REVIEW 8 cited by
Explainable AI for Trees: From Local Explanations to Global Understanding
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet comparatively little attention has been paid to explaining their predictions. Here we significantly improve the interpretability of tree-based models through three main contributions: 1) The first polynomial time algorithm to compute optimal explanations based on game theory. 2) A new type of explanation that directly measures local feature interaction effects. 3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to i) identify high magnitude but low frequency non-linear mortality risk factors in the general US population, ii) highlight distinct population sub-groups with shared risk characteristics, iii) identify non-linear interaction effects among risk factors for chronic kidney disease, and iv) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model's performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains.
Forward citations
Cited by 8 Pith papers
-
Interpreting Multi-Branch Anti-Spoofing Architectures: Correlating Internal Strategy with Empirical Performance
A framework using covariance-based spectral signatures and TreeSHAP attributions on AASIST3 branches identifies four operational archetypes and a flawed specialization mode that explains high error rates on specific s...
-
Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
Aleatoric uncertainty selects between counterfactual and feature-importance explanations, epistemic uncertainty rejects unreliable explanations, and correlation experiments support the rule.
-
Unifying Attribution-Based Explanations Using Functional Decomposition
A unification framework for XAI attribution methods whose core canonical decomposition theorem fails because the components sum to the fully removed function rather than to the original function.
-
Wavelet Scattering Transform for Interpretable Schizophrenia Biomarker Discovery and Classification from Resting-State EEG
A single sentence stating the discovery directly. ≤ 300 chars.
-
Forma mentis networks predict creativity ratings of short texts via interpretable artificial intelligence in human and GPT-simulated raters
GPT-3.5's creativity ratings of short stories barely correlate with human ratings, and when scoring its own stories it leans on emotional features while humans lean on semantic network structure.
-
Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction
TabPFN and top tree-based models reach threat scores of about 0.62 to 0.64 for post-wildfire debris-flow prediction, with rainfall intensity and storm accumulation the most important features, and synthetic data augme...
-
Automating Credit Card Limit Adjustments Using Machine Learning
An XGBoost model with cost-sensitive learning reports Cohen's kappa of 0.81 against a bank committee's credit card limit decisions and is proposed to automate the process.
-
Integrating Explainable AI for Effective Malware Detection in Encrypted Network Traffic
An application of standard ensemble classifiers and SHAP to a private dataset reports >99% detection accuracy, but the evaluation may be leaky and no baselines are given.
Discussion (0). Continue with ORCID to comment.