SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing ↗
SeLMRoute selects an LLM using explicit probabilistic evidence about what a query requires.
arXiv:2609.34736Read summary ↗
Research & publications
Ideas, on paper.
28 records from my Scholar profile, with summaries and source links.
Federated Learning for Electric Vehicle Energy Demand Prediction Across Distributed Users ↗
Daily EV energy demand is forecast across heterogeneous users and fleets without requiring central collection of their raw records.
Availability, Reliability and Security: ARES 2026 EU Projects Symposium Workshops, LNCS 16903, pp. 166-184Read summary ↗
Explainable machine learning for non-technical loss detection in power systems ↗
Explainable learning helps utilities identify non-technical losses, including electricity theft and metering irregularities.
Sustainable Energy, Grids and Networks 47, 102479Read summary ↗
Federated Learning for Early Prediction of EV Charging Demand ↗
The total energy of an EV charging session is estimated from plug-in information and its first minutes, while intervention is still possible.
arXiv:2605.04993Read summary ↗
DUTH at EXIST 2025: Multilingual Sexism Detection with Soft Labels and Transformers. ↗
The DUTH system detects multilingual sexist content while accounting for disagreement between annotators.
CLEF 2025 Working Notes, CEUR Workshop Proceedings 4038, 1793-1800Read summary ↗
Federated learning for privacy-friendly health apps: a case study on ovulation tracking ↗
FLORA explores how ovulation tracking can combine useful predictions with stronger control over sensitive health information.
Journal of Sensor and Actuator Networks 14(1), 11Read summary ↗
Evaluation of bio-inspired models under different learning settings for energy efficiency in network traffic prediction ↗
Can biologically inspired neural models forecast cellular traffic while consuming less energy?
International Journal of Neural Systems 35(12), 2550058Read summary ↗
Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attacks ↗
The study asks whether targeted machine unlearning can reduce privacy leakage from trained models.
arXiv:2508.16150Read summary ↗
Federated Learning for Recommender Systems: Advances and Perspectives ↗
A review of how federated learning supports personalized recommendations while reducing the need to collect user interactions centrally.
Federated Learning Systems: Towards Privacy-Preserving Distributed AI, pp. 87-106Read summary ↗
Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets ↗
An empirical investigation of prompted LLMs as predictive models for small structured datasets.
Model and Data Engineering, MEDI 2025, pp. 109-116Read summary ↗
Bridging the Gap: Challenges and Limitations of Federated Learning in Real-World Applications ↗
This paper examines the practical obstacles between federated learning research and deployed applications.
2025 10th International Conference on Smart and Sustainable Technologies (SpliTech), pp. 1-6Read summary ↗
Justification Retrieval with LLMs, Retrieval-Augmented Generation, and Hybrid Labels ↗
A hybrid pipeline grades whether retrieved passages provide supporting evidence for a query in the TREC 2025 RAG relevance judgment task.
Proceedings of the 34th Text REtrieval Conference (TREC 2025)Read summary ↗
Federated Learning in Real-World Applications: Mitigating the Data Availability Problem ↗
A position paper on a tension in federated learning: keeping records decentralized can conflict with applications that need continuous access to original data.
Author-posted position paperRead summary ↗
A federated explainable ai model for breast cancer classification ↗
This study combines federated learning with explanations for breast-cancer classification on two Wisconsin benchmark datasets.
European Interdisciplinary Cybersecurity Conference (EICC 2024), 194-201Read summary ↗
Federated learning in mobile networks: A comprehensive case study on traffic forecasting ↗
A detailed real-world study of how federated learning behaves when forecasting traffic across mobile-network sites.
IEEE Transactions on Sustainable Computing, 10(3), 576-587Read summary ↗
Federated Anomaly Detection for Early-Stage Diagnosis of Autism Spectrum Disorders using Serious Game Data ↗
This preprint studies an autism-risk indicator from serious-game behavior using distributed anomaly detection. It explores screening support rather than establishing a clinical diagnosis.
arXiv:2410.20003Read summary ↗
Towards Detecting Non-Technical Losses in Electrical Power Systems with Machine Learning ↗
This study uses Greek electricity-distribution data to distinguish normal consumption from patterns associated with non-technical losses.
Energy Transition in the Mediterranean Area (SyNERGY MED 2024), 1-5Read summary ↗
Carbon-Aware Machine Learning: A Case Study on Cellular Traffic Forecasting with Spiking Neural Networks ↗
Can spiking neural networks reduce the energy cost of forecasting cellular traffic without sacrificing prediction quality?
Artificial Intelligence Applications and Innovations (AIAI 2024), 178-191Read summary ↗
SFTC: Machine Unlearning via Selective Fine-tuning and Targeted Confusion ↗
SFTC addresses requests to remove the influence of selected training examples from an existing image classifier.
European Interdisciplinary Cybersecurity Conference (EICC 2024), 29-36Read summary ↗
Federated learning for 5G base station traffic forecasting ↗
Can base stations forecast network demand together while keeping their traffic measurements local? This study tests federated learning on real LTE observations.
Computer Networks, 235, 109950Read summary ↗
Towards Energy-Aware Federated Traffic Prediction for Cellular Networks ↗
Accurate traffic prediction has an environmental cost. This paper evaluates that trade-off for federated cellular-network forecasting.
Fog and Mobile Edge Computing (FMEC 2023), 93-100Read summary ↗
Intelligent client selection for federated learning using cellular automata ↗
CA-CS selects federated clients according to changing device and network conditions instead of choosing participants uniformly at random.
Cellular Nanoscale Networks and their Applications (CNNA 2023), 1-4Read summary ↗
DUTH at SemEval-2023 Task 9: An Ensemble Approach for Twitter Intimacy Analysis ↗
The DUTH system estimates the intimacy expressed in multilingual tweets for SemEval-2023 Task 9.
SemEval-2023, 1225-1230Read summary ↗
Federated Learning for Early Dropout Prediction on Healthy Ageing Applications ↗
This work predicts early disengagement from healthy-ageing applications through collaborative training without transferring individual records.
Fog and Mobile Edge Computing (FMEC 2023), 135-142Read summary ↗
An Extensive Overview of Feature Representation Techniques for Molecule Classification ↗
This study examines how representing a molecule affects classification performance and computational efficiency.
Pan-Hellenic Conference on Progress in Computing and Informatics (PCI 2023), 156-162Read summary ↗
Predicting Early Dropouts of an Active and Healthy Ageing App ↗
Machine learning predicts which users may stop using an active and healthy ageing application early.
arXiv:2308.00539Read summary ↗
FedPOIRec: Privacy-Preserving Federated POI Recommendation with Social Influence ↗
FedPOIRec recommends places through federated learning and incorporates social influence without pooling users’ location histories.
Information Sciences, 623, 767-790Read summary ↗
Federated Neural Collaborative Filtering ↗
Federated recommendations without collecting users’ interaction histories in one place. FedNCF adapts neural collaborative filtering to collaborative local training.
Knowledge-Based Systems, 242, 108441Read summary ↗