Advances in Knowledge Discovery and Data Mining

Name: Advances in Knowledge Discovery and Data Mining | 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2024, Taipei, Taiwan, May 7-10, 2024, Proceedings, Part III
Brand: Springer
Price: 139.09 EUR
Availability: OnlineOnly

28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2024, Taipei, Taiwan, May 7-10, 2024, Proceedings, Part III

De-Nian Yang Xing Xie Vincent S. Tseng Jian Pei Jen-Wei Huang Jerry Chun-Wei Lin(Editor)

Springer (Publisher)

Published on 24. April 2024

XXXIV, 422 pages

E-Book

PDF with digital watermarking

System requirements

978-981-97-2259-4 (ISBN)

€139.09incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
General Chairs' Preface
PC Chairs' Preface
Organization
Contents - Part III
Interpretability and Explainability
Neural Additive and Basis Models with Feature Selection and Interactions
1 Introduction
2 Generalized Additive Models (GAMs)
2.1 Neural Additive Model (NAM)
2.2 Neural Basis Model (NBM)
3 NAM and NBM with Feature Selection
3.1 Motivation
3.2 Model Architecture
3.3 Implementation Remark
4 Discussion of Model Complexities
5 Experiments
5.1 Experimental Settings
5.2 Baselines
5.3 Results
6 Conclusion
References
Random Mask Perturbation Based Explainable Method of Graph Neural Networks
1 Introduction
2 Related Work
3 Problem Statement
4 Explainable Method
4.1 Node Importance Based on Fidelity
4.2 Explanation Sparsity
5 Experiments
5.1 Experimental Setup
5.2 Quantitative Experiments
5.3 Ablation Study
5.4 Use Case
6 Conclusion
References
RouteExplainer: An Explanation Framework for Vehicle Routing Problem
1 Introduction
2 Related Work
3 Proposed Framework: RouteExplainer
3.1 Many-to-Many Edge Classifier
3.2 Counterfactual Explanation for VRP
4 Experiments
4.1 Quantitative Evaluation of the Edge Classifier
4.2 Qualitative Evaluation of Generated Explanations
5 Conclusion and Future Work
References
On the Efficient Explanation of Outlier Detection Ensembles Through Shapley Values
1 Introduction
2 Related Work
3 Outlier Detection Ensembles
4 The bagged Shapley Values
5 Theoretical Guarantees for the Approximation
6 Experiments
6.1 Quality of the Approximation
6.2 Effectiveness
6.3 Scalability
7 Conclusions
References
Interpreting Pretrained Language Models via Concept Bottlenecks
1 Introduction
2 Related Work
2.1 Interpreting Pretrained Language Models
2.2 Learning from Noisy Labels
3 Enable Concept Bottlenecks for PLMs
3.1 Problem Setup
4 C3M: A General Framework for Learning CBE-PLMs
4.1 ChatGPT-Guided Concept Augmentation
4.2 Learning from Noisy Concept Labels
5 Experiments
6 Conclusion
A Definitions of Training Strategies
B Details of the Manual Concept Annotation for the IMDB Dataset
C Implementation Detail
D Parameters and Notations
E Statistics of Data Splits
F Statistics of Concepts in Transformed Datasets
G More Results on Explainable Predictions
H A Case Study on Test-Time Intervention
I Examples of Querying ChatGPT
References
Unmasking Dementia Detection by Masking Input Gradients: A JSM Approach to Model Interpretability and Precision
1 Introduction
2 Related Work
3 Methods
3.1 Jacobian Saliency Map (JSM)
3.2 Jacobian-Augmented Loss Function (JAL)
4 Experiments
4.1 Dataset
4.2 Preprocessing
4.3 Multimodal Classification
4.4 Performance Evaluation
5 Conclusion
References
Towards Nonparametric Topological Layers in Neural Networks
