Halina Kwaśnicka

Julia Farganus, Krzysztof Żurawicki, Arkadiusz Gaweł et al.

3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of various geometric deep learning architectures for the classification of 3D scenes represented using Gaussian Splatting. We benchmark point-based and graph-based models across both traditional point cloud datasets and dedicated Gaussian Splatting datasets. Scenes are embedded into latent representations, which are evaluated through end-to-end classification, linear probing, and clustering analysis. Our study provides insight into the suitability of different geometry-aware architectures and input feature configurations for learning effective 3D Gaussian Splat representations. The results highlight consistent differences between architectural families and reveal the impact of Gaussian-specific attributes on the quality of representation.

Adam Piróg, Halina Kwaśnicka

Despite tremendous advancements in Artificial Intelligence, learning from large sets of data in an unsupervised manner remains a significant challenge. Classical clustering algorithms often fail to discover complex dependencies in large datasets, especially considering sparse, high-dimensional spaces. However, deep learning techniques proved to be successful when dealing with large quantities of data, efficiently reducing their dimensionality without losing track of underlying information. Several interesting advancements have already been made to combine deep learning and clustering. Still, the idea of enhancing the clustering results by combining multiple views of the data generated by deep neural networks appears to be insufficiently explored yet. This paper aims to investigate this direction and bridge the gap between deep neural networks, clustering techniques and ensemble learning methods. To achieve this goal, we propose a novel deep clustering ensemble method - Snapshot Spectral Clustering, designed to maximize the gain from combining multiple data views while minimizing the computational costs of creating the ensemble. Comparative analysis and experiments described in this paper prove the proposed concept, while the conducted hyperparameter study provides a valuable intuition to follow when selecting proper values.

Bianka Kowalska, Halina Kwaśnicka

The black box nature of deep neural networks poses a significant challenge for the deployment of transparent and trustworthy artificial intelligence (AI) systems. With the growing presence of AI in society, it becomes increasingly important to develop methods that can explain and interpret the decisions made by these systems. To address this, mechanistic interpretability (MI) emerged as a promising and distinctive research program within the broader field of explainable artificial intelligence (XAI). MI is the process of studying the inner computations of neural networks and translating them into human-understandable algorithms. It encompasses reverse engineering techniques aimed at uncovering the computational algorithms implemented by neural networks. In this article, we propose a unified taxonomy of MI approaches and provide a detailed analysis of key techniques, illustrated with concrete examples and pseudo-code. We contextualize MI within the broader interpretability landscape, comparing its goals, methods, and insights to other strands of XAI. Additionally, we trace the development of MI as a research area, highlighting its conceptual roots and the accelerating pace of recent work. We argue that MI holds significant potential to support a more scientific understanding of machine learning systems -- treating models not only as tools for solving tasks, but also as systems to be studied and understood. We hope to invite new researchers into the field of mechanistic interpretability.

Łukasz P. Olech, Michał Spytkowski, Halina Kwaśnicka et al.

Object Cluster Hierarchies is a new variant of Hierarchical Cluster Analysis that gains interest in the field of Machine Learning. Being still at an early stage of development, the lack of tools for systematic analysis of Object Cluster Hierarchies inhibits its further improvement. In this paper we address this issue by proposing a generator of synthetic hierarchical data that can be used for benchmarking Object Cluster Hierarchy methods. The article presents a thorough empirical and theoretical analysis of the generator and provides guidance on how to control its parameters. Conducted experiments show the usefulness of the data generator that is capable of producing a wide range of differently structured data. Further, benchmarking datasets that mirror the most common types of hierarchies are generated and made available to the public, together with the developed generator (http://kio.pwr.edu.pl/?page\_id=396).

Michał Spytkowski, Łukasz P. Olech, Halina Kwaśnicka

The paper presents a cursory examination of clustering, focusing on a rarely explored field of hierarchy of clusters. Based on this, a short discussion of clustering quality measures is presented and the F-score measure is examined more deeply. As there are no attempts to assess the quality for hierarchies of clusters, three variants of the F-Score based index are presented: classic, hierarchical and partial order. The partial order index is the authors' approach to the subject. Conducted experiments show the properties of the considered measures. In conclusions, the strong and weak sides of each variant are presented.