Jan Kralj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jan Kralj has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Nada Lavrač
Jozef Stefan Institute
9 shared publications - Blaž Škrlj
Jožef Stefan Institute, Ljubljana, Slovenia
7 shared publications Nada Lavrač
Jožef Stefan International Postgraduate School
5 shared publicationsMarko Robnik-Šikonja
University of Ljubljana
4 shared publicationsAnita Valmarska
Jozef Stefan Institute
2 shared publications- Anže Vavpetič
Jozef Stefan Institute
2 shared publications
Latest Publications
- 10 September 2021
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (1) , 914-943
Deep node ranking for neuro‐symbolic structural node embedding and classification
- 10 September 2021
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (1) , 914-943
Deep node ranking for neuro‐symbolic structural node embedding and classification
- Open Access
New Cross-Talks between Pathways Involved in Grapevine Infection with ‘Candidatus Phytoplasma solani’ Revealed by Temporal Network Modelling
Understanding temporal biological phenomena is a challenging task that can be approached using network analysis. Here, we explored whether network reconstruction can be used to better understand the temporal dynamics of bois noir, which is associated with ‘Candidatus Phytoplasma solani’, and is one of the most widespread phytoplasma diseases of grapevine in Europe. We proposed a methodology that explores the temporal network dynamics at the community level, i.e., densely connected subnetworks. The methodology offers both insights into the functional dynamics via enrichment analysis at the community level, and analyses of the community dissipation, as a measure that accounts for community degradation. We validated this methodology with cases on experimental temporal expression data of uninfected grapevines and grapevines infected with ‘Ca. P. solani’. These data confirm some known gene communities involved in this infection. They also reveal several new gene communities and their potential regulatory networks that have not been linked to ‘Ca. P. solani’ to date. To confirm the capabilities of the proposed method, selected predictions were empirically evaluated.
Open AccessNew Cross-Talks between Pathways Involved in Grapevine Infection with ‘Candidatus Phytoplasma solani’ Revealed by Temporal Network Modelling
Understanding temporal biological phenomena is a challenging task that can be approached using network analysis. Here, we explored whether network reconstruction can be used to better understand the temporal dynamics of bois noir, which is associated with ‘Candidatus Phytoplasma solani’, and is one of the most widespread phytoplasma diseases of grapevine in Europe. We proposed a methodology that explores the temporal network dynamics at the community level, i.e., densely connected subnetworks. The methodology offers both insights into the functional dynamics via enrichment analysis at the community level, and analyses of the community dissipation, as a measure that accounts for community degradation. We validated this methodology with cases on experimental temporal expression data of uninfected grapevines and grapevines infected with ‘Ca. P. solani’. These data confirm some known gene communities involved in this infection. They also reveal several new gene communities and their potential regulatory networks that have not been linked to ‘Ca. P. solani’ to date. To confirm the capabilities of the proposed method, selected predictions were empirically evaluated.
- Open Access
- 1 January 2021
- Published by Elsevier in Computer Speech & Language
- Vol. 65, 101104
tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
- 1 January 2021
- Published by Elsevier in Computer Speech & Language
- Vol. 65, 101104
Open Accesstax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
- Open Access
- 27 July 2020
- Published by Springer Nature in Machine Learning
- Vol. 109 (11) , 2161-2193
Embedding-based Silhouette community detection
Mining complex data in the form of networks is of increasing interest in many scientific disciplines. Network communities correspond to densely connected subnetworks, and often represent key functional parts of real-world systems. This paper proposes the embedding-based Silhouette community detection (SCD), an approach for detecting communities, based on clustering of network node embeddings, i.e. real valued representations of nodes derived from their neighborhoods. We investigate the performance of the proposed SCD approach on 234 synthetic networks, as well as on a real-life social network. Even though SCD is not based on any form of modularity optimization, it performs comparably or better than state-of-the-art community detection algorithms, such as the InfoMap and Louvain. Further, we demonstrate that SCD’s outputs can be used along with domain ontologies in semantic subgroup discovery, yielding human-understandable explanations of communities detected in a real-life protein interaction network. Being embedding-based, SCD is widely applicable and can be tested out-of-the-box as part of many existing network learning and exploration pipelines.
- 27 July 2020
- Published by Springer Nature in Machine Learning
- Vol. 109 (11) , 2161-2193
Open AccessEmbedding-based Silhouette community detection
Mining complex data in the form of networks is of increasing interest in many scientific disciplines. Network communities correspond to densely connected subnetworks, and often represent key functional parts of real-world systems. This paper proposes the embedding-based Silhouette community detection (SCD), an approach for detecting communities, based on clustering of network node embeddings, i.e. real valued representations of nodes derived from their neighborhoods. We investigate the performance of the proposed SCD approach on 234 synthetic networks, as well as on a real-life social network. Even though SCD is not based on any form of modularity optimization, it performs comparably or better than state-of-the-art community detection algorithms, such as the InfoMap and Louvain. Further, we demonstrate that SCD’s outputs can be used along with domain ontologies in semantic subgroup discovery, yielding human-understandable explanations of communities detected in a real-life protein interaction network. Being embedding-based, SCD is widely applicable and can be tested out-of-the-box as part of many existing network learning and exploration pipelines.
