Research map / Label-efficient and robust learning / Recognition and long-tail
Fast Abductive Learning by Similarity-based Consistency Optimization
Yu-Xuan Huang, Wang-Zhou Dai, Le-Wen Cai, Stephen Muggleton, Yuan Jiang
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 |
|---|---|---|---|
| use similarity-based consistency (ABLSim) instead of NGS/DeepProbLog confidence-based search | neuro-symbolic learning from random init · HWF (CIFAR) | test accuracy (%): 66.0±14.5 -> 88.4±0.7 | Improved |
| ABLSim vs NGS-opt on easy MNIST Addition | ABLSim · MNIST Addition | test accuracy (%): 98.5±0.3 -> 98.8±0.1 | No clear effect |
| ABLSim vs NGS-opt on CIFAR Addition | ABLSim · Addition (CIFAR) | test accuracy (%): 88.7±0.8 -> 88.9±0.5 | No clear effect |
| increase beam width from 16 to 2048 (ablation) | ABLSim · CIFAR-10 Decimal Equation first iteration | successful abduction rate: 62% -> 75% | Improved |
| use similarity in consistency measure rather than confidence only (ABL-Conf) (ablation) | ABL · CIFAR-10 Decimal Equation | test perception accuracy | Improved |
| add supervised pre-training to ABL-Conf (ablation) | ABL-Conf · CIFAR-10 Decimal Equation | convergence speed | Mixed |
| weaken the knowledge base by removing rules in ABLSim (ablation) | ABLSim-10 · Theft Judicial Sentencing 10% labels | Micro-F1: 0.861 -> 0.851 | Hurt |
| ABLSim vs SS-ABL with partial KB | SS-ABL · Theft Judicial Sentencing 10% labels | Micro-F1: 0.833 -> 0.851 | Improved |
Closest papers by meaning
- Ambiguity-Aware Abductive Learning (ICML 2024 · similarity 0.91)
- Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts (ICML 2024 · similarity 0.89)
- Curriculum Abductive Learning (NeurIPS 2025 · similarity 0.87)
- Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection (AAAI 2025 · similarity 0.87)
- Safe Abductive Learning in the Presence of Inaccurate Rules (AAAI 2024 · similarity 0.87)
- Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments (AAAI 2026 · similarity 0.86)
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.
