Research map / Probabilistic and scientific modeling / Molecules and proteins
Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks
Agastya Kalra, Abdullah Rashwan, Wei-Shou Hsu, Pascal Poupart, Prashant Doshi, Georgios Trimponias
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 changed | Where | Measured | Effect |
|---|---|---|---|
| oSLRAU structure learning instead of random networks of equal size | SPN · Power | average log-likelihood: -2.83 -> -2.46 | Improved |
| oSLRAU structure learning versus random network structure | SPN · Network | average log-likelihood: -5.34 -> -4.27 | Improved |
| periodic pruning of stale subtrees (ablation) | oSLRAU · Power | log-likelihood / size: -2.46 -> -2.40; nodes 23360 -> 5330 | Improved |
| periodic pruning of stale subtrees (ablation) | oSLRAU · GasSen | log-likelihood: -102 -> -130 | Hurt |
| periodic pruning of stale subtrees (ablation) | oSLRAU · MSD | log-likelihood: -527.7 -> -526.8 | No clear effect |
| periodic pruning on a nonstationary ordered MNIST stream (ablation) | oSLRAU · MNIST ordered by label | generated samples | Mixed |
| oSLRAU versus RealNVP online | oSLRAU · MSD | average log-likelihood: -531.4 vs -362.4 | Hurt |
| oSLRAU instead of search-and-score for recurrent SPNs | RSPN · eegEye | average log-likelihood: 25.9 -> 36.9 | Improved |
| oSLRAU RSPN versus LSTM RNN | RSPN+oSLRAU · ozLevel | average log-likelihood: -30.1 vs -15.3 | Hurt |
Closest papers by meaning
- Bayesian Learning of Sum-Product Networks (NeurIPS 2019 · similarity 0.89)
- Sum-product networks: A survey (TPAMI 2021 · similarity 0.88)
- The Sum-Product Theorem: A Foundation for Learning Tractable Models (ICML 2016 · similarity 0.88)
- A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks (JMLR 2020 · similarity 0.86)
- Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs (ICLR 2024 · similarity 0.86)
- Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks (ICLR 2024 · similarity 0.85)
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.
