AI Paper Atlas

Research map / Large language models / Agents, code and math

Inferring the Invisible: Neuro-Symbolic Rule Discovery for Missing Value Imputation

Wendi Ren, Ke Wan, Junyu Leng, Shuang Li

ICLR 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation

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
add joint fine-tuning with soft-OR after sequential covering (ablation)NS-FCN · Synthetic disjunctive rule X5imputation accuracy: 0.8729 -> 1.0Improved
joint optimization of rule discovery and target inference vs impute-then-classifyNS-FCN · Heart Disease downstreamaccuracy: 0.89 vs best baseline 0.85Improved
model continuous features directly with soft predicates instead of discretizingNS-FCN · Heart Disease imputationimputation accuracy: trestbps 0.87 vs 0.88; oldpeak 0.78 vs 0.89 (GAIN)Mixed
use NS-FCN instead of MLP on simple Birds logicNS-FCN · Birdsimputation accuracy: 0.96 -> 0.95 (abnormal bird)Hurt
use NS-FCN rule learner instead of rule-based baselines (LEN, RRL, BRCG, DR-NET)NS-FCN · Birdsimputation accuracy: 0.57 -> 1.00Improved
change missingness from MCAR to MNAR (ablation)NS-FCN · Synthetic chain X5imputation accuracy: 0.95 -> 0.93No clear effect
change rule optimization order (ablation)NS-FCN · Synthetic chain (a)rule learning success: X4 imputation 0.87 vs 1.00 across ordersMixed

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