We convert per-model votes into auditable traces
and Shapley-like attributions for RF ensemble decisions. We
expose hooks in classify_signal() to log per-model logits, calibrated probabilities, weights, and OSR gates, enabling
timeline and contribution analyses with negligible overhead.
Our approach provides interpretable explanations for ensemble
classifications through vote tracing, model attribution, and disagreement analysis, enhancing trust and debugging capabilities
for RF signal classification systems.
Index Terms—Explainable AI, ensemble methods, RF signal
classification, Shapley values, vote attribution
https://grok.com/share/bGVnYWN5_37105d9b-e6a3-45f2-9346-a8d95357f166
IX. REPRODUCIBILITY
Run the complete pipeline with:
DATASET_FUNC=”my_dataset_module:iter_eval”
CLASSIFIER_SPEC=”ensemble_ml_classifier:EnsembleMLCmake traces && make figs && make tables-vt
&& make pdf
All source code and data generation scripts are included in
the repository >> bgilbert1984/Vote-Tracing-Model-Level-Explainability-for-RF-Signal-Classification-Ensembles: Explainable AI, ensemble methods, RF signal classification, exact Shapley values, vote attribution, open-set rejection
[PDF] The Shapley Value of Classifiers in Ensemble Games – arXiv
arxiv.orgMeasuring individual model importance based on contribution to …Forecast; Ensemble; Model importance; Shapley value; COVID-19 Forecasting … Thus, the obtained values may not precisely represent Shapley values …arxiv.org[PDF] Measuring individual model importance based on contribution to …Keywords: Forecast; Ensemble; Model importance; Shapley value;. COVID … nascent stages of thinking about and understanding Shapley values.arxiv.orgA Survey of Privacy-Preserving Model Explanations – arXivWithout knowledge of the target’s data distribution, it becomes challenging to learn an attack model by observing Shapley values. To mitigate …arxiv.orgLayerIF: Estimating Layer Quality for Large Language Models … – arXivMore recent work has used Shapley Values [56] to identify which layers contribute more to the model’s capabilities [57] . Other research has …arxiv.orgInterpreting Time Series Forecasts with LIME and SHAP – arXivGradient boosting builds an ensemble of decision trees by … SHAP derives from Shapley values in cooperative game theory and …arxiv.org[PDF] A principled approach for comparing Variable Importance – arXivNote that Shapley values assigns nonzero importance to X1, even though it does not appear in the true model. Importance was estimated using. Gradient Boosting …arxiv.orgA Guide to Feature Importance Methods for Scientific Inference – arXivTo account for the collaborative nature of FI, SAGE values use Shapley values … Ensemble Detectors and Background Knowledge. Progress in Artificial …arxiv.orgGeneralized SHAP: Generating multiple types of explanations in …Shapley’s values are model-agnostic, and the marginal contribution … Ensemble learning models trained on Sentinel-2 multispectral …arxiv.org[PDF] Your Model Is Unfair, Are You Even Aware? Inverse … – arXivFor LightGBM, ELI5 traces ensemble decision tree paths to determine how each step impacts the prediction. … We neither varied the model’s level …arxiv.org
model class reliance fisher rudin10
All Models are Wrong, but Many are Useful: Learning a Variable’s …
arxiv.org[PDF] Learning a Variable’s Importance by Studying an Entire Class of …Applying this approach to study variable importance, we define model class reliance. (MCR) as the highest and lowest degree to which any well-performing model …jmlr.csail.mit.eduAll Models are Wrong, but Many are Useful: Learning a Variable’s …In this paper, we propose model class reliance (MCR) as the range of VI values across all well-performing model in a prespecified class.pmc.ncbi.nlm.nih.govModel Class Reliance: Variable Importance Measures for any …Aaron Fisher · Cynthia Rudin · Francesca Dominici. Variable importance (VI) tools describe how much covariates contribute to a prediction model’s accuracy.researchgate.netModel class reliance: Variable importance measures for any …Papers; Model class reliance: Variable importance measures for any machine learning model class, from the “Rashomon” perspective …rmwinslow.comModel Class Reliance for Variable Importance (MCR) – N/LAB[1] Fisher, Rudin, and Dominici. “All Models are Wrong, but Many are Useful: Learning a Variable’s Importance by Studying an Entire Class of Prediction …nlab.org.uk[PDF] Variable Importance Duke Course NotesThis is called Model Class Reliance. Model Class Reliance. Let us define the set of all good models in class F to be the set of models with loss …users.cs.duke.eduModel Class Reliance for Demonstrating Variable ImportanceModel Class Reliance. MCR was developed by Fisher et al. to compute the feature importance bounds across all optimal models called the Rashomon set for Kernel ( …nhsx.github.ioAll Models are Wrong, but Many are Useful: Learning a Variable’s …Model class reliance (MCR) is proposed as the range of VI values across all well-performing model in a prespecified class, which gives a more comprehensive …semanticscholar.org[PDF] Model Class Reliance for Random Forests[7] Aaron Fisher, Cynthia Rudin, and Francesca Dominici. All models are wrong, but many are useful: Learning a variable’s importance by studying an entire …proceedings.neurips.cc
The Shapley Value of Classifiers in Ensemble Games10
The Shapley Value of Classifiers in Ensemble Games – arXiv
