
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.
The 6-volume set LNAI 14645-14650 constitutes the proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2024, which took place in Taipei, Taiwan, during May 7-10, 2024.
The 177 papers presented in these proceedings were carefully reviewed and selected from 720 submissions. They deal with 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, big data technologies, and foundations.
More details
Other editions
Additional editions

Content
- Intro
- General Chairs' Preface
- PC Chairs' Preface
- Organization
- Contents - Part II
- Deep Learning
- AdaPQ: Adaptive Exploration Product Quantization with Adversary-Aware Block Size Selection Toward Compression Efficiency
- 1 Introduction
- 2 Related Works
- 3 Preliminary
- 4 Methodology
- 4.1 Adaptive Exploration Quantization
- 4.2 Adversary-Aware Block Size Selection
- 5 Experiments
- 6 Conclusion
- References
- Ranking Enhanced Supervised Contrastive Learning for Regression
- 1 Introduction
- 2 Related Work
- 3 Preliminaries
- 4 Methodology
- 4.1 Motivation
- 4.2 Ranking Enhanced Supervised Contrastive Learning (RESupCon)
- 5 Experiments
- 5.1 Datasets
- 5.2 Baselines and Settings
- 5.3 Overall Performance
- 5.4 Comparison on Spearman's Rank Correlation Coefficients
- 5.5 Parameter Study and Loss Curve
- 6 Conclusion
- References
- Treatment Effect Estimation Under Unknown Interference
- 1 Introduction
- 2 Related Work
- 3 Preliminaries
- 4 Proposed Method: Treatment Effect Estimation Under Unknown Interference
- 4.1 Covariate Representation Learner
- 4.2 Graph Structure Learner
- 4.3 Aggregation Function
- 4.4 Outcome Predictors and ITE Estimators
- 5 Experiments
- 5.1 Experiment Settings
- 5.2 Results
- 6 Conclusion
- A Identifiability of the Expectation of Potential Outcomes
- B HSIC
- C Implementation Details
- D Ablation Experiments
- References
- A New Loss for Image Retrieval: Class Anchor Margin
- 1 Introduction
- 2 Related Work
- 3 Method
- 4 Experiments
- 4.1 Datasets
- 4.2 Experimental Setup
- 4.3 Results
- 5 Conclusion
- References
- Personalized EDM Subject Generation via Co-factored User-Subject Embedding
- 1 Introduction
- 2 Related Work
- 3 Proposed Model
- 3.1 Retrieve and Re-rank
- 3.2 Variational Encoder and Bi-directional Selective Encoder
- 3.3 User-Subject Co-factor System
- 3.4 User-Based Decoder
- 4 Experimental Results
- 4.1 Quantitative Results
- 4.2 Effect of Template
- 5 Conclusions and Future Work
- References
- Spatial-Temporal Bipartite Graph Attention Network for Traffic Forecasting
- 1 Introduction
- 2 Related Work
- 3 Definitions and Problem Statement
- 3.1 Definitions
- 3.2 Problem Statement
- 4 Methodology
- 4.1 Data Inputs and Data Preprocessing
- 4.2 Encoder Decoder Architecture
- 4.3 Bipartite Graph Attention Layer
- 4.4 Heterogeneous Cross Attention Layers
- 5 Experiments
- 5.1 Experiment Setup
- 5.2 Comparison of Performance
- 5.3 Ablation Study
- 6 Conclusion and Future Works
- References
- CMed-GPT: Prompt Tuning for Entity-Aware Chinese Medical Dialogue Generation
- 1 Introduction
- 2 Related Work
- 3 Datasets
- 4 Method
- 4.1 Pre-training Model
- 4.2 Medical Dialogue Generation Model
- 5 Experiments
- 5.1 Experimental Setting
- 5.2 Experimental Results
- 6 Conclusion
- References
- MvRNA: A New Multi-view Deep Neural Network for Predicting Parkinson's Disease
- 1 Introduction
- 2 Related Work
- 3 Methods
