Discovery Science

Name: Discovery Science | 25th International Conference, DS 2022, Montpellier, France, October 10-12, 2022, Proceedings
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

25th International Conference, DS 2022, Montpellier, France, October 10-12, 2022, Proceedings

Poncelet Pascal Dino Ienco(Herausgeber*in)

Springer (Verlag)

Erschienen am 5. November 2022

XVIII, 568 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-031-18840-4 (ISBN)

96,29 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Keynote Talks
Unsupervised Model Selection in Outlier Detection: The Elephant in the Room
Coloring Social Relationships
35 Years of 'Scientific Discovery: Computational Explorations of the Creative Processes' - From the Early Days to the State of the Art
Contents
Regression and Limited Data
Model Optimization in Imbalanced Regression
1 Introduction
2 Related Work
3 Imbalanced Regression
3.1 Relevance Function
3.2 Squared Error Relevance Area (SERA)
4 Optimization Loss Function for Imbalanced Regression
5 Experimental Study
5.1 Experimental Setup
5.2 Results on Model Optimization
5.3 Results in Out-of-Sample
6 Conclusions
A SERA numerical approximation
B Tables of Results
References
Discovery of Differential Equations Using Probabilistic Grammars
1 Introduction
2 Related Work
3 Methods
3.1 Algebraic Equations and Numeric Differentiation
3.2 Differential Equations and Direct Simulation
3.3 Parallel Computation
4 Experimental Evaluation
4.1 Experimental Setup
4.2 Results
5 Conclusion
References
Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
1 Introduction
2 Background
2.1 Functional ANOVA
2.2 Supervised Learning with Parameterized Quantum Circuits
3 Methods
3.1 Hyperparameters and Configuration Space
3.2 Assessing Hyperparameter Importance
3.3 Verifying Hyperparameter Importance
4 Dataset and Inclusion Criteria
5 Results
5.1 Performance Distributions per Dataset
5.2 Surrogate Verification
5.3 Marginal Contributions
5.4 Random Search Verification
6 Conclusion
References
ImitAL: Learned Active Learning Strategy on Synthetic Data
1 Introduction
2 Simulating AL on Synthetic Training Data
3 Training a Neural Network by Imitation Learning
3.1 Imitation Learning
3.2 Neural Network Input and Output Encoding
3.3 Pre-selection
4 Evaluation
4.1 Experiment Details
4.2 Comparison with Other Active Learning Strategies
5 Conclusion
References
Incremental/Continual Learning
Predicting Potential Real-Time Donations in YouTube Live Streaming Services via Continuous-Time Dynamic Graph
1 Introduction
2 Related Work
2.1 Online Live Streaming Service
2.2 Dynamic Graph Learning
3 Methodology
3.1 Dataset
3.2 Dynamic Graph Generation
3.3 Temporal Graph Neural Network
3.4 Strategies for Data Imbalance
4 Experiments
4.1 Dataset Description
4.2 Experiment Setup
4.3 Baselines
4.4 Evaluation
4.5 Case Study
5 Conclusion
References
Semi-supervised Change Point Detection Using Active Learning
1 Introduction
2 AL-CPD
2.1 Algorithm Outline
2.2 Selecting Candidate Change Points
2.3 Finding New Candidate Change Points
3 Experiments
3.1 Datasets
3.2 Methodology
3.3 Q1: Comparison to Existing Change Point Detection Algorithms
3.4 Q2: Labelling Effort of AL-CPD
3.5 Q3: Contribution of Each Component of AL-CPD
3.6 Q4: Sensitivity Analysis
4 Conclusion
References
Adaptive Neural Networks for Online Domain Incremental Continual Learning
1 Introduction
2 Related Work
3 Online Domain Incremental Networks
4 Experiments
5 Conclusion
References
Incremental Update of Locally Optimal Classification Rules
1 Introduction
2 The Lord Algorithm
3 Incremental Lord
3.1 Incremental Updates