- 16 October 2019
- Published by Springer Nature
- p. 261-275
Symbolic Graph Embedding Using Frequent Pattern Mining
- 16 October 2019
- Published by Springer Nature
- p. 261-275
Symbolic Graph Embedding Using Frequent Pattern Mining
- Open Access
Embedding-based Silhouette Community Detection
Mining complex data in the form of networks is of increasing interest in many scientific disciplines. Network communities correspond to densely connected subnetworks, and often represent key functional parts of real-world systems. In this work, we propose Silhouette Community Detection (SCD), an approach for detecting communities, based on clustering of network node embeddings, i.e. real valued representations of nodes derived from their neighborhoods. We investigate the performance of the proposed SCD approach on 234 synthetic networks, as well as on a real-life social network. Even though SCD is not based on any form of modularity optimization, it performs comparably or better than state-of-the-art community detection algorithms, such as the InfoMap and Louvain algorithms. Further, we demonstrate how SCD's outputs can be used along with domain ontologies in semantic subgroup discovery, yielding human-understandable explanations of communities detected in a real-life protein interaction network. Being embedding-based, SCD is widely applicable and can be tested out-of-the-box as part of many existing network learning and exploration pipelines.
Open AccessEmbedding-based Silhouette Community Detection
Mining complex data in the form of networks is of increasing interest in many scientific disciplines. Network communities correspond to densely connected subnetworks, and often represent key functional parts of real-world systems. In this work, we propose Silhouette Community Detection (SCD), an approach for detecting communities, based on clustering of network node embeddings, i.e. real valued representations of nodes derived from their neighborhoods. We investigate the performance of the proposed SCD approach on 234 synthetic networks, as well as on a real-life social network. Even though SCD is not based on any form of modularity optimization, it performs comparably or better than state-of-the-art community detection algorithms, such as the InfoMap and Louvain algorithms. Further, we demonstrate how SCD's outputs can be used along with domain ontologies in semantic subgroup discovery, yielding human-understandable explanations of communities detected in a real-life protein interaction network. Being embedding-based, SCD is widely applicable and can be tested out-of-the-box as part of many existing network learning and exploration pipelines.
- Open Access
- 4 April 2019
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 1 (2) , 575-589
Towards Robust Text Classification with Semantics-Aware Recurrent Neural Architecture
Deep neural networks are becoming ubiquitous in text mining and natural language processing, but semantic resources, such as taxonomies and ontologies, are yet to be fully exploited in a deep learning setting. This paper presents an efficient semantic text mining approach, which converts semantic information related to a given set of documents into a set of novel features that are used for learning. The proposed Semantics-aware Recurrent deep Neural Architecture (SRNA) enables the system to learn simultaneously from the semantic vectors and from the raw text documents. We test the effectiveness of the approach on three text classification tasks: news topic categorization, sentiment analysis and gender profiling. The experiments show that the proposed approach outperforms the approach without semantic knowledge, with highest accuracy gain (up to 10%) achieved on short document fragments.
- 4 April 2019
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 1 (2) , 575-589
Open AccessTowards Robust Text Classification with Semantics-Aware Recurrent Neural Architecture
Deep neural networks are becoming ubiquitous in text mining and natural language processing, but semantic resources, such as taxonomies and ontologies, are yet to be fully exploited in a deep learning setting. This paper presents an efficient semantic text mining approach, which converts semantic information related to a given set of documents into a set of novel features that are used for learning. The proposed Semantics-aware Recurrent deep Neural Architecture (SRNA) enables the system to learn simultaneously from the semantic vectors and from the raw text documents. We test the effectiveness of the approach on three text classification tasks: news topic categorization, sentiment analysis and gender profiling. The experiments show that the proposed approach outperforms the approach without semantic knowledge, with highest accuracy gain (up to 10%) achieved on short document fragments.
- Open Access
- 26 January 2019
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 53 (2) , 265-304
CBSSD: community-based semantic subgroup discovery
- 26 January 2019
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 53 (2) , 265-304
Open AccessCBSSD: community-based semantic subgroup discovery
- 28 January 2017
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 50 (1) , 29-61
HINMINE: heterogeneous information network mining with information retrieval heuristics
- 28 January 2017
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 50 (1) , 29-61
HINMINE: heterogeneous information network mining with information retrieval heuristics
- 10 June 2016
- Published by Springer Nature in Machine Learning
- Vol. 105 (1) , 3-39
Explaining mixture models through semantic pattern mining and banded matrix visualization
- 10 June 2016
- Published by Springer Nature in Machine Learning
- Vol. 105 (1) , 3-39
Explaining mixture models through semantic pattern mining and banded matrix visualization