Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track : European Conference, ECML PKDD 2024, Vilnius, Lithuania, September 9–13, 2024, Proceedings, Part IX / / edited by Albert Bifet, Tomas Krilavičius, Ioanna Miliou, Slawomir Nowaczyk

• Autore: Bifet Albert
• Pubblicazione: Cham : , : Springer Nature Switzerland : , : Imprint : Springer, , 2024
• Edizione: 1st ed. 2024.
• Descrizione fisica: 1 online resource (521 pages)
• Disciplina: 371.395
• Soggetto topico: Artificial intelligence; Computer engineering; Computer networks; Computers; Image processing - Digital techniques; Computer vision; Software engineering; Artificial Intelligence; Computer Engineering and Networks; Computing Milieux; Computer Imaging, Vision, Pattern Recognition and Graphics; Software Engineering
• Nota di contenuto: 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 IX -- Applied Data Science Track -- VulEXplaineR: XAI for Vulnerability Detection on Assembly Code -- 1 Introduction -- 2 Related Work -- 2.1 Vulnerability Detection -- 2.2 XAI for Vulnerability Detection -- 3 Methodology -- 3.1 Method of Communication for Vulnerability Detection -- 3.2 Graph Explanation -- 3.3 VulEXplaineR -- 4 Experimental Results -- 4.1 Dataset -- 4.2 Experimental Setup -- 4.3 Results -- 4.4 Graph Explanation -- 5 Conclusion -- References -- Guiding Catalogue Enrichment with User Queries -- 1 Introduction -- 2 Background and Related Work -- 3 Query-Guided Triplet Prediction -- 3.1 Prediction from KGE Using Rejection Sampling (RS) -- 3.2 Guided Prediction with Queries (QG) -- 4 Evaluation and Results -- 4.1 Experimental Setup -- 4.2 Automatic Evaluation -- 4.3 Human Evaluation -- 4.4 Comparison with Other Types of Guidance -- 5 Conclusions and Limitations -- References -- PeersimGym: An Environment for Solving the Task Offloading Problem with Reinforcement Learning -- 1 Introduction -- 2 Background and Related Work -- 3 Enhancing Task Offloading with MARL -- 4 PeersimGym -- 4.1 System Modeling -- 4.2 Implementation Details -- 4.3 Reducing the Reality Gap -- 5 Experimental Results and Analysis -- 5.1 Experimental Setup -- 5.2 Results Analysis -- 6 Conclusion and Future Work -- References -- Robust Interaction-Based Relevance Modeling for Online e-Commerce Search -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Dynamic-Length Representation Scheme. ; 3.2 Professional Terms Recognition Strategy -- 3.3 Contrastive Adversarial Training Mechanism -- 4 Experiments -- 4.1 Offline Evaluation -- 4.2 Online Experiments -- 5 Conclusion -- References -- Learning Optimal Linear Precoding for Cell-Free Massive MIMO with GNN -- 1 Introduction -- 2 Related Work -- 3 System Model and Notation -- 3.1 Notation -- 3.2 Cell-Free Massive MIMO -- 3.3 Precoding Matrix and Downlink SINR Calculation -- 3.4 Optimal Linear Precoding -- 3.5 Zero Forcing and Maximum Ratio Precoding -- 4 Graph Neural Network -- 4.1 Graph Representation -- 4.2 Data Preprocessing and Postprocessing -- 4.3 Structure of the Neural Network -- 4.4 Training and Loss Function -- 5 Numerical Results -- 5.1 Simulation Parameters and Performance Metrics -- 5.2 Spectral Efficiency -- 5.3 Computational Complexity and Runtime -- 6 Conclusions -- References -- Multiple Hypergraph Learning for Ephemeral Group Recommendation -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Model Overview -- 3.2 Hypergraph Construction -- 3.3 Hypergraph Convolution -- 3.4 