1 Introduction
1.1 Background
1.2 Motivation and Challenges
1.3 Contributions
2 Preliminaries and Related Work
2.1 Basics of Topology
2.2 Topological Neural Network
2.3 Functional Spaces for Machine Learning
3 Methodology
4 Evaluation
4.1 Experimental Setup
4.2 Implementation
4.3 Overall Performance
4.4 Learning Rate
4.5 Temporal-Spatial Correlation
5 Conclusion
References
Online, Streaming, Distributed Algorithms
Streaming Fair k-Center Clustering over Massive Dataset with Performance Guarantee
1 Introduction
1.1 Problem Statement
1.2 Related Work
1.3 Our Contribution
2 A Two-Pass Algorithm with Approximation Ratio 3
2.1 The -Independent Center Set
2.2 The Two-Pass Streaming Algorithm
3 The Streaming Algorithm with an Approximation Ratio 7
3.1 The Streaming Algorithm for Constructing 1 and 2
3.2 Post-streaming Construction of Center Set C from 12
4 Experimental Results
4.1 Experimental Setting
4.2 Experimental Analysis
5 Conclusion
References
Projection-Free Bandit Convex Optimization over Strongly Convex Sets
1 Introduction
2 Related Work
2.1 Projection-Free OCO Algorithms
2.2 Bandit Convex Optimization
3 Main Results
3.1 Preliminaries
3.2 Our Proposed Algorithm
3.3 Theoretical Guarantees
4 Experiments
4.1 Problem Settings
4.2 Experimental Results
5 Conclusion
References
Adaptive Prediction Interval for Data Stream Regression
1 Introduction
2 Related Work
3 Background
4 Adaptive Prediction Interval(AdaPI)
5 Experiments and Results
5.1 Comparison to Interval Forecast
5.2 Comparison Between MVE and AdaPI
6 Conclusions
References
Probabilistic Guarantees of Stochastic Recursive Gradient in Non-convex Finite Sum Problems
1 Introduction
1.1 Related Works
1.2 Our Contributions
1.3 Notation
2 Prob-SARAH Algorithm
3 Theoretical Results
3.1 Technical Assumptions
3.2 Main Results on Complexity
3.3 Proof Sketch
4 Numerical Experiments
4.1 Logistic Regression with Non-convex Regularization
4.2 Two-Layer Neural Network
5 Conclusion
References
Rethinking Personalized Federated Learning with Clustering-Based Dynamic Graph Propagation
1 Introduction
2 Related Work
3 Methodology
3.1 Model Overview
3.2 Client Model Clustering
3.3 Dynamic Weighted Graph Construction
3.4 Knowledge Propagation and Aggregation
3.5 Precise Personalized Model Distribution
4 Experiment
4.1 Experiment Setup
4.2 Performance Evaluation
4.3 Ablation Study
4.4 Case Study
4.5 Hyperparameter Study
5 Conclusion
References
Unveiling Backdoor Risks Brought by Foundation Models in Heterogeneous Federated Learning
1 Introduction
2 Related Work
3 Methodology
3.1 Threat Model
3.2 FMs Empowered Backdoor Attacks to HFL
4 Experiment
4.1 Experiment Setup
4.2 Experimental Results
4.3 Homogeneous Setting Evaluation
4.4 Case Study: Attack Effectiveness v.s. Public Data Utilization Ratio
4.5 Hyper-Parameter Study: ASR v.s. Poisoning Ratio
5 Conclusion
References
Combating Quality Distortion in Federated Learning with Collaborative Data Selection
1 Introduction
2 Related Works
3 Proposal
3.1 Preliminaries
3.2 Design Principle
3.3 Collaborative Sample Selection (CSS)
4 Evaluation
4.1 Datasets and Experimental Settings
4.2 Experimental Results
5 Conclusion
References
Probabilistic Models and Statistical Inference
Neural Marked Hawkes Process for Limit Order Book Modeling
1 Introduction
2 Background
3 Neural Marked Hawkes Process
4 Related Work
5 Experiments
6 Conclusion
References
