activity
20182021
most citedRelative Molecule Self-Attention Transformer

3 citations · 3 across the 4 of their papers we have counts for

collaborators

11 papers

cs.LG20213 cited

Relative Molecule Self-Attention Transformer

Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel +5

Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learni…

cs.LG2021

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…

cs.LG2021

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…

physics.chem-ph2020

Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction

Agnieszka Pocha, Tomasz Danel, Łukasz Maziarka

Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing n…

cs.CV2020

Processing of incomplete images by (graph) convolutional neural networks

Tomasz Danel, Marek Śmieja, Łukasz Struski +2

We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which m…

cs.LG2020

Molecule Attention Transformer

Łukasz Maziarka, Tomasz Danel, Sławomir Mucha +3

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution…