About

Dimitrios is an Assistant Professor of Data Organization and Mining at the School of Science and Technology at the University Centre of International Programmes of Studies at the International Hellenic University (IHU). His research lies at the intersection of data management and machine learning, exploring how scalable, robust architectures empower intelligent models, and how machine learning, in turn, transforms foundational data tasks such as entity resolution, similarity search, and high-dimensional indexing. A core focus of his work is the development of similarity algorithms, specialized data structures, and approximation schemes, with a strong emphasis on scalable, distributed solutions that leverage advanced randomization techniques.

Before joining IHU, Dimitrios was a postdoctoral associate at the Hellenic Open University. He holds a PhD from the Hellenic Open University and an MSc from the University of York (UK). His doctoral thesis was featured in the IEEE Intelligent Informatics Bulletin in August 2017.

Dimitrios is actively involved in research on data integration and data analysis. He has published extensively in high-impact journals such as Transactions on Knowledge and Data Engineering, ACM Computing Surveys, Information Systems, Data Mining and Knowledge Discovery, Knowledge and Information Systems, Knowledge-Based Systems, Transactions on Information Forensics etc, as well as in major conference proceedings including PVLDB, ICDE, ICDM, CIKM, ADBIS, Big Data, EDBT etc.

I am on the lookout for highly motivated doctoral candidates passionate about Machine Learning and Data Management. If you are passionate about scalable algorithms, active learning, Agentic AI, LLMs, or entity resolution, explore the open PhD topic.

Research Interests

  • Entity Resolution & Similarity Search: Design of algorithms and data structures utilizing Approximate Nearest Neighbor Search for large-scale environments.
  • Dimensionality Reduction: Development of randomized algorithms and data structures to improve computational efficiency while preserving accuracy guarantees.
  • Machine Learning for Knowledge Extraction: Utilization of deep learning, language models, and synergistic lexical/semantic similarities to extract knowledge from complex data.
  • Data Streams: Design of randomized summarization algorithms for real-time processing.
  • Interdisciplinary AI Applications: Applying machine learning to medical diagnosis, sports analytics, and distance learning modeling.

Selected Recent Journal Publications

  • D. Karapiperis, C. Tjortjis, V. Verykios, A Comprehensive Survey of Deep Learning for Entity Resolution, ACM Computing Surveys, 2026.
  • D. Karapiperis, C. Tjortjis, V. Verykios, Resource-Efficient Blocking: Optimizing the Trade-off between Effectiveness and Scalability in Entity Resolution, Information Systems, 2026.
  • D. Karapiperis, L. Akritidis, P. Bozanis, The Impact of Fine-Tuning on Entity Resolution: An Experimental Evaluation, Knowledge-Based Systems, 2026
  • D. Karapiperis, C. Tjortjis, V. Verykios, DynaHash: An Efficient Blocking Structure for Streaming Record Linkage, Information Systems, 2026

Selected Recent Conference Publications

  • L. Stetsikas, D. Karapiperis, G. Papadakis, M. Koubarakis, privJedAI: A Unified Open-Source Pipeline for Privacy-Preserving Record Linkage, PVLDB, 2026
  • D. Karapiperis, L. Akritidis, P. Bozanis, V. Verykios, ALER: An Active Learning Hybrid System for Efficient Entity Resolution, PVLDB, 2026
  • L. Stetsikas, D. Karapiperis, G. Papadakis, M. Koubarakis, Privacy-Preserving Record Linkage: Past, Present and Yet-to-Come, EDBT, 2026
  • D. Karapiperis, G. Papadakis, M. Koubarakis, V. Verykios, SPER: Accelerating Progressive Entity Resolution via Stochastic Bipartite Maximization, CIKM, 2026

Blogroll