Research map / Probabilistic and scientific modeling / Molecules and proteins
KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
Binbin Yong, haoran pei, Jun Shen, Haoran Li, Qingguo Zhou, Zhao Su
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 |
|---|---|---|---|
| add sparsity and distinctiveness regularization (ablation) | KANFIS · five datasets | average features per rule: maximum reduction of 63.94% on Spambase | Improved |
| raise regularization from normal to high (ablation) | IT2-KANFIS · CCPP | RMSE: 4.1240 -> 4.2304 | Hurt |
| raise regularization from normal to high (ablation) | IT2-KANFIS · BCW | accuracy: 0.9912 -> 0.9474 | Hurt |
| lower regularization from normal to low (ablation) | IT2-KANFIS · Parkinsons | RMSE: 0.0397 -> 0.0403 | No clear effect |
| use IT2 instead of T1 fuzzy sets | KANFIS · CCPP | RMSE: 3.9542 -> 4.1240 | Hurt |
| use IT2 instead of T1 fuzzy sets | KANFIS · Spambase | accuracy: 0.9381 -> 0.9392 | No clear effect |
| replace MLP with KANFIS | MLP · MHR | accuracy: 0.7094 -> 0.7931 | Improved |
| replace KAN with KANFIS | KAN · CCPP | RMSE: 3.9313 -> 3.9542 | Hurt |
| replace grid-partition ANFIS with KANFIS in high dimensions | T1-ANFIS · BCW, Spambase | trainability | Improved |
| replace scatter-partition IT2-ANFIS with KANFIS | IT2-ANFIS · Spambase | accuracy: 0.8827 -> 0.9392 | Improved |
Closest papers by meaning
- Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees (AAAI 2024 · similarity 0.83)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.83)
- On the Independence Assumption in Neurosymbolic Learning (ICML 2024 · similarity 0.83)
- Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible (ICML 2025 · similarity 0.83)
- A learnability analysis on neuro-symbolic learning (NeurIPS 2025 · similarity 0.82)
- Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models (NeurIPS 2026 · similarity 0.82)
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.
