Machine Learning and Knowledge Discovery in Databases. Research Track

Name: Machine Learning and Knowledge Discovery in Databases. Research Track | European Conference, ECML PKDD 2024, Vilnius, Lithuania, September 9-13, 2024, Proceedings, Part IV
Brand: Springer
Price: 85.59 EUR
Availability: OnlineOnly

European Conference, ECML PKDD 2024, Vilnius, Lithuania, September 9-13, 2024, Proceedings, Part IV

Albert Bifet Jesse Davis Tomas Krilavicius Meelis Kull Eirini Ntoutsi Indre Zliobaite(Editor)

Springer (Publisher)

Published on 29. August 2024

LVII, 456 pages

E-Book

PDF with digital watermarking

System requirements

978-3-031-70359-1 (ISBN)

€85.59incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.

Alles über E-Books, Kopierschutz & Dateiformate finden Sie in unserem Info- & Hilfebereich.

This multi-volume set, LNAI 14941 to LNAI 14950, constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2024, held in Vilnius, Lithuania, in September 2024.

The papers presented in these proceedings are from the following three conference tracks: -

Research Track: The 202 full papers presented here, from this track, were carefully reviewed and selected from 826 submissions. These papers are present in the following volumes: Part I, II, III, IV, V, VI, VII, VIII.

Demo Track: The 14 papers presented here, from this track, were selected from 30 submissions. These papers are present in the following volume: Part VIII.

Applied Data Science Track: The 56 full papers presented here, from this track, were carefully reviewed and selected from 224 submissions. These papers are present in the following volumes: Part IX and Part X.