3.2 Overall Algorithm
4 Experiments
4.1 Comparison to HoeffdingTree and VFDR
4.2 Sensitivity to Parameter Settings
5 Conclusion
References
Policy Evaluation with Delayed, Aggregated Anonymous Feedback
1 Introduction
2 Related Work
3 Preliminaries
4 Policy Evaluation with DAAF
5 Methodology
6 Results
7 Discussion and Future Work
8 Summary and Conclusions
References
Spatial and Temporal Analysis
Spatial Cross-Validation for Globally Distributed Data
1 Introduction
2 Related Work
3 Spatial k-Fold Cross-Validation
4 Evaluation of Performance
4.1 Data Sets
4.2 Experimental Design
4.3 Analysis of Performance
5 Conclusions
References
.26em plus .1em minus .1emLeveraging Spatio-Temporal Autocorrelation to Improve the Forecasting of the Energy Consumption in Smart Grids
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Modeling the Temporal Autocorrelation
3.2 Modeling the Spatial Autocorrelation
4 Experiments
4.1 Experimental Setting
4.2 Results and Discussion
5 Conclusion
References
Elastic Product Quantization for Time Series
1 Introduction
2 Background
2.1 Dynamic Time Warping
2.2 Product Quantization
3 Approximate Dynamic Time Warping with Product Quantization
3.1 Training Phase
3.2 Encoding Time Series
3.3 Computing Distances Between Time Series
3.4 Memory Cost
3.5 Pre-alignment of Subspaces
4 Data Mining Applications
4.1 NN Search with PQ Approximates
4.2 Clustering with PQ Approximates
5 Experimental Settings
6 Experimental Results
6.1 Empirical Time Complexity
6.2 1NN Classification
6.3 Hierarchical Clustering
7 Conclusions
References
Stress Detection from Wearable Sensor Data Using Gramian Angular Fields and CNN
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 Preprocessing
2.3 Sample Construction
2.4 Convolutional Neural Network
3 Results
3.1 Implementation
3.2 Experiments
4 Conclusions and Future Work
References
Multi-attribute Transformers for Sequence Prediction in Business Process Management
1 Introduction
2 Definitions and Problem Statement
3 Related Work
4 Proposed Architectures
4.1 Encoder Architectures
4.2 Simplified Decoder Architectures
5 Experiments and Discussion
6 Conclusions and Final Remarks
References
Social Media Analysis
Data-Driven Prediction of Athletes' Performance Based on Their Social Media Presence
1 Introduction
2 Related Work
2.1 Social Media as a Mood and Behaviour Detection Proxy
2.2 Social Media as a Distraction Factor
3 Methodology
3.1 Data Selection
3.2 Data Preparation
3.3 Predictive Significance Analysis
3.4 Implementation Details
4 Results
5 Discussion
6 Conclusion
References
Link Prediction with Text in Online Social Networks: The Role of Textual Content on High-Resolution Temporal Data
1 Introduction
2 Background
3 Methodology
3.1 Graph Construction and Sequence-Based Framework
3.2 Learning Algorithms for Link Prediction in Temporal OSNs
3.3 Features for Link Prediction
4 Dataset
5 Results
5.1 Results for Traditional Models
5.2 Results for Graph Neural Networks
6 Discussion
References
Weakly Supervised Named Entity Recognition for Carbon Storage Using Deep Neural Networks
1 Introduction
2 Overview
2.1 Contributions
3 Background
4 Methodology
4.1 Noisy Data Set Creation
4.2 Overcoming Noisy Labels Effect
5 Evaluation
6 Related Work
7 Conclusion
References
Predicting User Dropout from Their Online Learning Behavior
1 Introduction
2 Background
3 Methodology
3.1 Data Set
3.2 Features
3.3 Pre-processing
3.4 Predictive Model
3.5 Evaluation
4 Results
4.1 Predictive Model
4.2 Evaluation
5 Discussion
6 Conclusions
References
Efficient Multivariate Data Fusion for Misinformation Detection During High Impact Events
