74 citations · 140 across the 34 of their papers we have counts for
20 papers · 1 filter
SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
Mikołaj Zasada, Łukasz Struski, Jacek Tabor +1
Sparse Mixture-of-Experts (MoE) architectures enable scaling LLM parameters under a fixed inference budget by activating only a small subset of experts via top- routing. While t…
LAPLEX: The FFT of Learnable Laplace Kernels
Łukasz Struski, Hanna Blazhko, Piotr Kubaty +1
Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense paramete…
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…
SEMU: Singular Value Decomposition for Efficient Machine Unlearning
Marcin Sendera, Łukasz Struski, Kamil Książek +3
While the capabilities of generative foundational models have advanced rapidly in recent years, methods to prevent harmful and unsafe behaviors remain underdeveloped. Among the pre…
ProPML: Probability Partial Multi-label Learning
Łukasz Struski, Adam Pardyl, Jacek Tabor +1
Partial Multi-label Learning (PML) is a type of weakly supervised learning where each training instance corresponds to a set of candidate labels, among which only some are true. In…
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…
ProPaLL: Probabilistic Partial Label Learning
Łukasz Struski, Jacek Tabor, Bartosz Zieliński
Partial label learning is a type of weakly supervised learning, where each training instance corresponds to a set of candidate labels, among which only one is true. In this paper,…
Bounding Evidence and Estimating Log-Likelihood in VAE
Łukasz Struski, Marcin Mazur, Paweł Batorski +2
Many crucial problems in deep learning and statistical inference are caused by a variational gap, i.e., a difference between model evidence (log-likelihood) and evidence lower boun…
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…
Efficient GPU implementation of randomized SVD and its applications
Łukasz Struski, Paweł Morkisz, Przemysław Spurek +2
Matrix decompositions are ubiquitous in machine learning, including applications in dimensionality reduction, data compression and deep learning algorithms. Typical solutions for m…
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…
Estimating conditional density of missing values using deep Gaussian mixture model
Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski
We consider the problem of estimating the conditional probability distribution of missing values given the observed ones. We propose an approach, which combines the flexibility of…
A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints
Marek Śmieja, Łukasz Struski, Mário A. T. Figueiredo
In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints. In contrast to existing approaches…
Spatial Graph Convolutional Networks
Tomasz Danel, Przemysław Spurek, Jacek Tabor +4
Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compound…
Independent Component Analysis based on multiple data-weighting
Andrzej Bedychaj, Przemysław Spurek, Łukasz Struskim +1
Independent Component Analysis (ICA) - one of the basic tools in data analysis - aims to find a coordinate system in which the components of the data are independent. In this paper…
Set Aggregation Network as a Trainable Pooling Layer
Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak +3
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Bas…
Processing of missing data by neural networks
Marek Smieja, Łukasz Struski, Jacek Tabor +2
We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron's response in the first hidden layer b…
Semi-supervised model-based clustering with controlled clusters leakage
Marek Śmieja, Łukasz Struski, Jacek Tabor
In this paper, we focus on finding clusters in partially categorized data sets. We propose a semi-supervised version of Gaussian mixture model, called C3L, which retrieves natural…
Pointed subspace approach to incomplete data
Łukasz Struski, Marek Śmieja, Jacek Tabor
Incomplete data are often represented as vectors with filled missing attributes joined with flag vectors indicating missing components. In this paper we generalize this approach an…
Generalized RBF kernel for incomplete data
Łukasz Struski, Marek Śmieja, Jacek Tabor
We construct kernel, which generalizes the classical Gaussian RBF kernel to the case of incomplete data. We model the uncertainty contained in missing attributes makin…