How Large Corpora Sizes Influence the Distribution of Low Frequency Text n-grams
1 Introduction
2 Background and Related Work
3 The Model
4 Results
4.1 The Corpora Collection
4.2 The Range of k Values for W(k,C
L,n) Prediction
4.3 The Assessment Criteria and Parameter Estimation
4.4 Comparison with Other Models
4.5 Obtained Results
4.6 The Predictions with Growing Corpus Size
5 Conclusions
References
Meta-Reinforcement Learning Algorithm Based on Reward and Dynamic Inference
1 Introduction
2 Background
2.1 Meta-Reinforcement Learning
2.2 Context-Based Meta-Reinforcement Learning
2.3 Parametric Task Distributions
3 Problem Statement
4 Method
4.1 Reward and Dynamics Inference
4.2 Meta-Reinforcement Learning Algorithm Based on Reward and Dynamics Inference Encoders
5 Experiment
5.1 Common MuJoCo Environments
5.2 Cartesian Product Combinations of Tasks with Different Goals and Dynamics
6 Discussion
References
Security and Privacy
SecureBoost+: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree
1 Introduction
2 Preliminaries
2.1 Gradient Boosting Decision Tree
2.2 Paillier Homomorphic Encryption
2.3 SecureBoost
2.4 Performance Bottlenecks Analysis for SecureBoost
3 Proposed SecureBoost+ Framework
3.1 Ciphertext Operation Optimization
3.2 Training Mechanism Optimization
4 Experiments
4.1 Setup
4.2 Ciphertext Operation Optimization Evaluation
4.3 Training Mechanism Optimization Evaluation
5 Conclusion
References
Construct a Secure CNN Against Gradient Inversion Attack
1 Introduction
2 Preliminary
2.1 Federated Learning
2.2 Gradient Inversion Attack
2.3 Recursive Gradient Attack on Privacy (R-GAP)
3 Secure Convolutional Neural Networks
4 Experiment
4.1 Quantitative Results
4.2 Quantitative Results
5 Related Work
6 Limitation and Conclusion
References
Backdoor Attack Against One-Class Sequential Anomaly Detection Models
1 Introduction
2 Related Work
3 Preliminaries
3.1 Deep One-Class Sequential Anomaly Detection
3.2 Mutual Information Maximization
4 Methodology
4.1 Threat Model
4.2 The Proposed Attack
4.3 Post-deployment Attack
5 Experiments
5.1 Experimental Setup
5.2 Experimental Results
6 Conclusions
References
Semi-supervised and Unsupervised Learning
DALLMi: Domain Adaption for LLM-Based Multi-label Classifier
1 Introduction
2 Language Model and Domain Adaptation
3 DALLMi
4 Experiments
5 Conclusion
References
Contrastive Learning for Unsupervised Sentence Embedding with False Negative Calibration
1 Introduction
2 Related Work
2.1 Contrastive Learning
2.2 SimCSE
3 Method
3.1 False Negative Elimination
3.2 False Negative Reuse
4 Experiment and Analysis
4.1 Setup
4.2 Training Details
4.3 Main Result
4.4 Short Text Clustering
4.5 Ablation Study
4.6 Comparison with Other False Negative Solutions
5 Conclusion
References
Recovering Population Dynamics from a Single Point Cloud Snapshot
1 Introduction
2 Related Work
3 Problem Setting
4 Proposed Method
4.1 Notation
4.2 Optimal Transport for Recovering the Vector Field
4.3 Vector and Acceleration Smoothing
4.4 Objective Function and Algorithm
5 Experiment
5.1 Datasets
5.2 Comparison Methods
5.3 Evaluation Metrics
5.4 Parameter Configuration
5.5 Result
5.6 Ablation Study
5.7 Discussion and Limitation
6 Conclusion
References
SAWTab: Smoothed Adaptive Weighting for Tabular Data in Semi-supervised Learning
1 Introduction
2 Related Works
2.1 Semi-supervised Learning on Tabular Data