- 3.1 Data Representation Based on Multiple Views
- 3.2 ResNet18 with BWH
- 3.3 Channel Attention Implemented Using SENet
- 4 Experiments and Results
- 4.1 Dataset
- 4.2 Experimental Settings
- 4.3 Experimental Results and Analysis
- 4.4 Ablation Experiment
- 5 Conclusion
- References
- Path-Aware Cross-Attention Network for Question Answering
- 1 Introduction
- 2 Related Work
- 3 Task Definition
- 4 Method
- 4.1 Text Encoder and Path Encoder
- 4.2 Path-Aware Cross-Attention
- 4.3 Self-learning Based Path Scoring Method
- 4.4 Learning and Inference
- 5 Experiment
- 5.1 Dataset
- 5.2 Baseline Models
- 5.3 Main Result
- 6 Analysis
- 6.1 Ablation Studies
- 6.2 Model Interpretability
- 6.3 Quantitative Analisis
- 7 Conclusion
- References
- StyleAutoEncoder for Manipulating Image Attributes Using Pre-trained StyleGAN
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Preliminaries
- 3.2 StyleAutoEncoder
- 3.3 Discussion
- 4 Experiments
- 4.1 Evaluation Metrics
- 4.2 Models Implementation
- 4.3 Manipulation of Facial Features
- 4.4 Evaluation on Animal Faces
- 5 Conclusion
- References
- SEE: Spherical Embedding Expansion for Improving Deep Metric Learning
- 1 Introduction
- 2 Related Works
- 3 Method
- 3.1 Preliminary
- 3.2 Spherical Embedding Expansion
- 4 Experiments
- 4.1 Experiment Setting
- 4.2 Quantitative Results
- 4.3 Ablation Studies
- 5 Conclusion
- References
- Multi-modal Recurrent Graph Neural Networks for Spatiotemporal Forecasting
- 1 Introduction
- 2 Related Work
- 3 Methods
- 3.1 Problem Formulation
- 3.2 Model Design
- 4 Experiments
- 4.1 Model Baselines
- 4.2 Primary Results
- 4.3 Ablation Study
- 5 Conclusions
- 7 Appendix
- References
- Layer-Wise Sparse Training of Transformer via Convolutional Flood Filling
- 1 Introduction
- 2 Background and Related Work
- 2.1 Transformer
- 2.2 Related Work on Sparse Attention
- 3 Motivation: Analysis of Sparse Patterns in MHA
- 4 SPION: Layer-Wise Sparse Attention in Transformer
- 4.1 Overview of SPION
- 4.2 Sparsity Pattern Generation with Convolutional Flood Fill Algorithm
- 5 Experimental Evaluation
- 5.1 Performance Evaluation
- 5.2 Computational Complexity Analysis
- 6 Conclusion
- References
- Towards Cost-Efficient Federated Multi-agent RL with Learnable Aggregation
- 1 Introduction
- 2 Preliminary
- 3 Federated MARL with Learnable Aggregation
- 4 Convergence Analysis
- 5 Experiments
- 6 Related Work
- 7 Conclusion
- References
- LongStory: Coherent, Complete and Length Controlled Long Story Generation
- 1 Introduction
- 2 Related Works
- 2.1 Neural Story Generation
- 2.2 Recursive Models
- 2.3 Autometic Metrics
- 3 Methodology
- 3.1 Task Description
- 3.2 Long and Short Term Contexts Weight Calibrator(CWC)
- 3.3 Long Story Structural Positions (LSP)
- 3.4 Base Pretrained Model
- 4 Experiments
- 4.1 Experiments Set-Up
- 4.2 Experimental Results
- 4.3 Further Analysis
- 5 Conclusion
- References
- Relation-Aware Label Smoothing for Self-KD
- 1 Introduction
- 2 Related Work
- 3 Our Approach
- 3.1 RAS-KD
- 4 Experimental Results
- 5 Ablation Study
- 6 Conclusion
- References
- Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference
- 1 Introduction
- 2 Relevant Work
- 3 Our Bi-CryptoNets
- 3.1 The Bi-branch of Neural Network
- 3.2 The Unidirectional Connections
- 3.3 The Feature Integration
- 4 Knowledge Distillation for Bi-CryptoNets
- 5 Experiments
- 6 Conclusion
- References
