Gustav Šír

Dr. Gustav Šír


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
15 June 2021 in Machine Learning
Verified
Journal Article
Open access
PDF file
GŠGustav Šír
Gustav Šír
FŽFilip Železný
Filip Železný
OKOndřej Kuželka
Ondřej Kuželka
We introduce a declarative differentiable programming framework, based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to encode deep relational learning scenarios through the underlying symmetries. When presented with relational data, such as various forms of graphs, the logic program interpreter dynamically unfolds differentiable computation graphs to be used for the program parameter optimization by standard means. Following from the declarative, relational logic-based encoding, this results into a unified representation of a wide range of neural models in the form of compact and elegant learning programs, in contrast to the existing procedural approaches operating directly on the computational graph level. We illustrate how this idea can be used for a concise encoding of existing advanced neural architectures, with the main focus on Graph Neural Networks (GNNs). Importantly, using the framework, we also show how the contemporary GNN models can be easily extended towards higher expressiveness in various ways. In the experiments, we demonstrate correctness and computation efficiency through comparison against specialized GNN frameworks, while shedding some light on the learning performance of the existing GNN models.

19 March 2022 in International Journal of Forecasting
Verified
Journal Article
Open access
OHOndřej Hubáček
Ondřej Hubáček
GŠGustav Šír
Gustav Šír

22 July 2025 in ACM Transactions on Intelligent Systems and Technology
Verified
Journal Article
Open access
JPJakub Peleška
Jakub Peleška
GŠGustav Šír
Gustav Šír
Transformer models have continuously expanded into all machine learning domains convertible to the underlying sequence-to-sequence representation, including tabular data. However, while ubiquitous, this representation restricts their extension to the more general case of relational databases . In this paper, we introduce a modular neural message-passing scheme that closely adheres to the formal relational model, enabling direct end-to-end learning of tabular transformers from database storage systems. We address the associated challenges of appropriate learning data representation and loading, which are critical in the database setting, and compare our approach against a number of representative models from various related fields across a significantly wide range of datasets. Our results then demonstrate superior performance of this newly proposed class of neural architectures.

16 July 2017
Verified
Book Chapter
Closed access
PDF file
GŠGustav Šír
Gustav Šír
SMSuresh Manandhar
Suresh Manandhar
FŽFilip Železný
Filip Železný
SSSteven Schockaert
Steven Schockaert
OKOndřej Kuželka
Ondřej Kuželka

15 March 2018
Verified
Book Chapter
Closed access
PDF file
GŠGustav Šír
Gustav Šír
MSMartin Svatoš
Martin Svatoš
FŽFilip Železný
Filip Železný
SSSteven Schockaert
Steven Schockaert
OKOndřej Kuželka
Ondřej Kuželka

6 February 2019 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
GŠGustav Šír
Gustav Šír
FZFilip Zelezny
Filip Zelezny
To perform sophisticated traffic analysis, such as intrusion detection, network monitoring tools firstly need to extract higher-level information from lower-level data by reconstructing events and activities from as primitive information as individual network packets or traffic flows. Aggregating communication data into meaningful entities is an open problem and existing, typically clustering-based, solutions are often highly suboptimal, producing results that may misinterpret the extracted information and consequently miss many network events. We propose a novel method for the extraction of various predefined types of network events from raw network flow data. The new method is based on analysis of computational properties of the event types as prescribed by their attributes in a given descriptive language. The corresponding events are then extracted with a supreme recall as compared to a respective event extraction part of an in-production intrusion detection system Camnep.