GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions

Yang, Zebin; Zhang, Aijun; Sudjianto, Agus

doi:10.48550/arxiv.2003.07132

Cited by 8 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NAM can be viewed as a neural network implementation of GAM where shape functions are selected from a class of functions which can be realized by neural networks with a certain architecture. Similar approaches using neural networks for constructing GAMs and performing shape functions called GAMI-Net and the Adaptive Explainable Neural Networks (AxNNs) were proposed by Yang et al [15] and Chen et al [16], respectively. In order to avoid the neural network overfitting, an ensemble of gradient boosting machines producing shape functions was proposed by Konstantinov and Utkin [76].…”

Section: Related Workmentioning

confidence: 99%

“…The impact of every feature on the prediction is determined by its corresponding shape function. Similar methods using neural networks for constructing GAMs and performing shape functions called GAMI-Net and the Adaptive Explainable Neural Networks (AxNNs) were proposed by Yang et al [15] and Chen et al [16], respectively. LIME as well as other methods have been successfully applied to many machine learning models for explanation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SurvNAM: The machine learning survival model explanation

Utkin¹,

Satyukov²,

Konstantinov³

2021

Preprint

View full text Add to dashboard Cite

A new modification of the Neural Additive Model (NAM) called SurvNAM and its modifications are proposed to explain predictions of the black-box machine learning survival model. The method is based on applying the original NAM to solving the explanation problem in the framework of survival analysis. The basic idea behind SurvNAM is to train the network by means of a specific expected loss function which takes into account peculiarities of the survival model predictions and is based on approximating the black-box model by the extension of the Cox proportional hazards model which uses the well-known Generalized Additive Model (GAM) in place of the simple linear relationship of covariates. The proposed method SurvNAM allows performing the local and global explanation. A set of examples around the explained example is randomly generated for the local explanation. The global explanation uses the whole training dataset. The proposed modifications of SurvNAM are based on using the Lasso-based regularization for functions from GAM and for a special representation of the GAM functions using their weighted linear and non-linear parts, which is implemented as a shortcut connection. A lot of numerical experiments illustrate the SurvNAM efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SurvNAM: The machine learning survival model explanation

Utkin¹,

Satyukov²,

Konstantinov³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A linear combination of neural networks implementing shape functions in GAM is a basis for NAMs [15] which sufficiently extend the available explanation methods and, in fact, open a door for constructing a new class of methods. Similar approaches using neural networks to construct GAMs and to perform shape functions are the basis of methods called GAMI-Net [16] and AxNNs [17]. An architecture called the regression network which can be also regarded as a modification of NAM is proposed by O'Neill et al [61].…”

Section: Related Workmentioning

confidence: 99%

“…the GAM outcome is a linear combination of some functions of features. Several explanation models based on GAMs have been proposed, including the well-known Explainable Boosting Machine (EBM) [14], the Neural Additive Model (NAM) [15], GAMI-Net [16], the Adaptive Explainable Neural Networks [17]. The main peculiarity of the aforementioned surrogate models is that the influence or shape functions from GAM are obtained by training neural networks (in NAM or GAMI-Net) or by training the functions iteratively (EBM).…”

Section: Introductionmentioning

confidence: 99%

“…Another important problem, which can be met in explanation, is a lack of efficient methods for identifying interactive effects or interactions between features when only combinations of two and larger features explain predictions of a black-box model. This problem has been partially solved in NAM and its modifications [15,61,16] where pairs of features can be fed to separate subnetworks and provide shape functions of two variables as outputs of these networks. The main obstacle for implementing NAM with pairs of features is that a huge number of subnetworks should be trained.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention-like feature explanation for tabular data

Konstantinov¹,

Utkin²

2021

Preprint

View full text Add to dashboard Cite

A new method for local and global explanation of the machine learning black-box model predictions by tabular data is proposed. It is implemented as a system called AFEX (Attention-like Feature EXplanation) and consisting of two main parts. The first part is a set of the one-feature neural subnetworks which aim to get a specific representation for every feature in the form of a basis of shape functions. The subnetworks use shortcut connections with trainable parameters to improve the network performance. The second part of AFEX produces shape functions of features as the weighted sum of the basis shape functions where weights are computed by using an attention-like mechanism. AFEX identifies pairwise interactions between features based on pairwise multiplications of shape functions corresponding to different features. A modification of AFEX with incorporating an additional surrogate model which approximates the black-box model is proposed. AFEX is trained end-to-end on a whole dataset only once such that it does not require to train neural networks again in the explanation stage. Numerical experiments with synthetic and real data illustrate AFEX.

show abstract

Cost of Explainability in AI: An Example with Credit Scoring Models

Dessain,

Bentaleb,

Vinas

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

This paper examines the cost of explainability in machine learning models for credit scoring. The analysis is conducted under the constraint of meeting the regulatory requirements of the European Central Bank (ECB), using a real-life dataset of over 50,000 credit exposures. We compare the statistical and financial performances of black-box models, such as XGBoost and neural networks, with inherently explainable models like logistic regression and GAMs. Notably, statistical performance does not necessarily correlate with financial performance. Our results reveal a difference of 15 to 20 basis points in annual return on investment between the best performing black-box model and the best performing inherently explainable model, as cost of explainability. We also find that the cost of explainability increases together with the risk appetite.To enhance the interpretability of explainable models, we apply isotonic smoothing of features’ shape functions based on expert judgment. Our findings suggest that incorporating expert judgment in the form of isotonic smoothing improves the explainability without compromising the performance. These results have significant implications for the use of explainable models in credit risk assessment and for regulatory compliance.

show abstract

GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions

Cited by 8 publications

References 33 publications

SurvNAM: The machine learning survival model explanation

SurvNAM: The machine learning survival model explanation

Attention-like feature explanation for tabular data

Cost of Explainability in AI: An Example with Credit Scoring Models

Contact Info

Product

Resources

About