Structural Drift Repair in Decision Trees via Bayesian Model-Based Diagnosis

Yoav Zelinger, Meir Kalech
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:7992-8005, 2026.

Abstract

Decision trees are widely used in machine learning due to their interpretability. However, when the underlying data distribution changes—a phenomenon known as concept drift—their performance can degrade significantly. Retraining the model from scratch discards the learned structure and offers no insight into which nodes were actually affected. Prior work, APPETITE, used spectrum-based fault localization to identify and modify a single faulty node, but cannot handle drift that affects multiple nodes simultaneously or that demands structural changes to the tree. We propose BTAD ({Bayesian} Tree Adaptation for Drift), which formalizes the Decision Tree Concept Drift Problem as a Model-Based Diagnosis task and employs BARINEL, a {Bayesian} algorithm that ranks multi-node fault hypotheses across the entire tree. For repair, BTAD applies Subtree Re-fitting, replacing affected subtrees with ones fitted to the post-drift distribution. BTAD relies on lightweight node-level statistics and requires no access to the original training data. Experiments show that BTAD outperforms APPETITE in both recovery and localization, achieving accuracy comparable to full retraining—which provides no drift insight and requires the original data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-zelinger26a, title = {Structural Drift Repair in Decision Trees via {Bayesian} Model-Based Diagnosis}, author = {Zelinger, Yoav and Kalech, Meir}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {7992--8005}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/zelinger26a/zelinger26a.pdf}, url = {https://proceedings.mlr.press/v337/zelinger26a.html}, abstract = {Decision trees are widely used in machine learning due to their interpretability. However, when the underlying data distribution changes—a phenomenon known as concept drift—their performance can degrade significantly. Retraining the model from scratch discards the learned structure and offers no insight into which nodes were actually affected. Prior work, APPETITE, used spectrum-based fault localization to identify and modify a single faulty node, but cannot handle drift that affects multiple nodes simultaneously or that demands structural changes to the tree. We propose BTAD ({Bayesian} Tree Adaptation for Drift), which formalizes the Decision Tree Concept Drift Problem as a Model-Based Diagnosis task and employs BARINEL, a {Bayesian} algorithm that ranks multi-node fault hypotheses across the entire tree. For repair, BTAD applies Subtree Re-fitting, replacing affected subtrees with ones fitted to the post-drift distribution. BTAD relies on lightweight node-level statistics and requires no access to the original training data. Experiments show that BTAD outperforms APPETITE in both recovery and localization, achieving accuracy comparable to full retraining—which provides no drift insight and requires the original data.} }
Endnote
%0 Conference Paper %T Structural Drift Repair in Decision Trees via Bayesian Model-Based Diagnosis %A Yoav Zelinger %A Meir Kalech %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-zelinger26a %I PMLR %P 7992--8005 %U https://proceedings.mlr.press/v337/zelinger26a.html %V 337 %X Decision trees are widely used in machine learning due to their interpretability. However, when the underlying data distribution changes—a phenomenon known as concept drift—their performance can degrade significantly. Retraining the model from scratch discards the learned structure and offers no insight into which nodes were actually affected. Prior work, APPETITE, used spectrum-based fault localization to identify and modify a single faulty node, but cannot handle drift that affects multiple nodes simultaneously or that demands structural changes to the tree. We propose BTAD ({Bayesian} Tree Adaptation for Drift), which formalizes the Decision Tree Concept Drift Problem as a Model-Based Diagnosis task and employs BARINEL, a {Bayesian} algorithm that ranks multi-node fault hypotheses across the entire tree. For repair, BTAD applies Subtree Re-fitting, replacing affected subtrees with ones fitted to the post-drift distribution. BTAD relies on lightweight node-level statistics and requires no access to the original training data. Experiments show that BTAD outperforms APPETITE in both recovery and localization, achieving accuracy comparable to full retraining—which provides no drift insight and requires the original data.
APA
Zelinger, Y. & Kalech, M.. (2026). Structural Drift Repair in Decision Trees via Bayesian Model-Based Diagnosis. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:7992-8005 Available from https://proceedings.mlr.press/v337/zelinger26a.html.

Related Material