- ホーム
- > 洋書
- > 英文書
- > Computer / Databases
Full Description
This volume constitutes the proceedings of the 23rd International Symposium on Intelligent Data Analysis, IDA 2025, which was held in Konstanz, Germany, during May 7-9, 2025.
The 35 full papers included in the proceedings were carefully reviewed and selected from 91 submissions. They were organized in topical sections as follows: Applications of data science, foundations of data science; natural language processing; temporal and streaming data; and explainable and interpretable data science.
Contents
Applications of Data Science.- Credal Knowledge Tracing for Imprecise and Uncertain MCQ.- Development of Models to Quantify Training Load in Outdoor Running using Inertial Sensors.- Estimating the Learning Capacity of Bacterial Metabolic Networks.- Semi-supervised learning with pairwise instance comparisons for medical instance classification.- Local-global Data Augmentation for Contrastive Learning in Static Sign Language Recognition.- SiamCircle: Trajectory Representation Learning in Free Settings.- Synthetic Tabular Data Detection In the Wild.- Assessing the Impact of Graph Structure Learning in Graph Deviation Networks.- Foundations of Data Science.- The When and How of Target Variable Transformations.- Balancing performance and scalability of demand forecasting ML models.- Balancing global importance and source proximity for personalized recommendations using random walk length.- Counterintuitive Behavior of Clustering Quality: Findings for K-Means
on Synthetic and Real Data.- BOWSA: a contribution of sensitivity analysis to improve Bayesian optimization for parameter tuning.- Overfitting in Combined Algorithm Selection and Hyperparameter
Optimization.- Local Subgroup Discovery on Attributed Network Graphs.- Imposing Constraints in Probabilistic Circuits via Gradient Optimization.- Natural Language Processing.- Improving Next Tokens via Second-Last Predictions with 'Generate and Refine'.- Detection of Large Language Model Contamination with Tabular Data.- Imbalanced Data Clustering via Targeted Data Augmentation Using GMM and LLM.- Make Literature-Based Discovery Great Again through Reproducible Pipelines.- Extracting information in a low-resource setting: case study on bioinformatics workflows.- Vocabulary Quality in NLP Datasets: An Autoencoder-Based Framework Across Domains and Languages.- Temporal and Streaming Data Expertise Prediction of Tetris Players Using Eye Tracking Information.- Integrating Inverse and Forward Modeling for Sparse Temporal Data from Sensor Networks.- Bridging Spatial and Temporal Contexts: Sparse Transfer Learning.- Meta-learning and Data Augmentation for Stress Testing Forecasting Models.- Pragmatic Paradigm for Multi-stream Regression.- Two-in-one Models for Event Prediction and Time Series Forecasting. Comparison of Four Deep Learning Approaches to Simulate a Digital Patient under Anesthesia.- An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks.- Performative Drift Resistant Classification using Generative Domain Adversarial Networks.- Explainable and Interpretable Data Science.- Extracting Moore Machines from Transformers using Queries and Counterexamples.- Obtaining Example-Based Explanations from Deep Neural Networks.- Relevance-aware Algorithmic Recourse.- Expanding Polynomial Kernels for Global and Local Explanations of Support Vector Machines.- A Constrained Declarative Based Approach for Explainable Clustering.