2.2 Representation of Categorical Data
3 Methodology
3.1 Preliminaries
3.2 Smoothed Adaptive Weighting
3.3 Conditional Probability Representation with Weighting Schema
3.4 Progressive Feature Upgrading and SAWTab
4 Experiments and Evaluation
4.1 Tabular Dataset
4.2 Experiment Settings
4.3 Results
5 Ablation Study
5.1 Discussion
6 Conclusion
References
Big Data
Improving Anti-money Laundering via Fourier-Based Contrastive Learning
1 Introduction
2 Related Work
2.1 Anti-Money Laundering(AML)
2.2 Contrastive Learning
3 Methdology
3.1 Task Definition
3.2 Overall Architecture
3.3 Data Augmentation
3.4 Feature Encoding
3.5 Contrastive Pre-training
3.6 Money Laundering Detection
4 Experiment
4.1 Datasets
4.2 Hyperparameters
4.3 Baselines
4.4 Effectiveness of Data Augmentation
4.5 Future Direction
5 Conclusion
References
A Novel SegNet Model for Crack Image Semantic Segmentation in Bridge Inspection
1 Introduction
2 Proposed Methods
2.1 Enhanced SegNet
2.2 ConvNeXtV2 Module
2.3 Loss Function
3 Experiments
3.1 Experimental Setting and Datasets
3.2 Ablation Experiments
3.3 Comparison with State-of-the-Art
3.4 Visualization
4 Conclusion
References
Graph-based Dynamic Preference Modeling for Personalized Recommendation
1 Introduction
2 Related Work
2.1 Sequential Recommendation
2.2 Graph-Based Recommendation
3 Problem Formulation
4 The Proposed Method
4.1 Long-Term Graph Model
4.2 Short-Term Graph Model
4.3 Preference Fusion and Prediction
5 Experiments
5.1 Datasets
5.2 Baselines
5.3 Experimental Setup
5.4 Overall Comparison (RQ1)
5.5 Ablation Analysis (RQ2)
5.6 Hyper-parameter Analysis (RQ3)
6 Conclusion
References
LEAF: A Less Expert Annotation Framework with Active Learning
1 Introduction
2 Related Work
2.1 Large Language Models for Data Annotation
2.2 Active Learning
2.3 Automatic Machine Learning
3 The Framework
3.1 Overview of the Framework
3.2 Query Procedure
3.3 Annotation Procedure
3.4 Training Model Procedure
4 Experiments
4.1 Experiment in Annotation Process
4.2 Case Study: Real-World Annotation
5 Results and Discussion
5.1 Efficiency Evaluation
5.2 Accuracy Evaluation
5.3 Real-World Annotation Ability
6 Conclusions and Future Work
References
MLT-Trans: Multi-level Token Transformer for Hierarchical Image Classification
1 Introduction
2 Related Work
3 Mathematical Notation and MLT-Trans
4 Experimental Evaluation
5 Conclusions and Future Work
References
Improving Knowledge Tracing via Considering Students' Interaction Patterns
1 Introduction
2 Related Work
2.1 Knowledge Tracing
2.2 Students' Interaction Patterns
3 Preliminary
3.1 Knowledge Tracing Task
3.2 Embedding
4 Method
4.1 Input Embedding
4.2 Interaction Pattern Discovery
4.3 Knowledge Acquisition
4.4 Prediction and Objective Function
5 Experiment
5.1 Datasets
5.2 Experimental Setup
5.3 Baselines
5.4 Students' Performance Prediction
5.5 Ablation Study
6 Conclusion
References
MDAN: Multi-distribution Adaptive Networks for LTV Prediction
1 Introduction
2 Related Work
3 Method
3.1 Multi-distribution Adaptive Networks
3.2 Distance Similarity Loss
4 Experiments
4.1 Dataset
4.2 Evaluation Metrics and Baselines
4.3 Performance Comparison
4.4 Ablation Study
4.5 Embeddings Distribution Analysis
5 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Advances in Knowledge Discovery and Data Mining

Description

More details

Other editions

Additional editions

Content

System requirements