REVIEW 11 cited by
True to the Model or True to the Data?
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
Signed reviews
read the original abstract
A variety of recent papers discuss the application of Shapley values, a concept for explaining coalitional games, for feature attribution in machine learning. However, the correct way to connect a machine learning model to a coalitional game has been a source of controversy. The two main approaches that have been proposed differ in the way that they condition on known features, using either (1) an interventional or (2) an observational conditional expectation. While previous work has argued that one of the two approaches is preferable in general, we argue that the choice is application dependent. Furthermore, we argue that the choice comes down to whether it is desirable to be true to the model or true to the data. We use linear models to investigate this choice. After deriving an efficient method for calculating observational conditional expectation Shapley values for linear models, we investigate how correlation in simulated data impacts the convergence of observational conditional expectation Shapley values. Finally, we present two real data examples that we consider to be representative of possible use cases for feature attribution -- (1) credit risk modeling and (2) biological discovery. We show how a different choice of value function performs better in each scenario, and how possible attributions are impacted by modeling choices.
Forward citations
Cited by 11 Pith papers
-
RelShap: Relationally Consistent Shapley Explanations
RelShap restricts Shapley value explanations to relationally valid data configurations, using functional dependencies, domain constraints, and provenance, and provides a quotient-mode speedup that preserves exact Shap...
-
Identifying the post-pandemic determinants of low performing students in Latin America through Interpretable Machine Learning methods
Using stacked ML models and SHAP values on PISA 2022, the paper ranks the correlates of bottom and low performance in 10 Latin American countries, with grade repetition, family SES, and ICT access as the most consiste...
-
On Spectral Properties of Gradient-based Explanation Methods
Gradient-based explanations behave like frequency-band selectors: the gradient acts as a high-pass filter, perturbation as a low-pass filter, and their combination creates explanations that shift with the perturbation scale.
-
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.
-
ELATE: Evolutionary Language model for Automated Time-series Engineering
An LLM-guided evolutionary feature engineering method for time-series forecasting reduces RMSE by 8.4% on average across seven datasets.
-
A case for data valuation transparency via DValCards
Data valuation is unstable across imputation methods and can penalize minority groups; the paper proposes DValCards to document and constrain such valuation use.
-
On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
The paper introduces EF and ΔEF as spectral metrics, but ΔEF is derived from EF, making the complexity-faithfulness trade-off partly tautological.
-
Explaining deep neural network models for electricity price forecasting with XAI
SHAP and gradient explanations of five day-ahead electricity price forecasting DNNs reveal that the most recent price dominates forecasts, and new SSHAP aggregations help visualize these patterns.
-
Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
RL-Net, a neural rule-list model, reaches about 93% F1 on radar hand gestures after per-user fine-tuning while reducing rule complexity.
-
Complying with the EU AI Act: Innovations in Explainable and User-Centric Hand Gesture Recognition
A radar gesture recognition system with user-specific VAE thresholding and experience replay calibration reports 11.50% more flagged anomalies and 15.17% better user adaptation, plus a 97.5% characterization rate that...
-
On Process Awareness in Detecting Multi-stage Cyberattacks in Smart Grids
A co-simulation study reports that adding grid process data (OT/ET features) to a machine learning intrusion detector improves detection of IEC104 manipulation attacks relative to IT-only features, but no numeric eval...
Discussion (0). Continue with ORCID to comment.