AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference

Emile van Krieken, Thiviyan Thanapalasingam, Jakub M. Tomczak, Frank Van Harmelen, Annette Ten Teije

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse concepts and hypothesis testing · 2 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
remove the prior p(P) used to sample beliefs for training the inference model (ablation)A-NeSI (predict) · Multi-digit MNISTAdd N=15accuracy: 75.90 -> 0.03Hurt
remove the prior p(P) (ablation)A-NeSI (predict) · Multi-digit MNISTAdd N=4accuracy: 92.56 -> 44.58Hurt
remove the prior p(P) (ablation)A-NeSI (predict) · Multi-digit MNISTAdd N=2accuracy: 95.96 -> 95.67No clear effect
explainable variant instead of prediction-only (ablation)A-NeSI · Multi-digit MNISTAdd N=15 (symbolic)accuracy: 75.90 -> 76.84Improved
explainable variant instead of prediction-only (ablation)A-NeSI · Multi-digit MNISTAdd N=15 (neural prediction)accuracy: 54.66 -> 61.77Improved
add symbolic pruning to prediction-only variant (ablation)A-NeSI · Multi-digit MNISTAdd N=15 (neural prediction)accuracy: 54.66 -> 59.88Improved
add symbolic pruning to prediction-only variant (ablation)A-NeSI · Multi-digit MNISTAdd N=2 (symbolic)accuracy: 95.96 -> 95.82No clear effect
neural prediction instead of symbolic predictionA-NeSI (predict) · Multi-digit MNISTAdd N=15accuracy: 75.90 -> 54.66Hurt
A-NeSI approximate inference instead of exact inference (DeepProbLog)A-NeSI (predict) · Multi-digit MNISTAdd N=2accuracy: 95.20 -> 95.96No clear effect
A-NeSI instead of Embed2Sym baselineA-NeSI (predict) · Multi-digit MNISTAdd N=15 (symbolic)accuracy: 60.46 -> 75.90Improved
train neural predictor with A-NeSI loop vs Embed2Sym without background knowledgeA-NeSI (predict) · Multi-digit MNISTAdd N=2 (neural prediction)accuracy: 84.35 -> 95.95Improved
A-NeSI instead of exact inference on 4x4 SudokuA-NeSI · Visual Sudoku N=4accuracy: 86.70 -> 89.70Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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