AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

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

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

AAAI 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
encode label space with SPAE CAT embeddings (scenario II) rather than raw labelsLinear predictor on MLC · 10 MLC benchmarksavg relative JAC vs LR: +24.07Improved
encode features with SPAE CAT embeddings (scenario I)LR · 10 MLC benchmarksavg relative JAC vs LR: -11.90Hurt
encode features with SPAE ACT embeddings (scenario I)LR · 10 MLC benchmarksavg relative EXA vs LR: +17.18Improved
combine ACT feature embedding with CAT label embedding (scenario III) (ablation)SPAE · 10 MLC benchmarksavg relative JAC vs LR: +24.07 -> +25.47Improved
use kNN decoding instead of tree decoding gCAT (ablation)SPAE CAT · MLC scenario IIavg relative JAC vs LR: +24.07 -> +22.83Hurt
use kNN decoding for MADE decoder (ablation)MADE · MLC scenario IIavg relative JAC vs LR: -30.42 -> +14.57Improved
remove up to half of label embedding components at random (ablation)SPAE CAT/ACT decoding · EXAEXA: degrades by less than 50% on average when half missingHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy