93 citations · 391 across the 45 of their papers we have counts for
11 papers · 1 filter
Predicting Generalization in Deep Learning via Metric Learning -- PGDL Shared task
Sebastian Mežnar, Blaž Škrlj
The competition "Predicting Generalization in Deep Learning (PGDL)" aims to provide a platform for rigorous study of generalization of deep learning models and offer insight into t…
Ensemble- and Distance-Based Feature Ranking for Unsupervised Learning
Matej Petković, Dragi Kocev, Blaž Škrlj +1
In this work, we propose two novel (groups of) methods for unsupervised feature ranking and selection. The first group includes feature ranking scores (Genie3 score, RandomForest s…
SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations
Sebastian Mežnar, Nada Lavrač, Blaž Škrlj
Learning from complex real-life networks is a lively research area, with recent advances in learning information-rich, low-dimensional network node representations. However, state-…
Fuzzy Jaccard Index: A robust comparison of ordered lists
Matej Petković, Blaž Škrlj, Dragi Kocev +1
We propose Fuzzy Jaccard Index (FUJI) -- a scale-invariant score for assessment of the similarity between two ranked/ordered lists. FUJI improves upon the Jaccard index by incorpor…
COVID-19 therapy target discovery with context-aware literature mining
Matej Martinc, Blaž Škrlj, Sergej Pirkmajer +4
The abundance of literature related to the widespread COVID-19 pandemic is beyond manual inspection of a single expert. Development of systems, capable of automatically processing…
To BAN or not to BAN: Bayesian Attention Networks for Reliable Hate Speech Detection
Kristian Miok, Blaz Skrlj, Daniela Zaharie +1
Hate speech is an important problem in the management of user-generated content. To remove offensive content or ban misbehaving users, content moderators need reliable hate speech…
Propositionalization and Embeddings: Two Sides of the Same Coin
Nada Lavrač, Blaž Škrlj, Marko Robnik-Šikonja
Data preprocessing is an important component of machine learning pipelines, which requires ample time and resources. An integral part of preprocessing is data transformation into t…
AttViz: Online exploration of self-attention for transparent neural language modeling
Blaž Škrlj, Nika Eržen, Shane Sheehan +3
Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation. Commonly comprised…
Layer entanglement in multiplex, temporal multiplex, and coupled multilayer networks
Blaž Škrlj, Benjamin Renoust
Complex networks, such as transportation networks, social networks, or biological networks, capture the complex system they model often by representing only one type of interaction…
TNT-KID: Transformer-based Neural Tagger for Keyword Identification
Matej Martinc, Blaž Škrlj, Senja Pollak
With growing amounts of available textual data, development of algorithms capable of automatic analysis, categorization and summarization of these data has become a necessity. In t…
Feature Importance Estimation with Self-Attention Networks
Blaž Škrlj, Sašo Džeroski, Nada Lavrač +1
Black-box neural network models are widely used in industry and science, yet are hard to understand and interpret. Recently, the attention mechanism was introduced, offering insigh…