Cross-Hypergraph Contrastive Learning -- 3.5 Model Optimization -- 3.6 Complexity Analysis -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Performance Comparison -- 4.3 Ablation Study -- 4.4 Hyperparameter Sensitivity Analysis -- 5 Conclusion -- References -- Spoofing Transaction Detection with Group Perceptual Enhanced Graph Neural Network -- 1 Introduction -- 2 Related Works -- 2.1 Spoofing Detection -- 2.2 Graph Learning in Finance -- 3 The Proposed Method -- 3.1 Model Architecture Overview -- 3.2 Transaction Graph Construction -- 3.3 Node and Edge Representation Learning -- 3.4 Group-Enhanced Representation Layer -- 3.5 Prediction Network Layer -- 4 Experiments -- 4.1 Datasets -- 4.2 Baseline Models -- 4.3 Experimental Parameter Settings -- 4.4 Spoofing Detection Experiment. ; 4.5 Parameter Sensitivity Experiment -- 4.6 Ablation Study -- 4.7 Case Study in Industry-Level Application Scenarios -- 5 Conclusion -- References -- Self-SLAM: A Self-supervised Learning Based Annotation Method to Reduce Labeling Overhead -- 1 Introduction -- 2 Dataset Description -- 2.1 Wheelchair -- 2.2 CASE -- 3 SSLAM: Self-supervised Label Generation Framework -- 3.1 Log-Cosh Loss in SSLAM Framework -- 4 Evaluation -- 4.1 Experimental Configuration -- 4.2 Results: CASE Dataset -- 4.3 Results on Wheelchair Dataset -- 5 Discussion -- 6 Relevant Literature -- 7 Conclusion and Future Works -- References -- Multi-intent Driven Contrastive Sequential Recommendation -- 1 Introduction -- 2 Related Work -- 2.1 Sequential Recommendation -- 2.2 Contrastive Learning -- 3 Problem Formulation -- 4 Our Model -- 4.1 Overview -- 4.2 Sequence Encoding -- 4.3 Intent Prototype Identifying and Updating -- 4.4 Multi-intent Guided Contrastive Learning -- 4.5 Overall Loss -- 4.6 Discussion -- 5 Experiments -- 5.1 Experimental Setting -- 5.2 Performance Comparison -- 5.3 Ablation Study -- 5.4 Robustness Analysis -- 5.5 Impact of Flase Negative Sample Elimination -- 5.6 Hyper-parameter Sensitivity -- 6 Conclusion -- References -- KAT5: Knowledge-Aware Transfer Learning with a Text-to-Text Transfer Transformer -- 1 Introduction -- 2 Related Work -- 3 Model -- 3.1 Baseline -- 3.2 KAT5: Knowledge-Aware Text-to-Text Transfer Transformer -- 3.3 Pre-training Data Creation -- 3.4 KAT5 Fine-Tuning -- 4 Experimental Settings -- 4.1 Datasets -- 4.2 Training -- 5 Results -- 5.1 Performance on Joint Entity-Relation Extraction -- 5.2 Performance on Summarization -- 5.3 Performance on Machine Translation -- 6 Discussion -- 7 Conclusion -- References -- Asymmetric Graph-Based Deep Reinforcement Learning for Portfolio Optimization -- 1 Introduction -- 2 Related Work. ; 3 The Proposed Method -- 3.1 Problem Formulation -- 3.2 Framework Overview -- 3.3 Construction of Asymmetric Graphs -- 3.4 Multi-dimensional Relation Representation -- 3.5 Generator for Portfolio Optimization -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Overall Results -- 4.3 Ablation Study -- 4.4 Interpretability Analysis -- 4.5 Hyperparameter Sensitivity -- 5 System Observation -- 6 Conclusion -- References -- Code Summarization with Project-Specific Features -- 1 Introduction -- 2 Related Work -- 3 The CSWPS Method -- 3.1 Stage 1: Learning Latent Summary Representations -- 3.2 Stage 2: Sampling Latent Summary Representations for Code Summarization -- 4 Experiment Settings -- 4.1 Datasets -- 4.2 Hyperparameters in Our Model -- 4.3 Evaluation