Fetching the paper…
Reading the bibliography…
This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions.
Canonical expressions in Boolean algebra
A. Blake · 1937
Earlier work this paper cites.
The problem of simplifying truth functions
W. V. Quine · 1952
Earlier work this paper cites.
A value for n n -person games
L. S. Shapley · 1953
Earlier work this paper cites.
A way to simplify truth functions
W. V. Quine · 1955
Earlier work this paper cites.
Minimization of boolean functions
E. J. McCluskey · 1956
Earlier work this paper cites.
On cores and prime implicants of truth functions
W. V. Quine · 1959
Earlier work this paper cites.
Minimal input solutions
S. L. Hight · 1971
Earlier work this paper cites.
The Shapley value: essays in honor of Lloyd S. Shapley
A. E. Roth · 1988
Earlier work this paper cites.
Boolean reasoning: the logic of Boolean equations
F. M. Brown · 1990
Earlier work this paper cites.
Hypothesis classification, abductive diagnosis and therapy
G. Friedrich, G. Gottlob, and W. Nejdl · 1990
Earlier work this paper cites.
Abductive and default reasoning: A computational core
B. Selman and H. J. Levesque · 1990
Earlier work this paper cites.
The complexity of logic-based abduction
T. Eiter and G. Gottlob · 1995
Earlier work this paper cites.
Equational characterizations of boolean function classes
O. Ekin, S. Foldes, P. L. Hammer, and L. Hellerstein · 2000
Earlier work this paper cites.
A knowledge compilation map
A. Darwiche and P. Marquis · 2002
Earlier work this paper cites.
The Shapley value
E. Winter · 2002
Earlier work this paper cites.
Computational Complexity - A Modern Approach
S. Arora and B. Barak · 2009
Earlier work this paper cites.
An efficient explanation of individual classifications using game theory
E. Strumbelj and I. Kononenko · 2010
Earlier work this paper cites.
Boolean Functions - Theory, Algorithms, and Applications
Y. Crama and P. L. Hammer · 2011
Earlier work this paper cites.
Orange: Data mining toolbox in python
J. Demšar, T. Curk, A. Erjavec, Črt Gorup, T. Hočevar, M. Milutinovič, M. Možina, M. Polajnar, M. Toplak, A. Starič, M. Štajdohar, L. Umek, L. Žagar, J. Žbontar, M. Žitnik, and B. Zupan · 2013
Earlier work this paper cites.
Explaining prediction models and individual predictions with feature contributions
E. Strumbelj and I. Kononenko · 2014
Earlier work this paper cites.
Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems
A. Datta, S. Sen, and Y. Zick · 2016
Earlier work this paper cites.
"why should I trust you?": Explaining the predictions of any classifier
M. T. Ribeiro, S. Singh, and C. Guestrin · 2016
Earlier work this paper cites.
A unified approach to interpreting model predictions
S. M. Lundberg and S. Lee · 2017
Earlier work this paper cites.
Pmlb: a large benchmark suite for machine learning evaluation and comparison
R. S. Olson, W. La Cava, P. Orzechowski, R. J. Urbanowicz, and J. H. Moore · 2017
Earlier work this paper cites.
Anchors: High-precision model-agnostic explanations
M. T. Ribeiro, S. Singh, and C. Guestrin · 2018
Earlier work this paper cites.
L-Shapley and C-Shapley: Efficient model interpretation for structured data
J. Chen, L. Song, M. J. Wainwright, and M. I. Jordan · 2019
Earlier work this paper cites.
A survey of methods for explaining black box models
R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, and D. Pedreschi · 2019
Earlier work this paper cites.
Abduction-based explanations for machine learning models
A. Ignatiev, N. Narodytska, and J. Marques-Silva · 2019
Earlier work this paper cites.
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
W. Samek, G. Montavon, A. Vedaldi, L. K. Hansen, and K. Müller, editors · 2019
Earlier work this paper cites.
Deep neural network or dermatologist?
K. Young, G. Booth, B. Simpson, R. Dutton, and S. Shrapnel · 2019
Earlier work this paper cites.
Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI
A. B. Arrieta, N. D. Rodríguez, J. D. Ser, A. Bennetot, S. Tabik, A. Barbado, S. García, S. Gil-Lopez, D. Molina, R. Benjamins, R. Chatila, and F. Herrera · 2020
Earlier work this paper cites.
On tractable XAI queries based on compiled representations
G. Audemard, F. Koriche, and P. Marquis · 2020
Earlier work this paper cites.
Model interpretability through the lens of computational complexity
P. Barceló, M. Monet, J. Pérez, and B. Subercaseaux · 2020
Earlier work this paper cites.
Understanding global feature contributions with additive importance measures
I. Covert, S. M. Lundberg, and S. Lee · 2020
Earlier work this paper cites.