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 High-Level Feature Extraction
2.3 Multi-modal Data Fusion Framework Based on Independent Vector Analysis
2.4 Effective Density Model for Capturing Multi-modal Associations
2.5 Classification Procedure
3 Results and Discussion
3.1 Classification Performance
3.2 Explainability
4 Conclusion
References
Fairness and Outlier Detection
MQ-OFL: Multi-sensitive Queue-based Online Fair Learning
1 Introduction
2 Background
2.1 Related Work
2.2 Fairness Definitions
2.3 Gerrymandering
2.4 Imbalanced and Drifted Data Stream
3 MQ-OFL Framework
3.1 Balanced and Fairness-Aware Pre-processing
3.2 Classifier Pool
3.3 Decision Boundary Adjustment
4 Experimental Evaluation
4.1 Datasets
4.2 Evaluation Metrics
4.3 Experimental Results
5 Conclusion
References
Multi-fairness Under Class-Imbalance
1 Introduction
2 Related Work
3 Basics and Multi-Max Mistreatment (MMM) Fairness
3.1 Multi-Max Mistreatment(MMM) Measure
4 Multi-Fairness-Aware Learning
4.1 Multi-discrimination-Free Learning Under Class-Imbalance
4.2 The MMM-Fair Boosting Post Pareto (MFBPP) Algorithm
5 Experiments
5.1 Experimental Settings
5.2 Evaluation Results
5.3 Internal Analysis
5.4 Flexibility of MFBPP
6 Conclusions and Outlook
References
When Correlation Clustering Meets Fairness Constraints
1 Introduction
2 Related Work
3 Fairness Constraints in Correlation Clustering
3.1 Background on Correlation Clustering
3.2 Problem Statement
4 Algorithm
5 Fairness Evaluation
6 Experimental Methodology
6.1 Competing Methods
6.2 Data
6.3 Evaluation Goals
6.4 Hyper-parameters and Configurations
7 Results
8 Conclusions
References
Cooperative Deep Unsupervised Anomaly Detection
1 Introduction
2 Preliminaries
3 Method
4 Experimental Results
5 Conclusions
References
On the Ranking of Variable Length Discords Through a Hybrid Outlier Detection Approach
1 Introduction
2 Background
2.1 Point Outliers Detectors and Series Segmentation
2.2 Matrix Profile, MAD and PROPHET
3 Our Approach
3.1 Experimental Comparison of MAD and PROPHET
3.2 Integrated Approach: Ranking and Outcomes
4 Conclusion and Future Work
References
Text, Ontologies and Cross-Modal Learning
TextMatcher: Cross-Attentional Neural Network to Compare Image and Text
1 Introduction
2 Related Work
3 Text Matching Problem
4 Proposed Approach
4.1 Image Embedding
4.2 Text Embedding
4.3 Cross-Attention Mechanism
4.4 Loss
5 Experiments
5.1 Industrial Use Case of Automated Cheque Processing
5.2 General Applicability of Text Matching (IAM Dataset)
5.3 Discussion
6 Conclusions
References
Can Cross-Domain Term Extraction Benefit from Cross-lingual Transfer?
1 Introduction
2 Related Work
2.1 Approaches Based on Term Characteristics
2.2 Approaches Based on Machine Learning and Deep Learning
2.3 Approaches for Slovenian Term Extraction
3 Methodology
3.1 Dataset
3.2 Methodology
3.3 Implementation Details
3.4 Evaluation Metrics
4 Results
4.1 Prediction on the ACTER Test Set
4.2 Evaluation on the RSDO5 Test Set
5 Error Analysis
6 Conclusion
References
Retrieval-Efficiency Trade-Off of Unsupervised Keyword Extraction
1 Introduction
2 Selected Related Work
3 Proposed Algorithm
4 Evaluation
5 Results
5.1 Scaling to 14M Documents
6 Discussion and Conclusions
7 Replicability
References
A Fuzzy OWL Ontologies Embedding for Complex Ontology Alignments
1 Introduction
2 Related Work
2.1 Complex Alignments
2.2 Ontologies Fuzzification
2.3 Ontology Embedding
3 The Fuzzy Complex Ontology Alignment Framework
3.1 Parsing Component
3.2 Fuzzification Component
3.3 Embedding Component
3.4 Alignment Component
4 Evaluation
5 Conclusion
