@inproceedings{pronobis2017icml-padl,
  author =       {Pronobis, Andrzej and Ranganath, Avinash and Rao, Rajesh P. N.},
  title =        {{LibSPN}: A Library for Learning and Inference with {S}um-{P}roduct {N}etworks and {TensorFlow}},
  booktitle =    {ICML 2017 Workshop on Principled Approaches to Deep Learning},
  year =         2017,
  address =      {Sydney, Australia},
  month =        aug,
  url =          {http://www.libspn.org},
  abstract =     {Sum-Product Networks (SPNs) are a probabilistic deep architecture with solid theoretical foundations, which demonstrated state-of-the-art performance in several domains. Yet, surprisingly, there are no mature, general-purpose SPN implementations that would serve as a platform for the community of machine learning researchers centered around SPNs. Here, we present a new general-purpose Python library called LibSPN, which aims to become such a platform. The library is designed to make it straightforward and effortless to apply various SPN architectures to large-scale datasets and problems. The library achieves scalability and efficiency, thanks to a tight coupling with TensorFlow, a framework already used by a large community of researchers and developers in multiple domains. We describe the design and benefits of LibSPN, give several use-case examples, and demonstrate the applicability of the library to real-world problems on the example of spatial understanding in mobile robotics.}
}