74 citations · 272 across the 40 of their papers we have counts for
49 papers
In-Context Density Estimation for Tabular Data
Patryk Marszałek, Jacek Tabor, Marek Śmieja
Density estimation underlies many unsupervised tasks on tabular data such as anomaly detection, out-of-distribution detection, and data augmentation. Although all these problems re…
Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
Piotr Kubaty, Patryk Marszałek, Łukasz Struski +3
Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they r…
Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
Patryk Krukowski, Jacek Tabor, Przemysław Spurek +2
Data-free continual learning (DFCIL) relies on model inversion to synthesize pseudo-samples and mitigate catastrophic forgetting. However, existing inversion methods are fundamenta…
SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
Kacper Jurek, Wojciech Batko, Marek Śmieja +1
Learning from scarce labeled data with a larger pool of unlabeled samples, known as semi-supervised few-shot learning (SS-FSL), remains critical for applications involving tabular…
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Patryk Marszałek, Tomasz Kuśmierczyk, Witold Wydmański +2
Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across da…
VisTabNet: Adapting Vision Transformers for Tabular Data
Witold Wydmański, Ulvi Movsum-zada, Jacek Tabor +1
Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, whic…
StyleAutoEncoder for manipulating image attributes using pre-trained StyleGAN
Andrzej Bedychaj, Jacek Tabor, Marek Śmieja
Deep conditional generative models are excellent tools for creating high-quality images and editing their attributes. However, training modern generative models from scratch is ver…
Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
Marcin Przewięźlikowski, Randall Balestriero, Wojciech Jasiński +2
Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typ…
RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets
Piotr Gaiński, Michał Koziarski, Krzysztof Maziarz +3
Single-step retrosynthesis aims to predict a set of reactions that lead to the creation of a target molecule, which is a crucial task in molecular discovery. Although a target mole…
A deep cut into Split Federated Self-supervised Learning
Marcin Przewięźlikowski, Marcin Osial, Bartosz Zieliński +1
Collaborative self-supervised learning has recently become feasible in highly distributed environments by dividing the network layers between client devices and a central server. H…
ChiENN: Embracing Molecular Chirality with Graph Neural Networks
Piotr Gaiński, Michał Koziarski, Jacek Tabor +1
Graph Neural Networks (GNNs) play a fundamental role in many deep learning problems, in particular in cheminformatics. However, typical GNNs cannot capture the concept of chirality…
Augmentation-aware Self-supervised Learning with Conditioned Projector
Marcin Przewięźlikowski, Mateusz Pyla, Bartosz Zieliński +3
Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and M…
r-softmax: Generalized Softmax with Controllable Sparsity Rate
Klaudia Bałazy, Łukasz Struski, Marek Śmieja +1
Nowadays artificial neural network models achieve remarkable results in many disciplines. Functions mapping the representation provided by the model to the probability distribution…
HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular Datasets
Witold Wydmański, Oleksii Bulenok, Marek Śmieja
Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabu…
Contrastive Hierarchical Clustering
Michał Znaleźniak, Przemysław Rola, Patryk Kaszuba +2
Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the g…
Hebbian Continual Representation Learning
Paweł Morawiecki, Andrii Krutsylo, Maciej Wołczyk +1
Continual Learning aims to bring machine learning into a more realistic scenario, where tasks are learned sequentially and the i.i.d. assumption is not preserved. Although this set…
SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifier
Bartosz Wójcik, Jacek Grela, Marek Śmieja +2
Deep neural networks present impressive performance, yet they cannot reliably estimate their predictive confidence, limiting their applicability in high-risk domains. We show that…
Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation
Sophie Steger, Bernhard C. Geiger, Marek Smieja
We connect the problem of semi-supervised clustering to constrained Markov aggregation, i.e., the task of partitioning the state space of a Markov chain. We achieve this connection…
MisConv: Convolutional Neural Networks for Missing Data
Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski +1
Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like image…
Pharmacoprint -- a combination of pharmacophore fingerprint and artificial intelligence as a tool for computer-aided drug design
Dawid Warszycki, Łukasz Struski, Marek Śmieja +2
Structural fingerprints and pharmacophore modeling are methodologies that have been used for at least two decades in various fields of cheminformatics: from similarity searching to…
PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka +4
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling. However, existing methods often lack the…
Flow-based SVDD for anomaly detection
Marcin Sendera, Marek Śmieja, Łukasz Maziarka +3
We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools. Contrary to other appro…
SONG: Self-Organizing Neural Graphs
Łukasz Struski, Tomasz Danel, Marek Śmieja +2
Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools. There are at least three advant…
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
Maciej Wołczyk, Bartosz Wójcik, Klaudia Bałazy +4
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by att…