1 code implementation • 27 Feb 2024 • Piotr Bielak, Tomasz Kajdanowicz
In recent years, unsupervised and self-supervised graph representation learning has gained popularity in the research community.
no code implementations • 27 Oct 2023 • Denis Janiak, Jakub Binkowski, Piotr Bielak, Tomasz Kajdanowicz
In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data.
1 code implementation • 3 Mar 2023 • Jakub Binkowski, Albert Sawczyn, Denis Janiak, Piotr Bielak, Tomasz Kajdanowicz
Graph machine learning models have been successfully deployed in a variety of application areas.
1 code implementation • 3 Mar 2023 • Kamil Tagowski, Piotr Bielak, Jakub Binkowski, Tomasz Kajdanowicz
A well-defined node embedding model should reflect both node features and the graph structure in the final embedding.
1 code implementation • 29 Jun 2021 • Edward Elson Kosasih, Joaquin Cabezas, Xavier Sumba, Piotr Bielak, Kamil Tagowski, Kelvin Idanwekhai, Benedict Aaron Tjandra, Arian Rokkum Jamasb
In order to advance large-scale graph machine learning, the Open Graph Benchmark Large Scale Challenge (OGB-LSC) was proposed at the KDD Cup 2021.
1 code implementation • 4 Jun 2021 • Piotr Bielak, Tomasz Kajdanowicz, Nitesh V. Chawla
The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling.
no code implementations • 29 Dec 2020 • Piotr Bielak, Tomasz Kajdanowicz, Nitesh V. Chawla
Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks.
1 code implementation • 6 Apr 2019 • Piotr Bielak, Kamil Tagowski, Maciej Falkiewicz, Tomasz Kajdanowicz, Nitesh V. Chawla
Experimental results on several downstream tasks, over seven real-world data sets, show that FILDNE is able to reduce memory and computational time costs while providing competitive quality measure gains with respect to the contemporary methods for representation learning on dynamic graphs.