More details

Other editions

Content

Intro
Preface
Organization
Invited Talks Abstracts
The Dynamics of Memorization and Unlearning
The Emerging Science of Benchmarks
Enhancing User Experience with AI-Powered Search and Recommendations at Spotify
How to Utilize (and Generate) Player Tracking Data in Sport
Resource-Aware Machine Learning-A User-Oriented Approach
Contents - Part IV
Research Track
Model Fusion via Neuron Transplantation
1 Introduction
2 Related Work
3 Neuron Transplantation
3.1 Analysis of NT
4 Experiments
4.1 Experimental Settings
4.2 Main Properties and Ablation Studies
4.3 Comparisons with Other Fusion Methods
5 Discussion and Conclusion
References
Compressed Federated Reinforcement Learning with a Generative Model
1 Introduction
2 Related Work
2.1 Single-Agent RL Algorithms
2.2 Distributed and Federated RL Algorithms
2.3 Communication-Efficient Learning Algorithms
2.4 Notation
3 Preliminaries and Background
3.1 Discounted Infinite-Horizon MDP
3.2 Policy, and Q-Function
3.3 Optimal Policy and Bellman Operator
3.4 RL with a Generative Model
4 CompFedRL
4.1 Compression Options for CompFedRL
5 Convergence Analysis
5.1 CompFedRL with UnbiasedComp
5.2 CompFedRLwith BiasedComp
6 Experiments
6.1 Setup
6.2 Communication Efficiency of CompFedRL
6.3 Convergence Speedup
6.4 Impact of Federated Parameter and Learning Rate
7 Conclusion
References
Walking Noise: On Layer-Specific Robustness of Neural Architectures Against Noisy Computations and Associated Characteristic Learning Dynamics
1 Introduction
2 Related Work
3 Methods
3.1 Global and Walking Noise
3.2 Data Sets, Models and Experimental Setup
4 Analysis of Global Noise
4.1 Quantifying Robustness
4.2 Robustness Results for Global Noise
5 Additive Noise
5.1 Impact of Batch Normalization
5.2 Impact of Weight Magnitude
6 Multiplicative Noise
6.1 Self-binarization of Model Activations
6.2 The Impact of Batch Normalization
7 Mixed Noise
8 Making Use of Walking Noise Results
9 Summary
References
KAFÈ: Kernel Aggregation for FEderated
1 Introduction
2 Related Work
2.1 KDE in Federated Learning
2.2 Statistical Heterogeneity in Federated Learning
3 Methodology
3.1 Preliminaries
3.2 The Proposed Framework: KAFÈ
3.3 Convergence Analysis
4 Experiment
4.1 Experimental Setting
4.2 Empirical Results
5 Conclusion
References
On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance
1 Introduction
2 Algorithmic Design of SET-Adam
2.1 Motivation of Layerwise Down-Scaling Operation
2.2 Design of Layerwise Down-Scaling Operation
2.3 -Embedding for Suppressing Range of Adaptive Stepsizes
2.4 Down-Translating for Avoiding Extremely Small Adaptive Stepsizes
2.5 Convergence Analysis
3 Experiments
3.1 On Training a Transformer
3.2 On Training LSTMs
3.3 On Training VGG11 and ResNet34 over CIFAR10 and CIFAR100
3.4 On Training WGAN-GP over CIFAR10
3.5 On Training ResNet18 over ImageNet
4 Conclusions
References
Graph Attention Network with Relational Dynamic Factual Fusion for Knowledge Graph Completion
1 Introduction
2 Related Work
2.1 Classical Embedding Models
2.2 Graph Convolutional Network Models
2.3 Graph Attention Network Models
3 Preliminary
3.1 Point Mutual Information
3.2 Related Impact Factor
4 Our Proposal
4.1 Relational Diversified Information Extraction
4.2 Relational Dynamic Factual Fusion
4.3 Relational Diversified Information Sharing
4.4 Entity Updating
4.5 Training Objective
4.6 Decoder
5 Experiments
5.1 Experimental Setup
5.2 Results
6 Conclusion
References
Low-Hanging Fruit: Knowledge Distillation from Noisy Teachers for Open Domain Spoken Language Understanding
1 Introduction
2 Related Work
3 Problem Setting
4 Noise Teacher and Consistently Guiding Student Paradigm
4.1 Incremental Progress Prompting Scheme for Intent and Slot Filling Distillation
4.2 Positively Fine-Tuned Paradigm
5 Experiment
6 Discussion
References
The Price of Labelling: A Two-Phase Federated Self-learning Approach
1 Introduction
2 Related Work
3 Overview and Fundamentals
4 The 2-Phase Federated Self-learning Framework
4.1 Local Data Augmentation
4.2 2PFL Training Phases
5 Experimental Evaluation
5.1 Experimental Set-up
5.2 Experimental Results
6 Conclusions
References
Disentangled Representations for Continual Learning: Overcoming Forgetting and Facilitating Knowledge Transfer
1 Introduction
2 Related Work
3 Methodology
3.1 Disentangled Representation Encoders
3.2 Prevent Forgetting in Shared Encoder
3.3 Facilitate Knowledge Transfer Among Task Encoders
4 Experiments
4.1 Experimental Setup
4.2 Results and Analysis
4.3 Knowledge Transfer Results
4.4 Ablation Study
4.5 Hyperparameter Sensitivity Analysis
5 Conclusion
References
On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
1 Introduction
2 Related Work
3 Principles of Epistemic Uncertainty
3.1 Data-Related Principle of Epistemic Uncertainty
3.2 Model-Related Principle of Epistemic Uncertainty
4 Conflictual Deep Ensembles
5 Empirical Analysis
6 Conclusion
References
Improving the Evaluation and Actionability of Explanation Methods for Multivariate Time Series Classification
1 Introduction
2 Related Work
2.1 Multivariate Time Series Classification
2.2 Attribution Methods for Multivariate Time Series Classification
2.3 Quantitative Evaluation of Attribution Methods for MTSC
2.4 Actionability of Explanation Methods
3 Background
3.1 Classifiers
3.2 XAI Methods
3.3 InterpretTime
3.4 Datasets
4 Methodology
4.1 MTS Chunking
4.2 Assessment Based on Ground Truth
4.3 Improving InterpretTime
4.4 Actionable XAI: Channel Selection for MTSC Using Attribution
5 Experiments
5.1 Validating InterpretTime Results
5.2 Improved XAI Evaluation Methodology
5.3 Real World Data
5.4 Actionability
6 Conclusion
References
Novel Node Category Detection Under Subpopulation Shift
1 Introduction
2 Related Work
2.1 PU Learning and Novel Category Detection
2.2 Subpopulation Shift and PU Learning
2.3 PU Learning on Graphs
2.4 Anomaly Detection and OOD Detection on Graphs
3 Problem Formulation
4 Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP)
4.1 Recall-Constrained Optimization
4.2 Selective Link Prediction
5 Experiments
5.1 Experimental Setup
5.2 Results and Discussions
5.3 Auxiliary Experiments
6 Conclusion
References
SynODC: Utilizing the Syntactic Structure for Outlier Detection in Categorical Attributes
1 Introduction
2 Related Work
3 Syntactic Patterns
3.1 Preliminaries
3.2 Expressive and Generalized Patterns
4 The System Architecture
4.1 Data Profiling and Numerical Attributes Pruning
4.2 Pattern Generation
4.3 Modified Min-Edit Distance (MMED)
4.4 Dominant Pattern Identification
4.5 Eliminating False Predictions
4.6 Time Complexity Analysis
5 Evaluation
5.1 Datasets
5.2 Baseline Methods
5.3 Experiment Setup
5.4 Results and Analysis
6 Conclusion and Future Work Directions
References
FELIX: Automatic and Interpretable Feature Engineering Using LLMs
1 Introduction
2 Related Work
3 FELIX
3.1 Feature Generation
3.2 Feature Selection
3.3 Value Assignment
4 Experiments
4.1 Datasets
4.2 Baselines
4.3 Experiment A: Feature Relevance
4.4 Experiment B: Sample Efficiency
4.5 Experiment C: Generalization Capabilities
4.6 Interpretability
5 Conclusion
References
Harnessing Superclasses for Learning from Hierarchical Databases
1 Introduction
2 Related Works
3 Hierarchical Loss
3.1 Notation
3.2 Weighting Scheme
3.3 Hierarchical Loss
3.4 Comparison with Hierarchical Cross-Entropy
4 Experimental Protocol
4.1 Hierarchical Measures of Accuracy
4.2 Architectures, Baselines and Datasets
4.3 Training Protocol
5 Results and Analysis
5.1 Variable Training Set Size
5.2 Coarsening Accuracy Curves
5.3 Sensitivity to Hyper-parameters
6 Conclusion
A Proofs
References
Approximation Error of Sobolev Regular Functions with Tanh Neural Networks: Theoretical Impact on PINNs
1 Introduction
2 Preliminary Background and Notations
2.1 PINNs and Functional Analysis
2.2 Notations
3 Approximation Bound for Sobolev Functions
3.1 General Bound for Tanh Networks
3.2 Instantiation for Our Proposed Methods for Choosing
3.3 Theoretical Impact on PINNs: the Case of Navier-Stokes PDEs
4 Differentiable Smoothing Windows
4.1 General Step Function and Differentiable Windows Phi_i
4.2 Tanh-Based Step Function
5 Novel Tanh Derivatives Analysis
6 Conclusion
References
A Theoretically Grounded Extension of Universal Attacks from the Attacker's Viewpoint
