The collaborative research center SFB876 brings together data mining and embedded systems. On the one hand, embedded systems can be further improved using machine learning. On the other hand, data mining algorithms can be realized in hardware, e.g. FPGAs, or run on GPGPUs. The restrictions of ubiquitous systems in computing power, memory, and energy demand new algorithms for known learning tasks. These resource bounded learning algorithms may also be applied on extremely large data bases on servers.
The deep learning based software "PyTorch Geometric" from the projects A6 and B2 is a PyTorch based library for deep learning on irregular input data like graphs, point clouds or manifolds. In addition to general data structures and processing methods, the software contains a variety of recently published methods from the fields of relational learning and 3D computing.
Last Friday, the software attracted some attention via Twitter and Facebook when it was specifically shared and recommended by Yann LeCun. Since then, it has been collecting around 250 stars a day on GitHub and can be found in particular among the trending repositories at GitHub.
PyTorch Geometric (PyG) is freely available on GitHub at https://github.com/rusty1s/pytorch_geometric.
more ...
