The 5-volume set CCIS 2839 – 2843 constitutes the refereed proceedings of several workshops held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2025, which took place in Porto, Portugal, in September 2025.
The 236 full papers included in these proceedings were carefully reviewed and selected from 413 submissions. The papers were organized topical sections as follows:
Part I: Workshop on Data Science for Social Good SoGood 2025), Workshop on Bias and Fairness in AI (BIAS 2025), Workshop on New Frontiers in Mining Complex Patterns (NFMCP 2025), Human-Centered Data Mining Workshop (HuMine 2025) and Workshop on Data-Centric Artificial Intelligence (DEARING 2025).
Part II: Workshop on Hybrid Human-Machine Learning and Decision Making (HLDM 2025), Workshop on IoT, Edge, and Mobile for Embedded Machine Learning (ITEM 2025), Workshop on Machine Learning for Pharma and Healthcare Applications (PharML 2025),Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI 2025), Workshop on Deep Learning Meets Neuromorphic Hardware (DLmNH 2025), Machine Learning for Cybersecurity (MLCS 2025),AI for Safety-Critical Infrastructures (AI-SCI 2025) and Workshop on Innovations, Privacy-preservation, and Evaluations of Machine Unlearning Techniques (WIPE-OUT).
Part III: Workshop on Machine Learning for Sustainable Power Systems (ML4SPS 2025), Workshop on Synthetic Data for AI Trustworthiness and Evolution (SynDAiTE 2025), Workshop on MIning Data for Financial Applications (MIDAS 2025), Workshop on Advancements in Federated Learning (WAFL 2025) and Workshop on Mining and Learning with Graphs (MLG 2025).
Part IV: Workshop on Interactive Adaptive Learning (IAL 2025), Workshop on Machine Learning for Irregular Time Series (ML4ITS 2025), Interactive eXplainable AI, Theory and Practice (IXAIT 2025), Workshop on Learning on Real and Synthetic Medical Time Series Data (MED-TIME 2025), Workshop on Responsible Healthcare Using Machine Learning (RHCML 2025), Workshop for Explainable AI in Time Series and Data Streams (TempXAI 2025) and Workshop on Explainable Knowledge Discovery in Data Mining and Unlearning (XKDD 2025).
Part V: Workshop on Learning from Small Data (LFSD 2025), Workshop on Machine Learning for Earth Observation (MACLEAN 2025), Workshop on Artificial Intelligence, Data Analytics and Democracy (AIDEM 2025) and Discovery Challenges.
Table of Contents:
.- Workshop on Hybrid Human-Machine Learning and Decision Making (HLDM 2025)
.- Learning from Less: Synthetic Clinical Data Augmentation for Predicting Cardiac Decompensation and Pulmonary Exacerbation.
.- Data Augmentation Using Diffusion Models with Geometric Pattern Masks for Industrial Defect Detection.
.- Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations.
.- Improving Neural Network-Based Material Simulations with Domain-Specific Data Filtering and Atom-Specific Training.
.- Evaluating Spatiotemporal Prediction Models in a Low-Data Regime.
.- Label Augmentation with Reinforced Labeling for Weak Supervision.
.- Should We Still Let Random Sampling Guide Model Performance ? Investigating Exemplar Selection for Few-Shot Named-Entity Recognition.
.- Tailored Transformation Invariance for Industrial Anomaly Detection.
.- Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics.
.- Varying Informativeness of Inductive Bias in Gaussian Processes Regression for Small Data.
.- Active Learning for cheap RUL Prediction in CMAPSS Dataset.
.- Learning local and global prototypes with optimal transport for unsupervised anomaly detection and localization.
.- Physics-Informed Diffusion Models for Unsupervised Anomaly Detection in Multivariate Time Series.
.- Evaluating Restoration Robustness under Historical-Inspired Synthetic Degradation.
.- Evaluating TabPFN for Real-World Small Dataset Regressions.
.- Workshop on Machine Learning for Earth Observation (MACLEAN 2025)
.- Can Multimodal Representation Learning by Alignment preserve modality-specific information?.
.- A Multi-Modal Spatial Risk Framework for EV Charging Infrastructure Using Remote Sensing.
.- Neural Network for Radiative Transfer Emulation.
.- A Reliable Remote Sensing-based Framework for Vessel Detection.
.- Distribution of phytoplankton assemblages accross fine-scale structures revealed by Earth Observation data: A Mediterranean Sea Case study.
.- Improved fine grained classification of buildings using aerial images and deep learning.
.- Neighbor-Aware Informal Settlement Mapping with Graph Convolutional Networks.
.- Kalman-Enhanced Streaming Linear Discriminant Analysis for Land Use Classification in Satellite Imagery.
.- Confidence-Filtered Relevance (CFR): An Interpretable and Uncertainty-Aware Machine Learning Framework for Naturalness Assessment in Satellite Imagery.
.- Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources.
.- Workshop on Artificial Intelligence, Data Analytics and Democracy (AIDEM 2025)
.- PolyTruth: Multilingual Disinformation Detection using Transformer-Based Language Models.
.- Identifying Algorithmic and Domain-Specific Bias in Parliamentary Debate Summarisation.
.- Entity Alignment for Multimodal Temporal Knowledge Graph.
.- Automated Media Assessment Using Large Language Models.
.- Improving Regulatory Oversight in Online Content Moderation.
.- Lost in Deliberation: Making Democracy Understandable.
.- POPOLARE: A Populism and Polarization Classification Framework for Italian Texts.
.- Beyond Synthetic Augmentation: Group-Aware Threshold Calibration for Robust Balanced Accuracy in Imbalanced Learning.
.- Discovery Challenges
.- Predictive Online Digital Sales (PODS) and Marketing Challenge at the 2025 ECML-PKDD.
.- Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics at ECML-PKDD 2025.
.- Foundation Models for Genomic Modeling and Understanding: Methods, Results, and Future Directions.
.- The Atmospheric Machine Learning Emulation Challenge (AMLEC).