Metrics -- 4.4 The Comparative Models -- 5 Experimental Results -- 5.1 RQ1: Our Main Model Vs. SOTA Models -- 5.2 RQ2: Can CSWPS Improve Existing Models? -- 5.3 RQ3: The Effect of the Modules Pertaining to Project-Specific Features -- 5.4 RQ4: Are the Generated Summaries More Project-Specific? -- 6 Discussion and Conclusion -- References -- Unraveling Anomalies in Time: Unsupervised Discovery and Isolation of Anomalous Behavior in Bio-Regenerative Life Support System Telemetry -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Anomaly Detection -- 3.2 Feature Extraction -- 3.3 Time Series Clustering -- 3.4 Quality Measures -- 4 Experimental Results -- 4.1 Dataset -- 4.2 RQ1: Are the Results of MDI and DAMP Complementary? -- 4.3 RQ2: Which Features Yield the Best Results? -- 4.4 RQ3: Which Algorithm Yields Better Results? -- 4.5 RQ4: What Anomaly Types can be Isolated? -- 4.6 RQ5: Can We Identify Recurring Abnormal Behavior? -- 5 Conclusions and Outlook -- References -- Long-Term Fairness in Ride-Hailing Platform -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 3.1 Problem Formulation. ; 3.2 Efficiency -- 3.3 Long-Term Fairness -- 3.4 Balance of Long-Term Fairness and Total Utility -- 4 Approach: Optimising Efficiency and Long-Term Fairness for Ride-Hailing -- 4.1 Overview -- 4.2 Time-Series Forecasting -- 4.3 Multi-objective Multi-agent Q Learning -- 4.4 Scalarisation Function -- 5 Experiments -- 5.1 Datasets -- 5.2 Experimental Details -- 5.3 Results and Analysis -- 5.4 Ablation Study -- 6 Conclusion -- References -- A Merge Sort Based Ranking System for the Evaluation of Large Language Models -- 1 Introduction -- 2 Related Work -- 3 Methodologies -- 3.1 Evaluation Platform -- 3.2 Transitive Merge Sort -- 4 Experiments -- 4.1 Experiment Settings -- 4.2 Experiment Results -- 5 Conclusion -- References -- Enhancing HVAC Control Efficiency: A Hybrid Approach Using Imitation and Reinforcement Learning -- 1 Introduction -- 2 Previous Work -- 3 Methodology -- 3.1 Behavioural Cloning from Demonstrations -- 3.2 Reinforcement Learning Fine-Tuning -- 4 Experimental Setup -- 4.1 Environment -- 4.2 Rewards -- 4.3 Training Setup -- 5 Results -- 5.1 Performance Analysis -- 5.2 Policy Analysis -- 6 Conclusion and Future Work -- References -- Synthesis of Standard 12-Lead ECG from Single-Lead ECG Using Shifted Diffusion Models -- 1 Introduction -- 2 Related Work -- 2.1 Synthesize ECG Using Diffusion Models -- 2.2 Synthesis of 12-Lead ECG from Reduced Leads -- 3 Preliminary -- 3.1 Synthesis of 12-Lead ECG from Single-Lead ECG -- 3.2 Diffusion Models -- 4 Time-Frequency Shifted Diffusion for 12-Lead ECG Synthesis -- 4.1 Motivation -- 4.2 Forward Process and Reverse Process -- 4.3 Training and Sampling -- 5 SD-ECG Architecture -- 5.1 Main Network -- 5.2 Shift Network -- 6 Experiments -- 6.1 Experimental Setup -- 6.2 Experimental Results -- 6.3 Model Analysis -- 7 Conclusion -- References. ; SAGS-DynamicBio: Integrating Semantic-Aware and Graph Structure-Aware Embedding for Dynamic Biological Data with Knowledge Graphs.
• Sommario/riassunto: 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.
• Titolo autorizzato: Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track
• ISBN: 3-031-70378-2
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910886098503321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture Notes in Artificial Intelligence, . 2945-9141 ; ; 14949