TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins

Across 4 benchmark datasets and 4 teacher architectures, TabKD achieves highest student-teacher agreement in 14 out of 16 configurations, outperforming 5 state-of-the-art baselines. It comes from a paper posted to arXiv on 30 September 2026. Data-free knowledge distillation enables model compression without original training data, critical for privacy-sensitive tabular domains. However, existing methods does not perform well on tabular data because they do not explicitly address feature interactions, the fundamental way tabular models encode predictive knowledge. We identify interaction diversity, systematic coverage of feature combinations, as an essential requirement for effective tabular distillation. To operationalize this insight, we propose TabKD, which learns adaptive feature bins aligned with teacher decision boundaries, then generates synthetic queries that maximize pairwise interaction coverage. We further show that interaction coverage strongly correlates with distillation quality, validating our core hypothesis. Our work establishes interaction-focused exploration as a principled framework for tabular model extraction.

Why it counts

Across 4 benchmark datasets and 4 teacher architectures, TabKD achieves highest student-teacher agreement in 14 out of 16 configurations, outperforming 5 state-of-the-art baselines.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.