1 Introduction
2 Preliminaries and Related Works
3 Generalization Guarantees: We Can Attack New Examples
3.1 From Universal Perturbation...
3.2 .to Generalized Universal Perturbations
4 Optimization and Selection of Universal Perturbations
5 Numerical Experiments
5.1 MNIST Experiments
5.2 ImageNet Experiments
6 Conclusion
References
Linear Modeling of the Adversarial Noise Space
1 Introduction
2 Preliminaries and Related Works
2.1 Specific Perturbations
2.2 Universal Perturbations
2.3 Manifold of Adversarial Perturbations
3 Linear Modeling of the Adversarial Noise Space
3.1 Problem Formulation
3.2 Relaxations and Algorithmic Solutions
4 Experiments
4.1 Experimental Settings
4.2 Insights and Attack Performance
4.3 Transferability of the Adversarial Noise Space
5 Conclusion
References
Classifier-Free Graph Diffusion for Molecular Property Targeting
1 Introduction
2 Background and Related Works
2.1 Deep Generative Models for Molecules
2.2 Denoising Diffusion Probabilistic Models
2.3 DiGress: Denoising Diffusion for Graphs
3 Classifier-Free Graph Diffusion
3.1 Conditioning on the Number of Nodes
4 Experiments
4.1 Datasets
4.2 Metrics and Targets
4.3 Experimental Details
5 Results
6 Conclusions
References
Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
1 Introduction
2 Related Work
3 Pruned Layer-Wise Relevance Propagation (PLRP)
3.1 Setting
3.2 Pruned LRP
4 Evaluation
4.1 Evaluation Metrics
4.2 Experiments
5 Conclusion
References
ILPO-NET: Network for the Invariant Recognition of Arbitrary Volumetric Patterns in 3D
1 Introduction
2 Related Work
3 Theory
3.1 Problem Statement
3.2 Method
3.3 Implementation for the Voxelized Data
4 Results
4.1 Orientation Invariance
4.2 Experiments on the CATH Dataset
4.3 Experiments on MedMNIST Datasets
4.4 Filter Demonstration
5 Discussion and Conclusion
References
Deep Domain Isolation and Sample Clustered Federated Learning for Semantic Segmentation
1 Introduction
2 Method
2.1 Notations, Global Federated Objective and FedAvg
2.2 Sample Clustered Federated Learning (SCFL)
2.3 Deep Domain Isolation (DDI) for Semantic Segmentation
3 Experiments
3.1 Datasets and Models
3.2 Federated Splits
3.3 Baselines and Experiments
3.4 Training Parameters
4 Results
4.1 On the Effect of Covariate Shift on FedAvg
4.2 SCFL Performance and Comparison to Baselines
4.3 Clustering Performance
4.4 Test Time Cluster Assignment Evaluation
5 Conclusion and Future Works
References
Pointer-Guided Pre-training: Infusing Large Language Models with Paragraph-Level Contextual Awareness
1 Introduction
2 Related Work
3 Methodology
3.1 Pointer-Guided Segment Ordering
3.2 Sample-Efficient Fine-Tuning Using Dynamic Sampling
4 Experiments
4.1 Pre-training
4.2 Downstream Fine-Tuning for Sequential Text Classification
4.3 Limitations
5 Conclusion
References
Cut-Stitch: A Simple and Effective Data Augmentation Method for Industrial Inspection
1 Introduction
2 Related Work
3 Method
3.1 Proposed Method: Cut-Stitch
3.2 Visual Analysis
4 Experimental Results
4.1 Implementation Details
4.2 Image Similarity Experiment
4.3 Image Classification Experiments
4.4 Object Detection Experiments
4.5 Ablation Study
4.6 Pixel Distribution
5 Limitations and Future Learning
6 Conclusion
References
Functional Latent Dynamics for Irregularly Sampled Time Series Forecasting
1 Introduction
2 Problem Formulation
3 Background
4 Functional Latent Dynamics
5 Inferring Coefficients
6 Modelling Goodwin Oscillators with FLD-L
7 Benchmark Experiments
7.1 Datasets
7.2 Competing Models
7.3 Task Protocol
7.4 Hyperparameters
7.5 Results
8 Efficiency
9 Conclusion and Future Work
References
Learning Model Agnostic Explanations via Constraint Programming
1 Introduction
1.1 Contributions
1.2 Related Work
2 Preliminaries
3 The Framework
3.1 From Explanations to Rules
3.2 Learning Rules via Constraint Optimization
3.3 From Learning to Explanations
4 Experiments
4.1 Experimental Setup
4.2 Experimental Results
5 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Machine Learning and Knowledge Discovery in Databases. Research Track

Description

More details

Other editions

Additional editions

Content

System requirements