On the reasons behind decisions
A. Darwiche and A. Hirth · 2020
Earlier work this paper cites.
Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
C. Frye, C. Rowat, and I. Feige · 2020
Earlier work this paper cites.
Towards trustable explainable AI
A. Ignatiev · 2020
Earlier work this paper cites.
Towards formal fairness in machine learning
A. Ignatiev, M. C. Cooper, M. Siala, E. Hebrard, and J. Marques-Silva · 2020
Cited alongside, same era.
From contrastive to abductive explanations and back again
A. Ignatiev, N. Narodytska, N. Asher, and J. Marques-Silva · 2020
Cited alongside, same era.
Machine learning explainability in breast cancer survival
T. Jansen, G. Geleijnse, M. Van Maaren, M. P. Hendriks, A. Ten Teije, and A. Moncada-Torres · 2020
Cited alongside, same era.
Problems with Shapley-value-based explanations as feature importance measures
I. E. Kumar, S. Venkatasubramanian, C. Scheidegger, and S. A. Friedler · 2020
Cited alongside, same era.
From local explanations to global understanding with explainable AI for trees
S. M. Lundberg, G. G. Erion, H. Chen, A. J. DeGrave, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S. Lee · 2020
Cited alongside, same era.
Explaining naive bayes and other linear classifiers with polynomial time and delay
Appley: Approximate Shapley value for model explainability in linear time
M. S. Alam and Y. Xie · 2022
Later among the works it cites.
Counterfactual Shapley additive explanations
E. Albini, J. Long, D. Dervovic, and D. Magazzeni · 2022
Later among the works it cites.
An explainable machine learning framework for lung cancer hospital length of stay prediction
B. Alsinglawi, O. Alshari, M. Alorjani, O. Mubin, F. Alnajjar, M. Novoa, and O. Darwish · 2022
Later among the works it cites.
On computing probabilistic explanations for decision trees
M. Arenas, P. Barceló, M. Romero, and B. Subercaseaux · 2022
Later among the works it cites.
Relation between prognostics predictor evaluation metrics and local interpretability SHAP values
M. L. Baptista, K. Goebel, and E. M. Henriques · 2022
Later among the works it cites.
Explaining Black Box with Visual Exploration of Latent Space
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
J. Marques-Silva, T. Gerspacher, M. C. Cooper, A. Ignatiev, and N. Narodytska · 2020
Cited alongside, same era.
The explanation game: Explaining machine learning models using Shapley values
L. Merrick and A. Taly · 2020
Cited alongside, same era.
Interpretable machine learning
C. Molnar · 2020
Cited alongside, same era.
The many Shapley values for model explanation
M. Sundararajan and A. Najmi · 2020
Cited alongside, same era.
Copy number variation in plasma as a tool for lung cancer prediction using extreme gradient boosting (xgboost) classifier
D. Yu, Z. Liu, C. Su, Y. Han, X. Duan, R. Zhang, X. Liu, Y. Yang, and S. Xu · 2020
Cited alongside, same era.
Towards rigorous interpretations: a formalisation of feature attribution
D. Afchar, V. Guigue, and R. Hennequin · 2021
Cited alongside, same era.
M. Arenas, P. Barceló, L. E. Bertossi, and M. Monet · 2021
Cited alongside, same era.
F. Bodria, S. Rinzivillo, D. Fadda, R. Guidotti, F. Giannotti, and D. Pedreschi · 2022
Later among the works it cites.
Exact Shapley values for local and model-true explanations of decision tree ensembles
T. W. Campbell, H. Roder, R. W. Georgantas III, and J. Roder · 2022
Later among the works it cites.
On the tractability of SHAP explanations
G. V. den Broeck, A. Lykov, M. Schleich, and D. Suciu · 2022
Later among the works it cites.
Explainable artificial intelligence for magnetic resonance imaging aging brainprints: Grounds and challenges
I. B. Galazzo, F. Cruciani, L. Brusini, A. M. A. Salih, P. Radeva, S. F. Storti, and G. Menegaz · 2022
Later among the works it cites.
Sufficient reasons for classifier decisions in the presence of domain constraints
N. Gorji and S. Rubin · 2022
Later among the works it cites.
Stable and actionable explanations of black-box models through factual and counterfactual rules
R. Guidotti, A. Monreale, S. Ruggieri, F. Naretto, F. Turini, D. Pedreschi, and F. Giannotti · 2022
Later among the works it cites.
Feature necessity & relevancy in ML classifier explanations
X. Huang, M. C. Cooper, A. Morgado, J. Planes, and J. Marques-Silva · 2022
Later among the works it cites.
On tackling explanation redundancy in decision trees
Y. Izza, A. Ignatiev, and J. Marques-Silva · 2022
Later among the works it cites.
