3 Bias and Variance Analyses
- 4.4 Time and Space Complexity Analyses
- 5 Experiments
- 5.1 Experimental Settings
- 5.2 Q1. Illustration of Our Theorems (Fig.2)
- 5.3 Q2. Performance (Fig.3)
- 6 Conclusion
- References
- WFSM-MaxPWS: An Efficient Approach for Mining Weighted Frequent Subgraphs from Edge-Weighted Graph Databases
- 1 Introduction
- 2 Background and Related Works
- 3 Our Proposed Algorithm
- 3.1 WFSM-MaxPWS Canonical Ordering of Subgraph
- 3.2 MaxPWS Pruning Technique
- 3.3 The WFSM-MaxPWS Algorithm
- 4 Experimental Results
- 5 Conclusions
- References
- A Game-Theoretic Adversarial Approach to Dynamic Network Prediction
- 1 Introduction
- 2 Related Work
- 3 Adversarial Dynamic Network Prediction
- 3.1 Adversarial Prediction Formulation
- 3.2 Performance Guarantees and Features
- 3.3 Relationship with TERGMs
- 4 Experiments
- 5 Conclusions
- References
- Targeted Influence Minimization in Social Networks
- 1 Introduction
- 2 Problem Definition
- 2.1 Diffusion Model
- 2.2 Targeted Influence Minimization
- 3 Budget Unconstrained Solution
- 4 Budget Constrained Solution
- 5 Sampling-Based Solution
- 5.1 Minimum Influence Path
- 5.2 Sampling-Based Greedy Algorithm
- 6 Experimental Study
- 6.1 Evaluation of Effectiveness
- 6.2 Evaluation of Efficiency
- 7 Conclusion
- References
- Maximizing Social Influence on Target Users
- 1 Introduction
- 2 Problem Formulation
- 3 Probabilistic Social Influence Model
- 3.1 Assigning Direct Weight
- 3.2 Social Influence Distribution
- 3.3 Objective Function
- 4 Cluster-Based Assembling Method
- 4.1 Cluster Detection Using Influence Behavior
- 4.2 Greedy Algorithm
- 5 Experiment Evaluation
- 5.1 Experiment Setup
- 5.2 Spread Achieved
- 5.3 Running Time
- 6 Conclusion
- References
- Team Expansion in Collaborative Environments
- 1 Introduction
- 2 Problem Statement
- 3 The Proposed Approach
- 3.1 The TECE Model
- 3.2 Generalizations and Discussions
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Experimental Results
- 5 Related Work
- 6 Conclusions
- References
- HashAlign: Hash-Based Alignment of Multiple Graphs
- 1 Introduction
- 2 Related Work
- 3 Proposed Formulation: Two-Graph Alignment
- 3.1 Definition: Relaxed Two-Graph Alignment Problem
- 3.2 Node Representation: Handling Node and Edge Attributes
- 3.3 Proposed Hashing-Based Computation of Potential Matchings
- 3.4 From Similarities to Matchings
- 4 HASHALIGN: Multiple Graph Alignment
- 5 Experimental Analysis
- 6 Conclusions
- References
- Evaluating and Analyzing Reliability over Decentralized and Complex Networks
- 1 Introduction
- 2 Main Definitions and Related Works
- 3 Agent-Based Reliability Estimation
- 3.1 Estimating Two-Terminal Reliability
- 3.2 Evaluation of the Graph Reduction Algorithm
- 4 Conclusion and Future Works
- References
- Efficient Exact and Approximate Algorithms for Computing Betweenness Centrality in Directed Graphs
- 1 Introduction
- 2 Preliminaries
- 3 Related Work
- 4 Computing Betweenness Centrality in Directed Graphs
- 4.1 Reachable Vertices
- 4.2 The Exact Algorithm
- 4.3 The Approximate Algorithm
- 5 Experimental Results
- 6 Conclusion
- References
- Forecasting Bitcoin Price with Graph Chainlets
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Graph Chainlets
- 3.2 Clustering Chainlets
- 4 Experiments
- 4.1 Granger Causality
- 4.2 Price Prediction
- 5 Conclusion
- References
- Information Propagation Trees for Protest Event Prediction
- 1 Introduction
- 2 Related Work
- 3 Preliminaries and Problem Setup
- 3.1 Definitions
- 3.2 Problem Setup
- 4 The Propagation Tree Framework
- 5 Experimental Settings and Results
- 5.1 Experiment Setup
- 5.2 Performance Metrics
- 5.3 Results and Discussions
- 6 Conclusion
- References
- Predictive Team Formation Analysis via Feature Representation Learning on Social Networks
- 1 Introduction
- 2 Problem Statement
- 3 Proposed Methods
- 3.1 Learning Node Representation (n2v) for Team Formation
- 3.2 The Biased-n2v Method
- 3.3 The Guided-n2v Method
- 4 Experimental Results
- 5 Related Work
- 6 Conclusions
- References
- Leveraging Local Interactions for Geolocating Social Media Users
- 1 Introduction
- 2 Related Work
- 2.1 Text-Based Methods
- 2.2 Network-Based Methods
- 2.3 Hybrid Methods
- 3 Data
- 4 The Proposed Approach
- 4.1 Construction of Social Graph
- 4.2 Predicting Geographical Proximity from Linguistic Similarity
- 4.3 Predicting Locations of Isolated Users
- 4.4 Label Propagation with Modified Adsorption
- 5 Experimental Results
- 5.1 Experiment Setting
- 5.2 Evaluation Metrics
- 5.3 Results
- 5.4 Other Textual Similarity Measures
- 6 Conclusion and Future Work
- References
- Utilizing Sequences of Touch Gestures for User Verification on Mobile Devices
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Attack Scenario
- 4 Suggested Approach
- 4.1 Data Acquisition
- 4.2 Feature Extraction
- 4.3 Verification
- 5 Experiment Setup
- 5.1 Data Collection
- 5.2 Evaluation Metrics
- 5.3 Hyper Parameter Tuning
- 6 Experiments and Results
- 6.1 Outsider and Insider Attack Scenario
- 6.2 Response Time and Comparison with State-of-the-Art
- 7 Conclusion
- 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.