@julasms.bsky.social
Predicting links with GNN - sure, but how can you visualize the influence of node feature values in a fast way? The answer is our (with P. Kaczyńska and D. Ślęzak) adaptation of the ALE method. arxiv.org/abs/2512.03061
Accumulated Local Effects and Graph Neural Networks for link prediction
We investigate how Accumulated Local Effects (ALE), a model-agnostic explanation method, can be adapted to visualize the influence of node feature values in link prediction tasks using Graph Neural Ne...
arxiv.org
December 4, 2025 at 5:59 PM
Predicting links with GNN - sure, but how can you visualize the influence of node feature values in a fast way? The answer is our (with P. Kaczyńska and D. Ślęzak) adaptation of the ALE method. arxiv.org/abs/2512.03061
How to examine if a preprint turns into a publication? You have to start with the (right) data! That's what our new preprint (with F. Badalova and P. Mayr) is about - data included! arxiv.org/abs/2510.01783
PreprintToPaper dataset: connecting bioRxiv preprints with journal publications
The PreprintToPaper dataset connects bioRxiv preprints with their corresponding journal publications, enabling large-scale analysis of the preprint-to-publication process. It comprises metadata for 14...
arxiv.org
October 3, 2025 at 9:46 AM
How to examine if a preprint turns into a publication? You have to start with the (right) data! That's what our new preprint (with F. Badalova and P. Mayr) is about - data included! arxiv.org/abs/2510.01783
Out this week: our new paper with A. Chmiel in Phys Rev E (doi.org/10.1103/v5q5...) on the relation between temperature and noise (prob. of choice) in multiplex networks for q-lobby models.
August 30, 2025 at 11:15 AM
Out this week: our new paper with A. Chmiel in Phys Rev E (doi.org/10.1103/v5q5...) on the relation between temperature and noise (prob. of choice) in multiplex networks for q-lobby models.
New piece with Kamil Orzechowski and Agata and Piotr Fronczak: "When the crowd gets it wrong – the limits of collective wisdom in machine learning" www.nature.com/articles/s41...
When the crowd gets it wrong – the limits of collective wisdom in machine learning - Scientific Reports
Scientific Reports - When the crowd gets it wrong – the limits of collective wisdom in machine learning
www.nature.com
July 2, 2025 at 9:33 PM
New piece with Kamil Orzechowski and Agata and Piotr Fronczak: "When the crowd gets it wrong – the limits of collective wisdom in machine learning" www.nature.com/articles/s41...
Our new work (with Anna Chmiel) shows relations between noise and temperature in a coupled opinion dynamics model. arxiv.org/abs/2506.07680
June 10, 2025 at 6:33 AM
Our new work (with Anna Chmiel) shows relations between noise and temperature in a coupled opinion dynamics model. arxiv.org/abs/2506.07680
Just out: our small theoretical study on what happens when we examine a limited influence in a strongly polarized environment. journals.aps.org/pre/abstract...
$Q$-Neighbor Ising model on a polarized network
In this paper, we examine the interplay between the lobby size $q$ in the $q$-neighbor Ising model of opinion formation [Phys. Rev. E 92, 052105 (2015)] and the level of overlap $v$ of two fully conne...
doi.org
December 9, 2024 at 4:30 PM
Just out: our small theoretical study on what happens when we examine a limited influence in a strongly polarized environment. journals.aps.org/pre/abstract...
Interesting that our work on information overload (www.nature.com/articles/s41...) has just been referenced in the context of recent crisis in Korea (www.forbes.com/sites/callum...).
www.nature.com
December 4, 2024 at 11:02 PM
Interesting that our work on information overload (www.nature.com/articles/s41...) has just been referenced in the context of recent crisis in Korea (www.forbes.com/sites/callum...).