Marko Bajec

Prof. Dr. Marko Bajec

Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2011 in Physical Review E
Verified
Journal Article
Closed access
LŠLovro Šubelj
Lovro Šubelj
Marko BajecMarko Bajec
Marko Bajec
Label propagation has proven to be a fast method for detecting communities in large complex networks. Recent developments have also improved the accuracy of the approach; however, a general algorithm is still an open issue. We present an advanced label propagation algorithm that combines two unique strategies of community formation, namely, defensive preservation and offensive expansion of communities. The two strategies are combined in a hierarchical manner to recursively extract the core of the network and to identify whisker communities. The algorithm was evaluated on two classes of benchmark networks with planted partition and on 23 real-world networks ranging from networks with tens of nodes to networks with several tens of millions of edges. It is shown to be comparable to the current state-of-the-art community detection algorithms and superior to all previous label propagation algorithms, with comparable time complexity. In particular, analysis on real-world networks has proven that the algorithm has almost linear complexity, O(m1.19), and scales even better than the basic label propagation algorithm (m is the number of edges in the network).

1 July 2017 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
NBNeli Blagus
Neli Blagus
LŠLovro Šubelj
Lovro Šubelj
Marko BajecMarko Bajec
Marko Bajec

1 November 2014 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
NBNeli Blagus
Neli Blagus
LŠLovro Šubelj
Lovro Šubelj
Marko BajecMarko Bajec
Marko Bajec

16 June 2022 in Informatica
Verified
Journal Article
Open access
PDF file
TKTimotej Knez
Timotej Knez
DGDomen Gašperlin
Domen Gašperlin
Marko BajecMarko Bajec
Marko Bajec
SZSlavko Zitnik
Slavko Zitnik
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: Blockchain-Based Transaction Manager for Ontology Databases, Authors: Timotej Knez, Domen Gašperlin, Marko Bajec, Slavko Žitnik , Knowledge graphs are commonly represented by ontology-based databases. Tracking the provenance of ontological changes and ensuring ontology consistency is important. In this work, we propose a transaction manager for ontology-based database manipulation that combines blockchain and Semantic Web technologies. The latter is used for the efficient querying and modification of data, whereas the blockchain is used for the secure storage and tracking of changes. The blockchain enables a decentralized setup and data restoration. We evaluate our solution by measuring cost and time. Our solution introduces some overhead for updates whereas querying works at the same speed as the underlying ontology database.

1 January 2008 in Informatica
Verified
Journal Article
Closed access
PDF file
Marko BajecMarko Bajec
Marko Bajec
DVDamjan Vavpotič
Damjan Vavpotič
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: A Framework and Tool-Support for Reengineering Software Development Methods, Authors: Marko Bajec, Damjan Vavpotič , The purpose of the research described in this paper is to propose a framework and supporting tools that will help software companies to establish formalised methods that will be technically and socially sound with their needs. Following the framework the companies can asses and improve their existing ways of working, capture them into formalised methods and continuously enrich them based on the past development experiences. Furthermore, the formalised methods that are designed based on the suggested framework are flexible and can be automatically adjusted by the supporting tools to suite circumstances of a particular project or team. This paper describes the framework philosophy and its tool support.

30 November 2024 in Language Resources and Evaluation
Verified
Journal Article
Open access
PDF file
DVDarinka Verdonik
Darinka Verdonik
ABAndreja Bizjak
Andreja Bizjak
AZAndrej Zgank
Andrej Zgank
MMMirjam Sepesy Maučec
Mirjam Sepesy Maučec
MTMitja Trojar
Mitja Trojar
Simon DobrišekSimon Dobrišek
Simon Dobrišek
The paper details the creation of an open access speech corpus for a less-resourced language, covering the diversity in terms of accents, dialects, speech styles and demographic characteristics that exist in the target population. Three primary challenges are identified that impact the time and cost efficiency of such a speech corpus development significantly. These challenges are (1) Managing copyrights, personality rights and personal data protection; (2) Obtaining precise word-by-word transcriptions with segmentation into meaningful segments and annotation of speaker exchanges; (3) Managing the new collaborators needed for field recording and manual transcribing or the correction of transcriptions, along with a strictly-defined workflow and platform for data collection. Several strategies are proposed to address each of these challenges, and the experiences are described from the creation of the Slovenian ARTUR corpus regarding these challenges. The ARTUR corpus comprises 1,000 h of carefully selected recordings, with 880 h accompanied by precise, manually checked or manually created transcriptions. It is freely available in the CLARIN.SI repository under the CC BY-SA 4.0 licence. Part of its data was used to upgrade the Slovenian reference speech corpus GOS.