References
Optimization and Network Analysis
Optimal Decoding of Hidden Markov Models with Consistency Constraints
1 Introduction
2 Related Work
3 Problem Definition
3.1 Most Likely Path in a Layered DAG with Consistency Constraints
4 Solving the Problem
4.1 Dynamic Programming
4.2 Branch and Bound
4.3 Cost Function Networks
5 Experimental Results
6 Conclusions and Future Work
References
Semi-parametric Approach to Random Forests for High-Dimensional Bayesian Optimisation
1 Introduction
2 Materials and Methods
3 Experimental Design
4 Results and Discussion
5 Summary and Conclusions
References
A Clustering-Inspired Quality Measure for Exceptional Preferences Mining-Design Choices and Consequences
1 Introduction
1.1 Main Contributions
2 Preliminaries
2.1 Order Relations
2.2 Local Pattern Mining Methods: SD, EMM, and EPM
2.3 Definitions
3 Related Work
4 Proposed Method: A Clustering-Based Quality Measure
4.1 Time Complexity
4.2 Qualitative Differences Between clus and Existing QMs
5 Synthetic Data Experiment
5.1 Results
6 Real-World Data Experiment
6.1 Comparing Against the Complement
6.2 Comparing Against the Average Dataset Ranking
7 Conclusions
References
Recurrent Segmentation Meets Block Models in Temporal Networks
1 Introduction
2 Preliminary Notation and Problem Definition
3 Fast Algorithm for Obtaining Good Model
3.1 Iterative Approach
3.2 Finding Groups
3.3 Updating Poisson Process Parameters
3.4 Finding Segmentation
4 Related Work
5 Experimental Evaluation
6 Concluding Remarks
References
Community Detection in Edge-Labeled Graphs
1 Introduction
2 Preliminary Notation and Problem Definition
3 Finding Dense Conjunctive-Induced Graphs
4 Finding Dense Disjunctive-Induced Graphs
5 Related Work
6 Experimental Evaluation
7 Concluding Remarks
References
A Fast Heuristic for Computing Geodesic Closures in Large Networks
1 Introduction
2 Notions and Notation
3 The Heuristic
4 Experimental Results
4.1 Datasets
4.2 Computing Closures in Outerplanar Graphs
4.3 Core Approximation in Real-World Networks
5 Concluding Remarks
References
Explainability and Interpretability
JUICE: JUstIfied Counterfactual Explanations
1 Introduction
2 The CF Justification Problem
3 Proposed Algorithms
3.1 JUstIfied Counterfactual Explanations (JUICE)
3.2 Mixed-features Justification Verification Algorithm
3.3 Complexity
4 Empirical Evaluation
4.1 Datasets
4.2 CF Generation Methods
4.3 Performance Metrics
4.4 Results and Discussion
5 Related Work
6 Conclusions and Future Work
References
Explaining Siamese Networks in Few-Shot Learning for Audio Data
1 Introduction
2 Related Works
3 Problem Formulation
4 Siamese Network Explainer
5 Experiments
6 Conclusion
References
Interpretable Latent Space to Enable Counterfactual Explanations
1 Introduction
2 Related Works
3 Methodology
3.1 Interpretable Latent Space Learning
3.2 Counterfactual Explanations
4 Experiments
4.1 Latent Space Evaluation
4.2 Explanations Evaluation
5 Conclusion
References
Shapley Chains: Extending Shapley Values to Classifier Chains
1 Introduction
2 Background and Related Work
2.1 Multi-output Classification and Output Dependencies
2.2 Classifier Chains
2.3 Shapley Values
2.4 Related Work
3 Proposed Method: Shapley Chains
4 Experiments
4.1 Synthetic Data
4.2 Explaining Adult Income with Shapley Chains
5 Conclusions and Perspectives
References
Explaining Crash Predictions on Multivariate Time Series Data
1 Introduction
2 Problem Description and Explanation Methodologies
3 Gradient-Based Explainer
4 Subsequence-Based Surrogates
5 Subsequence-Based Classifier
6 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken