Encoding and Decoding Representations with Sum- and Max-Product Networks

Abstract

Sum-Product Networks (SPNs) are deep density estimators allowing exact and tractable inference. While up to now SPNs have been employed as black-box inference machines, we exploit them as feature extractors for unsupervised Representation Learning. Representations learned by SPNs are rich probabilistic and hierarchical part-based features. SPNs converted into Max-Product Networks (MPNs) provide a way to decode these representations back to the original input space. In extensive experiments, SPN and MPN encoding and decoding schemes prove highly competitive for Multi-Label Classification tasks.

Cite

Text

Vergari et al. "Encoding and Decoding Representations with Sum- and Max-Product Networks." International Conference on Learning Representations, 2017.

Markdown

[Vergari et al. "Encoding and Decoding Representations with Sum- and Max-Product Networks." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/vergari2017iclr-encoding/)

BibTeX

@inproceedings{vergari2017iclr-encoding,
  title     = {{Encoding and Decoding Representations with Sum- and Max-Product Networks}},
  author    = {Vergari, Antonio and Peharz, Robert and Di Mauro, Nicola and Esposito, Floriana},
  booktitle = {International Conference on Learning Representations},
  year      = {2017},
  url       = {https://mlanthology.org/iclr/2017/vergari2017iclr-encoding/}
}