FastSHAP: Real-time Shapley value estimation
N. Jethani, M. Sudarshan, I. C. Covert, S. Lee, and R. Ranganath · 2022
Later among the works it cites.
Explanation of pseudo-boolean functions using cooperative game theory and prime implicants
C. Labreuche · 2022
Later among the works it cites.
Characterizing impact of positive lymph node number in endometrial cancer using machine-learning: A better prognostic indicator than figo staging?
C. Ladbury, R. Li, J. Shiao, J. Liu, M. Cristea, E. Han, T. Dellinger, S. Lee, E. Wang, C. Fisher, et al · 2022
Later among the works it cites.
Diagnosis of parkinson’s disease based on SHAP value feature selection
Y. Liu, Z. Liu, X. Luo, and H. Zhao · 2022
Later among the works it cites.
Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022)
H. W. Loh, C. P. Ooi, S. Seoni, P. D. Barua, F. Molinari, and U. R. Acharya · 2022
Later among the works it cites.
Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms
M. Ma, R. Liu, C. Wen, W. Xu, Z. Xu, S. Wang, J. Wu, D. Pan, B. Zheng, G. Qin, et al · 2022
Later among the works it cites.
Logic-based explainability in machine learning
J. Marques-Silva · 2022
Later among the works it cites.
Delivering trustworthy AI through formal XAI
J. Marques-Silva and A. Ignatiev · 2022
Later among the works it cites.
Explainable artificial intelligence: a comprehensive review
D. Minh, H. X. Wang, Y. F. Li, and T. N. Nguyen · 2022
Later among the works it cites.
The Shapley value in machine learning
B. Rozemberczki, L. Watson, P. Bayer, H. Yang, O. Kiss, S. Nilsson, and R. Sarkar · 2022
Later among the works it cites.
A modularized framework for explaining black box classifiers for text data
M. Sarvmaili, R. Guidotti, A. Monreale, A. Soares, Z. Sadeghi, F. Giannotti, D. Pedreschi, and S. Matwin · 2022
Later among the works it cites.
Application of machine learning techniques for predicting survival in ovarian cancer
A. Sorayaie Azar, S. Babaei Rikan, A. Naemi, J. Bagherzadeh Mohasefi, H. Pirnejad, M. Bagherzadeh Mohasefi, and U. K. Wiil · 2022
Later among the works it cites.
Understanding peace through the world news
V. Voukelatou, I. Miliou, F. Giannotti, and L. Pappalardo · 2022
Later among the works it cites.
The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study
Y. Wang, J. Lang, J. Z. Zuo, Y. Dong, Z. Hu, X. Xu, Y. Zhang, Q. Wang, L. Yang, S. T. Wong, et al · 2022
Later among the works it cites.
Rational Shapley values
D. S. Watson · 2022
Later among the works it cites.
Machine learning to refine prognostic and predictive nodal burden thresholds for post-operative radiotherapy in completely resected stage iii-n2 non-small cell lung cancer
R. Zarinshenas, C. Ladbury, H. McGee, D. Raz, L. Erhunmwunsee, R. Pathak, S. Glaser, R. Salgia, T. Williams, and A. Amini · 2022
Later among the works it cites.
A machine learning model based on ultrasound image features to assess the risk of sentinel lymph node metastasis in breast cancer patients: Applications of scikit-learn and SHAP
G. Zhang, Y. Shi, P. Yin, F. Liu, Y. Fang, X. Li, Q. Zhang, and Z. Zhang · 2022
Later among the works it cites.
Applications of explainable artificial intelligence in diagnosis and surgery
Y. Zhang, Y. Weng, and J. Lund · 2022
Later among the works it cites.
Explainable ensemble learning model improves identification of candidates for oral cancer screening
J. Adeoye, L.-W. Zheng, P. Thomson, S.-W. Choi, and Y.-X. Su · 2023
Closest in time.
eXplainable AI allows predicting upper limb rehabilitation outcomes in sub-acute stroke patients
M. Gandolfi, I. B. Galazzo, R. G. Pavan, F. Cruciani, N. Valè, A. Picelli, S. F. Storti, N. Smania, and G. Menegaz · 2023
Closest in time.
Machine learning for prediction of in-hospital mortality in lung cancer patients admitted to intensive care unit
T. Huang, D. Le, L. Yuan, S. Xu, and X. Peng · 2023
Closest in time.
Feature necessity & relevancy in ML classifier explanations
X. Huang, M. C. Cooper, A. Morgado, J. Planes, and J. Marques-Silva · 2023
Closest in time.
Solving explainability queries with quantification: The case of feature relevancy
X. Huang, Y. Izza, and J. Marques-Silva · 2023
Closest in time.