93 citations · 117 across the 24 of their papers we have counts for
25 papers
KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models
Boshko Koloski, Xiangjian Jiang, Senja Pollak +3
Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Yet in niche domains, where data…
Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models
Paula Dodig, Boshko Koloski, Katarina Sitar Šuštar +2
Environmental, Social, and Governance (ESG) considerations are increasingly integral to assessing corporate performance, reputation, and long-term sustainability. Yet, reliable ESG…
Multilingual Cognitive Impairment Detection in the Era of Foundation Models
Damar Hoogland, Boshko Koloski, Jaya Caporusso +5
We evaluate cognitive impairment (CI) classification from transcripts of speech in English, Slovene, and Korean. We compare zero-shot large language models (LLMs) used as direct cl…
MAPLE: Multi-Path Adaptive Propagation with Level-Aware Embeddings for Hierarchical Multi-Label Image Classification
Boshko Koloski, Marjan Stoimchev, Jurica Levatić +2
Hierarchical multi-label classification (HMLC) is essential for modeling structured label dependencies in remote sensing. Yet existing approaches struggle in multi-path settings, w…
HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification
Marjan Stoimchev, Boshko Koloski, Jurica Levatić +2
Hierarchical multi-label classification (HMLC) is essential for modeling complex label dependencies in remote sensing. Existing methods, however, struggle with multi-path hierarchi…
Incremental Graph Construction Enables Robust Spectral Clustering of Texts
Marko Pranjić, Boshko Koloski, Nada Lavrač +2
Neighborhood graphs are a critical but often fragile step in spectral clustering of text embeddings. On realistic text datasets, standard -NN graphs can contain many disconnecte…
FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation
Boshko Koloski, Senja Pollak, Roberto Navigli +1
Building on the success of Large Language Models (LLMs), LLM-based representations have dominated the document representation landscape, achieving great performance on the document…
From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
Blaž Škrlj, Boshko Koloski, Senja Pollak +1
Integrating structured knowledge from Knowledge Graphs (KGs) into Large Language Models (LLMs) enhances factual grounding and reasoning capabilities. This survey paper systematical…
Make Literature-Based Discovery Great Again through Reproducible Pipelines
Bojan Cestnik, Andrej Kastrin, Boshko Koloski +1
By connecting disparate sources of scientific literature, literature\-/based discovery (LBD) methods help to uncover new knowledge and generate new research hypotheses that cannot…
LLM Embeddings for Deep Learning on Tabular Data
Boshko Koloski, Andrei Margeloiu, Xiangjian Jiang +3
Tabular deep-learning methods require embedding numerical and categorical input features into high-dimensional spaces before processing them. Existing methods deal with this hetero…
HorNets: Learning from Discrete and Continuous Signals with Routing Neural Networks
Boshko Koloski, Nada Lavrač, Blaž Škrlj
Construction of neural network architectures suitable for learning from both continuous and discrete tabular data is a challenging research endeavor. Contemporary high-dimensional…
SEKE: Specialised Experts for Keyword Extraction
Matej Martinc, Hanh Thi Hong Tran, Senja Pollak +1
Keyword extraction involves identifying the most descriptive words in a document, allowing automatic categorisation and summarisation of large quantities of diverse textual data. R…
Evaluating and explaining training strategies for zero-shot cross-lingual news sentiment analysis
Luka Andrenšek, Boshko Koloski, Andraž Pelicon +3
We investigate zero-shot cross-lingual news sentiment detection, aiming to develop robust sentiment classifiers that can be deployed across multiple languages without target-langua…
AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification
Boshko Koloski, Senja Pollak, Roberto Navigli +1
Large semantic knowledge bases are grounded in factual knowledge. However, recent approaches to dense text representations (i.e. embeddings) do not efficiently exploit these resour…
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna +70
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learnin…
A Computational Analysis of the Dehumanisation of Migrants from Syria and Ukraine in Slovene News Media
Jaya Caporusso, Damar Hoogland, Mojca Brglez +3
Dehumanisation involves the perception and or treatment of a social group's members as less than human. This phenomenon is rarely addressed with computational linguistic techniques…
Multi-Task Learning for Features Extraction in Financial Annual Reports
Syrielle Montariol, Matej Martinc, Andraž Pelicon +4
For assessing various performance indicators of companies, the focus is shifting from strictly financial (quantitative) publicly disclosed information to qualitative (textual) info…
AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining
Boshko Koloski, Nada Lavrač, Bojan Cestnik +3
In an era marked by a rapid increase in scientific publications, researchers grapple with the challenge of keeping pace with field-specific advances. We present the `AHAM' methodol…
Latent Graphs for Semi-Supervised Learning on Biomedical Tabular Data
Boshko Koloski, Nada Lavrač, Senja Pollak +1
In the domain of semi-supervised learning, the current approaches insufficiently exploit the potential of considering inter-instance relationships among (un)labeled data. In this w…
Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies
Boshko Koloski, Blaž Škrlj, Marko Robnik-Šikonja +1
The cross-lingual transfer is a promising technique to solve tasks in less-resourced languages. In this empirical study, we compare two fine-tuning approaches combined with zero-sh…
Retrieval-efficiency trade-off of Unsupervised Keyword Extraction
Blaž Škrlj, Boshko Koloski, Senja Pollak
Efficiently identifying keyphrases that represent a given document is a challenging task. In the last years, plethora of keyword detection approaches were proposed. These approache…
Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?
Boshko Koloski, Senja Pollak, Blaž Škrlj +1
Keyword extraction is the task of retrieving words that are essential to the content of a given document. Researchers proposed various approaches to tackle this problem. At the top…
Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
Boshko Koloski, Timen Stepišnik-Perdih, Marko Robnik-Šikonja +2
Increasing amounts of freely available data both in textual and relational form offers exploration of richer document representations, potentially improving the model performance a…
Extending Neural Keyword Extraction with TF-IDF tagset matching
Boshko Koloski, Senja Pollak, Blaž Škrlj +1
Keyword extraction is the task of identifying words (or multi-word expressions) that best describe a given document and serve in news portals to link articles of similar topics. In…