Sum-product autoencoding: Encoding and decoding representations using sum-product networks

Antonio Vergari, Alejandro Molina, Robert Peharz, Kristian Kersting, Nicola Di Mauro, Floriana Esposito

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


Sum-Product Networks (SPNs) are a deep probabilistic architecture that up to now has been successfully employed for tractable inference. Here, we extend their scope towards unsupervised representation learning: we encode samples into continuous and categorical embeddings and show that they can also be decoded back into the original input space by leveraging MPE inference. We characterize when this Sum-Product Autoencoding (SPAE) leads to equivalent reconstructions and extend it towards dealing with missing embedding information. Our experimental results on several multi-label classification problems demonstrate that SPAE is competitive with state-of-the-art autoencoder architectures, even if the SPNs were never trained to reconstruct their inputs.

Original languageEnglish
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Publication statusPublished - 1 Jan 2018


Dive into the research topics of 'Sum-product autoencoding: Encoding and decoding representations using sum-product networks'. Together they form a unique fingerprint.

Cite this