Sum-Product Autoencoding: Encoding and Decoding Representations Using Sum-Product Networks

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 multilabel 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.

Authors

• Antonio Vergari University of Edinburgh
• Robert Peharz Eindhoven University of Technology Graz University of Technology
• Nicola Di Mauro
• Alejandro Molina
• Kristian Kersting
• Floriana Esposito

Keywords

No keywords are indexed for this paper.