mlsanityData to 7 Oct 2026

First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution

arXiv 2603.22346 ↗First posted 22 Mar 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We identify first-mover bias -- path-dependent concentration of SHAP feature importance from sequential residual fitting in gradient boosting -- as a mechanistic contributor to attribution instability under multicollinearity. Scaling up a single model amplifies this effect: a Large Single Model matching our method's total tree count produces the poorest attribution reproducibility of any approach tested. We show that model independence largely neutralizes first-mover bias. Both DASH (Diversified Aggregation of SHAP) and simple seed-averaging (Stochastic Retrain) restore stability by breaking the sequential dependency chain. At rho=0.9, both achieve stability ~0.977, while Single Best degrades to 0.958 and LSM to 0.938. On Breast Cancer, DASH improves stability from 0.376 to 0.925 (+0.549), outperforming Stochastic Retrain by +0.063. Under nonlinear DGPs, the advantage emerges at rho>=0.7. DASH provides two diagnostic tools -- the Feature Stability Index and Importance-Stability Plot -- that detect first-mover bias without ground truth. A crossed ANOVA with formal F-statistics confirms the mechanism: DASH shifts variance from model-dominated (40.6%) to data-dominated (73.6%). Software at https://github.com/DrakeCaraker/dash-shap

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 52 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

21 of 52 references.

References · 21

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  5. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  6. 2017Interpretation of Neural Networks is Fragilecited by 443
  7. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  8. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  9. 2017The (Un)reliability of saliency methodscited by 331
  10. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  11. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  12. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
9 more
  1. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  2. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156
  3. 2020True to the Model or True to the Data?cited by 123
  4. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  5. 2019On the Existence of Simpler Machine Learning Modelscited by 87
  6. 2022Impossibility Theorems for Feature Attributioncited by 78
  7. 2020General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Modelscited by 74
  8. 2024Provably Better Explanations with Optimized Aggregation of Feature Attributionscited by 6
  9. 2026Explanation Multiplicity in SHAP: Characterization and Assessmentcited by 5

Built on by

Not cited yet.