66 citations · 104 across the 7 of their papers we have counts for
7 papers · 1 filter
Continual Learning with Guarantees via Weight Interval Constraints
Maciej Wołczyk, Karol J. Piczak, Bartosz Wójcik +5
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus…
On the relationship between disentanglement and multi-task learning
Łukasz Maziarka, Aleksandra Nowak, Maciej Wołczyk +1
One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adapta…
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…
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…
Finding the Optimal Network Depth in Classification Tasks
Bartosz Wójcik, Maciej Wołczyk, Klaudia Bałazy +1
We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rew…
SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder
Marek Śmieja, Maciej Wołczyk, Jacek Tabor +1
We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and which is implemented in a typical Wasserstein auto…
Hypernetwork functional image representation
Sylwester Klocek, Łukasz Maziarka, Maciej Wołczyk +3
Motivated by the human way of memorizing images we introduce their functional representation, where an image is represented by a neural network. For this purpose, we construct a hy…