- Enhancing YOLOv7 for Plant Organs Detection Using Attention-Gate Mechanism
- 1 Introduction
- 2 Related Work
- 2.1 Attention-Gate Mechanism
- 3 YOLOv7 with Attention-Gate Mechanism
- 4 Experiments
- 4.1 Experiment Materials
- 4.2 Evaluation Metrics
- 4.3 Experimental Results
- 5 Conclusion
- References
- On Dark Knowledge for Distilling Generators
- 1 Introduction
- 2 Preliminary
- 3 Theoretical Analysis of Dark Knowledge in Distilling the Generator
- 3.1 Dark Knowledge of Generators
- 3.2 Distillation Empirical Risk
- 3.3 Generalization of the Student Generator
- 3.4 Impact of Probability Approximation
- 4 DKtill: Extracting Dark Knowledge for Training Student Generator
- 4.1 Extracting from Probabilistic Generators
- 4.2 Extracting from Non-probabilistic Generators
- 5 Empirical Illustration
- 5.1 Setting
- 5.2 Distilling Probabilistic Generators
- 5.3 Distilling Non-probabilistic Generators
- 5.4 Small Generators Through DKtill
- 6 Related Work
- 7 Conclusion
- References
- RPH-PGD: Randomly Projected Hessian for Perturbed Gradient Descent
- 1 Introduction
- 2 Preliminary
- 2.1 Notation
- 2.2 Methods to Escape from Saddle Points
- 2.3 Perturbed Gradient Descent
- 3 Algorithms
- 3.1 Randomly Projected Hessian
- 3.2 Shifted Randomly Projected Hessian
- 3.3 RPH-PGD
- 4 Experiments
- 5 Conclusion and Future Work
- References
- Transformer based Multitask Learning for Image Captioning and Object Detection
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 3.1 Objective Function
- 4 Experimental Setup
- 5 Results
- 5.1 Comparison and Analysis
- 5.2 Ablation Studies
- 6 Conclusion
- References
- Communicative and Cooperative Learning for Multi-agent Indoor Navigation
- 1 Introduction
- 2 Related Work
- 3 Cooperative Indoor Navigation Task
- 3.1 Task Definition
- 3.2 Multi-agent Indoor Navigation Environment
- 3.3 Data Collection
- 4 Cooperative Indoor Navigation Models
- 4.1 Preliminaries
- 4.2 Framework
- 5 Experiment
- 5.1 Benchmarking CIN with MARL Models
- 5.2 Implementation Details
- 5.3 Evaluation Metrics
- 5.4 Quantitative and Qualitative Results
- 6 Conclusion
- References
- Enhancing Continuous Domain Adaptation with Multi-path Transfer Curriculum
- 1 Introduction
- 2 Methodology
- 2.1 Preliminary
- 2.2 Method Framework
- 2.3 Wasserstein-Based Transfer Curriculum
- 2.4 Multi-path Optimal Transport
- 3 Experimental Results
- 3.1 Datasets and Experimental Configurations
- 3.2 Analysis of Wasserstein-Based Transfer Curriculum
- 3.3 Adaptation Comparison Results
- 3.4 Ablation Study
- 4 Conclusion
- References
- Graphs and Networks
- Enhancing Network Role Modeling: Introducing Attributed Multiplex Structural Role Embedding for Complex Networks
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Learning Framework
- 3.2 Model Training
- 4 Experiments
- 4.1 Visualization of Attributed Multiplex Role Embeddings
- 4.2 Node Clustering
- 4.3 Scalability
- 5 Studying Influential Roles on Social Media
- 5.1 Data Collection
- 5.2 Real-World Multiplex Role Similarity Ranking
- 5.3 Real-World Multiplex Role Visualization
- 6 Conclusion
- References
- Query-Decision Regression Between Shortest Path and Minimum Steiner Tree
- 1 Introduction
- 2 Preliminaries
- 3 A Warm-Up Method: QRTS-P
- 4 A Probabilistic Perspective: QRTS-D
- 4.1 Overall Framework
- 4.2 Hypothesis Design
- 4.3 QRTS-D
- 5 Empirical Studies
- 5.1 Experimental Settings
- 5.2 Analysis
- 6 Future Directions