arxiv.orgThe Shapley Value of Classifiers in Ensemble GamesWe argue that the Shapley value of models in these games is an effective decision metric for choosing a high-performing subset of models from the ensemble. Our …dl.acm.org[PDF] The Shapley Value of Classifiers in Ensemble GamesThe Shapley value [41] of a classifier is the average marginal con- tribution of the model over the possible different permutations in which the ensemble can …research.ed.ac.ukThe official implementation of “The Shapley Value of Classifiers in …Shapley is a Python library for evaluating binary classifiers in a machine learning ensemble. The library consists of various methods to compute (approximate) …github.com[PDF] The Shapley Value of Classifiers in Ensemble GamesTroupe is defined – an efficient algorithm that allocates payoffs based on approximate Shapley values of the classifiers in ensemble games, arguing that the …semanticscholar.org(PDF) The Shapley Value of Classifiers in Ensemble GamesThe Shapley value defines a unique payoff scheme that satisfies many desiderata for the notion of data value. However, the Shapley value often …researchgate.net[PDF] The Shapley Value in Machine Learning – IJCAIFigure 1: The Shapley value can be used to solve cooperative games. An ensemble game is a machine learning application for it – models in an ensemble are …ijcai.orgThe Shapley Value of Classifiers in Ensemble Games. – DBLPBibliographic details on The Shapley Value of Classifiers in Ensemble Games.dblp.orgShapley Values as a Strategy for Ensemble Weights Estimation – MDPIThis study introduces a novel performance-based weighting scheme for ensemble learning using the Shapley value.mdpi.com[PDF] Approximating the Shapley Value without Marginal ContributionsThe Shapley value, which is arguably the most popular ap- proach for assigning a meaningful contribution value to play- ers in a cooperative game, has recently …ojs.aaai.org
ensemble interpretability neural network RF signal classification10
Ensemble learning for biomedical signal classification – Nature
nature.comConvolutional Neural Network and Ensemble Learning-Based …This paper develops an ensemble learning ADS-B radio signal recognition framework. Firstly, the research analyzes the data content characteristics of the ADS-B …mdpi.comEnsemble of Deep Learning Architectures with Machine … – NIHThis study addresses the use of deep learning combined with machine learning classifiers (DLxMLCs) for pneumonia classification from chest X-ray (CXR) images.pmc.ncbi.nlm.nih.govA comprehensive review on ensemble deep learningThis review paper provides comprehensive reviews of the various strategies for ensemble learning, especially in the case of deep learning.sciencedirect.com(PDF) Ensemble learning for biomedical signal classification: a high …By achieving a classification accuracy of 95.4%, the ensemble framework outperformed traditional classifiers in capturing subtle diagnostic variations. This …researchgate.netEnsemble modeling with machine learning and deep learning to …We develop a protocol to combine the power of ML and DL to generate a set of simple rules that are easy to interpret with high prediction power.academic.oup.com[PDF] a machine learning ensemble approach for interference … – Lex localisIn order to improve CRN throughput and decrease interference, this research presents a new machine learning ensemble method that mixes Random. Forest (RF) with …lex-localis.org[PDF] Deep and Ensemble Learning to Win the Army RCO AI Signal …The methods discussed are capable of correctly classifying waveforms at -10 dB SNR with over 63% accuracy and signals at +10 dB SNR with over 95% accuracy from …proceedings.scipy.org[PDF] YOLO for Radio Frequency Signal ClassificationWe adapt YOLO for signal classification to enable the automatic and efficient identification of various signal types within a power spectral density image.inldigitallibrary.inl.govTreeNet: Layered Decision Ensembles – arXivThe study investigates various types of models for the classification of medical image and proposed a hybrid model named Layered Decision …arxiv.org
Explaining a series of models by propagating Shapley values – Nature
6: Explaining a series of models comprised of a convolutional neural network feature extractor and a gradient boosted tree classifier. figure 6.
nature.com
Neural network models and shapley additive explanations for a …
Shapley additive explanations provide interpretability for neural networks. •. Interpretability analysis helps to modify neural network models. •. An effective …
sciencedirect.com
ShapG: new feature importance method based on the Shapley value
ShapG method is suitable for explaining any type of model, including complex neural network models or hybrid models. Report issue for preceding …
arxiv.org
Analysis of the Impact of Integrating Neural Networks into Ensemble …
In our research, the ensemble learning approach that combines message passing neural network (MPNN) and conditional adversarial generative …
mrs.org
(PDF) The Shapley Value of Classifiers in Ensemble Games
… Shapley values were calculated from. the remaining 50% of graphs. E.1 Neural network ensembles. We created an ensemble of. m= 10. 3. neural …
researchgate.net
Ensemble Modeling for Neural Networks using large datasets
Thus, the most cost-effective and effective method of using a large dataset to train a neural network is by ensemble modeling. Why use Ensemble …
analyticsvidhya.com
What are Shapley Values? | C3 AI Glossary Definitions & Examples
Convolutional Neural Network (CNN) · Correlation · Data Cleansing · Data … Feature importance can be calculated by computing Shapley values for all the …
c3.ai
Explainability In Machine Learning: Top Techniques – Arize AI
DeepExplainer runs on deep learning frameworks to add explainability to neural network models by using DeepLIFT and Shapley values.
arize.com
An artificial neural network−pharmacokinetic model and its …
The trigger of the current AI boom is deep learning, a machine-learning method using a deep neural network (DNN) in which the machine-learning …
ascpt.onlinelibrary.wiley.com
How to explain neural networks using SHAP | Your Data Teacher
It is the SHAP approach. Let’s see how to use it for explain and interpret a neural network in Python. If you want to know more about neural …
yourdatateacher.com