Research map / Probabilistic and scientific modeling / Molecules and proteins
Semantic Probabilistic Layers for Neuro-Symbolic Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace the independent predictive layer with SPL | MLP · Simple Path | Exact: 30.1 -> 37.6 | Helped |
| Replace the independent predictive layer with SPL | MLP · Preference Learning | Exact: 18.2 -> 20.8 | Helped |
| Replace the independent predictive layer with SPL | ResNet-18 · Warcraft Shortest Path | Exact: 59.4 -> 78.2 | Helped |
| Use SPL instead of Semantic Loss | ResNet-18 · Warcraft Shortest Path | Hamming: 97.7 -> 96.3 | Hurt |
| Replace the independent predictive layer with SPL | ResNet-18 · Warcraft Shortest Path | Consistent: 61.2 -> 100.0 | Helped |
| Use SPL instead of HMCNN | HMLC models · 11 HMLC datasets | Exact Match | Helped |
| Increase mixture multiplication factor to k=4 (ablation) | Single-circuit SPL · HMLC validation datasets | Exact Match | Mixed |
| Increase circuit replicas to m≥4 (ablation) | Single-circuit SPL · HMLC validation datasets | Exact Match | Mixed |
| Use a deeper four-layer gating function instead of two layers (ablation) | Single-circuit SPL · HMLC validation datasets | Exact Match | Mixed |
| Overparameterize the constraint circuit (ablation) | Single-circuit SPL · HMLC validation datasets | Exact Match | Helped |
Closest papers by meaning
- Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees (AAAI 2024 · similarity 0.86)
- Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models (NeurIPS 2026 · similarity 0.86)
- Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible (ICML 2025 · similarity 0.85)
- On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models (NeurIPS 2024 · similarity 0.85)
- Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning (AAAI 2026 · similarity 0.85)
- On the Hardness of Probabilistic Neurosymbolic Learning (ICML 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.