- References
- Enhancing Policy Gradient for Traveling Salesman Problem with Data Augmented Behavior Cloning
- 1 Introduction
- 2 Related Work
- 3 Behavior Cloning Enhanced Policy Gradient
- 3.1 Behavior Cloning Pre-training
- 3.2 Policy Gradient Training
- 4 Experiments
- 4.1 Experimental Results
- 4.2 Ablation Study
- 5 Conclusion
- References
- Leveraging Transfer Learning for Enhancing Graph Optimization Problem Solving
- 1 Introduction
- 2 Related Work
- 2.1 Transfer Learning
- 2.2 Reinforcement Learning for Graph Optimization Problems
- 3 The State Extraction with Transfer-Learning Framework
- 3.1 Framework Structure
- 3.2 Reinforcement Learning Process
- 4 Experiments
- 4.1 Effectiveness and Efficiency
- 4.2 Transferability of Features
- 5 Conclusion
- References
- SD-Attack: Targeted Spectral Attacks on Graphs
- 1 Introduction
- 2 Preliminaries
- 2.1 Adversarial Attack on Graphs
- 2.2 Density of States
- 3 The Proposed Method SD-Attack
- 3.1 Spectral Density Distance
- 3.2 Why Wasserstein Distance
- 3.3 SD-Attack
- 4 Experiments
- 4.1 Setup
- 4.2 Attack Performance
- 4.3 Variants of SD-Attack
- 5 Related Works
- 6 Conclusion
- References
- Improving Structural and Semantic Global Knowledge in Graph Contrastive Learning with Distillation
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Distillation Node Contrastive Learning
- 3.2 Distillation Prototype Contrastive Learning
- 3.3 Model Learning
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Experimental Results
- 5 Conclusion
- References
- DEGNN: Dual Experts Graph Neural Network Handling both Edge and Node Feature Noise
- 1 Introduction
- 2 Related Work
- 2.1 Graph Neural Networks
- 2.2 Graph Structure Learning
- 3 The Proposed Model
- 3.1 Problem Definition
- 3.2 Overview
- 3.3 Node Feature Expert
- 3.4 Edge Expert
- 3.5 Downstream Network
- 3.6 Training Methodology
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Semi-supervised Node Classification
- 4.3 Edge Expert Analysis
- 4.4 Node Feature Expert Analysis
- 5 Conclusion
- References
- Alleviating Over-Smoothing via Aggregation over Compact Manifolds
- 1 Introduction
- 2 Related Work
- 3 Preliminaries
- 4 Contracted Aggregation Problem
- 4.1 Contracted Aggregation
- 4.2 Over-Smoothing Due to Contracted Aggregations
- 4.3 Constructing Non-contracted Aggregations
- 4.4 Our Non-contracted Aggregation
- 5 Aggregation over Compact Manifolds
- 6 Experiments
- 6.1 Experiments Setup
- 6.2 Experiment Results
- 7 Conclusion
- References
- Are Graph Embeddings the Panacea?
- 1 Introduction
- 2 Literature Review
- 3 Network Characteristics of Datasets
- 3.1 Dataset Selection
- 3.2 Summary
- 4 Experiments, Results and Discussions
- 4.1 Experiments
- 4.2 Results and Discussions
- 5 Conclusion and Future Work
- References
- Revisiting Link Prediction with the Dowker Complex
- 1 Introduction
- 2 Related Work
- 3 Background
- 4 Dowker Complex
- 5 Methodology
- 6 Experiments
- 6.1 Results
- 7 Conclusion
- References
- GraphNILM: A Graph Neural Network for Energy Disaggregation
- 1 Introduction
- 2 Related Work
- 3 Proposed Model
- 3.1 Problem Setup: Disaggregation
- 3.2 GraphNILM
- 4 Experiment
- 4.1 Dataset
- 4.2 Metrics
- 4.3 Results
- 5 Conclusion
- References
- A Contraction Tree SAT Encoding for Computing Twin-Width
- 1 Introduction
- 2 Preliminaries
- 3 Binary SAT Encoding
- 4 Experiments
- 5 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.