Research map / Learning theory and algorithms / Prediction and decision losses
Post-Hoc Refinement for Multitask Symbolic Regression via Consensus-Accelerated Shapley Analysis
Xinyue Li, Wang Hu, Yu Zhang
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 bidirectional subexpression cooperative extraction (ablation) | MTGP-BS · 16 MTSR problems | MSE | Improved |
| use multi-model ensemble instead of single-model SHAP analysis (MTGP-B1) (ablation) | MTGP-BS · 16 MTSR problems | MSE | Improved |
| use consensus selection instead of simple SHAP averaging (MTGP-B2) (ablation) | MTGP-BS · 16 MTSR problems | MSE | Improved |
| add roulette wheel selection on top of voting-only consensus (MTGP-B3) (ablation) | MTGP-BS · 16 MTSR problems | MSE | Improved |
| apply the post-hoc refinement framework to baseline multitask algorithms | MO-MFEA, MFEA-DGD, BLKT-DE, MTDE-MKTA, MTES-KG · 16 MTSR problems | MSE | Improved |
| post-hoc refinement overhead on top of evolution | MTGP-BS · running time | runtime | No clear effect |
| choose number of ensemble models K=5 versus 3 to 11 (ablation) | MTGP-BS · Problem Set 3 | MSE and runtime | Mixed |
| compare MTGP-BS with five multitask baselines under Wilcoxon test | MTGP-BS · 16 MTSR problems (32 tasks) | MSE: 140 out of 160 direct comparisons significantly better | Improved |
Closest papers by meaning
- SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery (NeurIPS 2026 · similarity 0.87)
- Improving Monte Carlo Tree Search for Symbolic Regression (NeurIPS 2025 · similarity 0.85)
- MetaSymNet: A Tree-like Symbol Network with Adaptive Architecture and Activation Functions (AAAI 2025 · similarity 0.85)
- Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$ (ICML 2025 · similarity 0.85)
- Symbolic Regression with a Learned Concept Library (NeurIPS 2024 · similarity 0.85)
- Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length (ICLR 2025 · similarity 0.84)
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.
