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)
.- Integrating Civic Initiatives into AI Agent Ecosystems: A Human-Aligned Extension of the A2A Protocol.
.- Goal-orientation in Machine Learning Development: A Systematic Mapping Study.
.- Towards Human-AI Complementarity in Matching Tasks.
.- Comparison of Cognitive-based and Classic Optimization-based Annotator Selection Approaches.
.- MEdGellan: LLM-Generated Medical Guidance to Support Physicians in Diagnosis.
.- Ground Truth Independent Active Learning with Multiple Annotators.
.- Comparing Imitation Learning Approaches for Solving the Haulier Capacity Matching Problem.
.- From Sea to System: Exploring User-Centered Explainable AI for Maritime Decision Support.
.- Hybrid Decision Making for Adaptive Industrial User Interfaces.
.- Workshop on IoT, Edge, and Mobile for Embedded Machine Learning (ITEM 2025)
.- Implementation and Optimization of Diagonal State Space Models.
.- On-Device Learning for Human Activity Recognition on Low-Power Microcontrollers.
.- Data Stream Processing for Resource Constrained TinyML Systems.
.- Mitigating Event Fluctuations with Adaptive Buffering for Robust Neuromorphic Systems.
.- MultiVic: A Time-Predictable RISC-V Multi-Core Processor Optimized for Neural Network Inference.
.- Workshop on Machine Learning for Pharma and Healthcare Applications (PharML 2025)
.- BeatVision: Explainable AI for Clinician-Grade Atrial Fibrillation Detection.
.- Evaluating Explainability Techniques for Machine Learning in Healthcare - A Human-Centered Approach through Expert Interviews.
.- A Case Study in Explainable AI for Drug-Drug Interaction Prediction: A SHAP-Based Approach.
.- Decoding Self-paced Activity in Mice with ActionFormer.
.- CKD-GEO - A multimodal workflow for detecting CKD using statistical and geographical data.
.- Challenging the Binary Classification Paradigm in Longitudinal Health Data Settings.
.- Graph Convolutional Networks for ATC Drug Classification from Molecular Data.
.- Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI 2025)
.- Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability.
.- Document Attribution in Retrieval-Augmented Generation.
.- Do Users Exploit XAI-saliency Maps in AI-supported Decision Making? A User Study in Continuous Production of Textile Fibers Via Eye-tracking Technology.
.- Workshop on Deep Learning Meets Neuromorphic Hardware (DLmNH 2025)
.- Pathways Towards Integrating Dendritic Compartments and Oscillating Neuron Behavior On Neuromorphic Hardware.
.- An Optimization Framework for Automated Assessment of Biological Plausibility of Spiking Neurons.
.- Precise spike timing meets discrete time: discretization effects in spiking neural networks.
.- Surrogate Gradient Descent based Spiking Intrusion Detection System for Edge Devices: A Performance study.
.- Minimum Complexity Memristive-Friendly Echo State Network.
.- Modeling Diagonal State Space Models as Electric Circuits for Analog Neural Network Inference.
.- Machine Learning for Cybersecurity (MLCS 2025)
.- Towards an Adversarial Model for Fraud Detection Systems.
.- An Object-Level Entropy-Based Adversarial Attack for Image Privacy.
.- From One to Many: Few-Shot Deep Ensembles for Slow DoS Attack Detection.
.- RAMPART-FL: Federated Learning for Intrusion Detection in the Edge through Reinforcement-based Multi-Criteria Participant Selection.
.- Small but Dangerous: Evaluating and Mitigating Jailbreak Vulnerabilities in Small Language Models.
.- AnomalyExplainerBot: Explainable AI for LLM-based anomaly detection using BERTViz & Captum.
.- ATTAXML: Behaviour-Based Prediction of MITRE ATT&CK Techniques in Ransomware with Extreme Multi-Label Learning.
.- AI for Safety-Critical Infrastructures (AI-SCI 2025)
.- Continuous Assessment-Driven Requirement Elicitation for Trustworthy AI Systems.
.- Beyond Correctness: Architecting Trustworthy Software for Autonomous Systems in the Age of AI.
.- Guidelines for Safe and Robust Reinforcement Learning: from Definitions to Design.
.- Multi-Objective Reinforcement Learning for Safety-Critical Gas Grid Management: Lessons from Real-World Pilot Deployment.
.- Differentiating Adversarial Attacks from Natural Sensory Anomalies in Object Detection.
.- Workshop on Innovations, Privacy-preservation, and Evaluations of Machine Unlearning Techniques (WIPE-OUT)
.- Standard vs Modular Sampling: Best Practices for Reliable LLM Unlearning.
