Interpretable machine learning has demonstrated impressive performance while preserving explainability. In particular, neural additive models (NAM) offer the interpretability to the black-box deep learning and achieve state-of-the-art accuracy among the large family of generalized additive models. In order to empower NAM with feature selection and improve the generalization, we propose the sparse neural additive models (SNAM) that employ the group sparsity regularization (e.g. Group LASSO), where each feature is learned by a sub-network whose trainable parameters are clustered as a group. We study the theoretical properties for SNAM with novel techniques to tackle the non-parametric truth, thus extending from classical sparse linear models such as the LASSO, which only works on the parametric truth.
Specifically, we show that SNAM with subgradient and proximal gradient descents provably converges to zero training loss as $t\to\infty$, and that the estimation error of SNAM vanishes asymptotically as $n\to\infty$. We also prove that SNAM, similar to LASSO, can have exact support recovery, i.e. perfect feature selection, with appropriate regularization. Moreover, we show that the SNAM can generalize well and preserve the `identifiability', recovering each feature's effect. We validate our theories via extensive experiments and further testify to the good accuracy and efficiency of SNAM.
Cluster-Based Generalized Additive Models Informed by Random Fourier Features
Department of Mathematics and Mathematical Statistics, Umeå University（数学与统计学系，乌梅大学）；Department of Statistics, The Pennsylvania State University（统计系，宾夕法尼亚州立大学）
Peter the Great St.Petersburg Polytechnic University（圣彼得堡彼得大帝理工大学）
A method for the local and global interpretation of a black-box model on the basis of the well-known generalized additive models is proposed. It can be viewed as an extension or a modification of the algorithm using the neural additive model. The method is based on using an ensemble of gradient boosting machines (GBMs) such that each GBM is learned on a single feature and produces a shape function of the feature. The ensemble is composed as a weighted sum of separate GBMs resulting a weighted sum of shape functions which form the generalized additive model. GBMs are built in parallel using ran…
In additive models with many nonparametric components, a number of regularized estimators have been proposed and proven to attain various error bounds under different combinations of sparsity and fixed smoothness conditions. Some of these error bounds match minimax rates in the corresponding settings. Some of the rate minimax methods are non-convex and computationally costly. From these perspectives, the existing solutions to the high-dimensional additive nonparametric regression problem are fragmented. In this paper, we propose a multi-resolution group Lasso (MR-GL) method in a unified approa…
Ecole Polytechnique Federale de Lausanne (EPFL)（洛桑联邦理工学院）；IBM Research（IBM研究院）
Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions. Besides flexibility and accuracy, a key benefit of these models is their interpretability: the transfer functions provide visual means for inspecting the models and identifying domain-specific relations between inputs and outputs. However, in large-scale problems involving the prediction of many related tasks, learning independently additive models results in a loss of model interpretability, and can cause over…
Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability
Department of Mathematics and Statistics（数学与统计学系）；Georgia State University（佐治亚州立大学）；Tri-institutional Center for Translational Research in Neuroimaging and Data Science（神经影像与数据科学转化研究三机构中心）
We consider the problem of predicting an outcome variable using $p$ covariates that are measured on $n$ independent observations, in the setting in which flexible and interpretable fits are desirable. We propose the fused lasso additive model (FLAM), in which each additive function is estimated to be piecewise constant with a small number of adaptively-chosen knots. FLAM is the solution to a convex optimization problem, for which a simple algorithm with guaranteed convergence to the global optimum is provided. FLAM is shown to be consistent in high dimensions, and an unbiased estimator of its …
Institut für Mathematik, Technische Universität Berlin（柏林工业大学数学研究所）；Department for AI in Society, Science, and Technology, Zuse Institute Berlin（柏林楚泽研究所社会、科学与技术人工智能系）
We study the effects of constrained optimization formulations and Frank-Wolfe algorithms for obtaining interpretable neural network predictions. Reformulating the Rate-Distortion Explanations (RDE) method for relevance attribution as a constrained optimization problem provides precise control over the sparsity of relevance maps. This enables a novel multi-rate as well as a relevance-ordering variant of RDE that both empirically outperform standard RDE and other baseline methods in a well-established comparison test. We showcase several deterministic and stochastic variants of the Frank-Wolfe a…
Optimal transport (OT) theory focuses, among all maps $T:\mathbb{R}^d\rightarrow \mathbb{R}^d$ that can morph a probability measure onto another, on those that are the ``thriftiest'', i.e. such that the averaged cost $c(x, T(x))$ between $x$ and its image $T(x)$ be as small as possible. Many computational approaches have been proposed to estimate such Monge maps when $c$ is the $\ell_2^2$ distance, e.g., using entropic maps [Pooladian'22], or neural networks [Makkuva'20, Korotin'20]. We propose a new model for transport maps, built on a family of translation invariant costs $c(x, y):=h(x-y)$, …
Bayesian optimization (BO) is a powerful approach to sample-efficient optimization of black-box objective functions. However, the application of BO to areas such as recommendation systems often requires taking the interpretability and simplicity of the configurations into consideration, a setting that has not been previously studied in the BO literature. To make BO useful for this setting, we present several regularization-based approaches that allow us to discover sparse and more interpretable configurations. We propose a novel differentiable relaxation based on homotopy continuation that mak…
The generalized partially linear additive model (GPLAM) is a flexible and interpretable approach to building predictive models. It combines features in an additive manner, allowing each to have either a linear or nonlinear effect on the response. However, the choice of which features to treat as linear or nonlinear is typically assumed known. Thus, to make a GPLAM a viable approach in situations in which little is known $a~priori$ about the features, one must overcome two primary model selection challenges: deciding which features to include in the model and determining which of these features…
Kyoto University（京都大学）；NTT Communication Science Laboratories（NTT通信科学实验室）；University College London（伦敦大学学院）；Aalto University（阿尔托大学）
We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality $d$ and small sample size $n$. More specifically, we consider a function defined by local sparse models, one at each data point. We introduce sample-wise network regularization to borrow strength across the models, and sample-wise exclusive group sparsity (a.k.a., $\ell_{1,2}$ norm) to introduce diversity into the choice of feature sets in the local models. The local models are interpretable in terms of similarity of their spars…
University of Gothenburg（哥德堡大学）；Chalmers University of Technology（查尔姆斯理工大学）
Non-parametric, additive models are able to capture complex data dependencies in a flexible, yet interpretable way. However, choosing the format of the additive components often requires non-trivial data exploration. Here, as an alternative, we propose PrAda-net, a one-hidden-layer neural network, trained with proximal gradient descent and adaptive lasso. PrAda-net automatically adjusts the size and architecture of the neural network to reflect the complexity and structure of the data. The compact network obtained by PrAda-net can be translated to additive model components, making it suitable …
Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models, whereas the alternative option of building an intrinsically interpretable ranking model with transparent and self-explainable structure remains unexplored. Developing fully-understandable ranking models is necessary in some scenarios (e.g., due to legal or policy constraints) where post-hoc methods cannot provide sufficiently accurate explanations. In this …
Google Research（谷歌研究院）；Microsoft Research（微软研究院）；Cohere；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；MIT（麻省理工学院）
Deep neural networks (DNNs) are powerful black-box predictors that have achieved impressive performance on a wide variety of tasks. However, their accuracy comes at the cost of intelligibility: it is usually unclear how they make their decisions. This hinders their applicability to high stakes decision-making domains such as healthcare. We propose Neural Additive Models (NAMs) which combine some of the expressivity of DNNs with the inherent intelligibility of generalized additive models. NAMs learn a linear combination of neural networks that each attend to a single input feature. These networ…
State University of New York at Buffalo（纽约州立大学布法罗分校）
Hospital readmissions have become one of the key measures of healthcare quality. Preventable readmissions have been identified as one of the primary targets for reducing costs and improving healthcare delivery. However, most data driven studies for understanding readmissions have produced black box classification and predictive models with moderate performance, which precludes them from being used effectively within the decision support systems in the hospitals. In this paper we present an application of structured sparsity-inducing norms for predicting readmission risk for patients based on t…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Hospital of Sick Children（病童医院）；Cornell University（康奈尔大学）；MIT（麻省理工学院）；Broad Institute（博德研究所）；Microsoft Research（微软研究院）
Generalized additive models (GAMs) have become a leading modelclass for interpretable machine learning. However, there are many algorithms for training GAMs, and these can learn different or even contradictory models, while being equally accurate. Which GAM should we trust? In this paper, we quantitatively and qualitatively investigate a variety of GAM algorithms on real and simulated datasets. We find that GAMs with high feature sparsity (only using afew variables to make predictions) can miss patterns in the data and be unfair to rare subpopulations. Our results suggest that inductive bias p…
Detecting Structural Heart Disease from Electrocardiograms via a Generalized Additive Model of Interpretable Foundation-Model Predictors
Department of Information Center, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College（信息中心部门，阜外医院，中国医学科学院和北京协和医学院）；The Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；National Clinical Research Center for Cardiovascular Diseases, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College（心血管疾病临床医学研究中心，阜外医院，中国医学科学院和北京协和医学院）
Machine Learning algorithms are increasingly being used in recent years due to their flexibility in model fitting and increased predictive performance. However, the complexity of the models makes them hard for the data analyst to interpret the results and explain them without additional tools. This has led to much research in developing various approaches to understand the model behavior. In this paper, we present the Explainable Neural Network (xNN), a structured neural network designed especially to learn interpretable features. Unlike fully connected neural networks, the features engineered…
Aston University（阿斯顿大学）；University of Sussex（萨塞克斯大学）；University of Birmingham（伯明翰大学）；Massachusetts Institute of Technology（麻省理工学院）
Ubiquitous linear Gaussian exploratory tools such as principle component analysis (PCA) and factor analysis (FA) remain widely used as tools for: exploratory analysis, pre-processing, data visualization and related tasks. However, due to their rigid assumptions including crowding of high dimensional data, they have been replaced in many settings by more flexible and still interpretable latent feature models. The Feature allocation is usually modelled using discrete latent variables assumed to follow either parametric Beta-Bernoulli distribution or Bayesian nonparametric prior. In this work we …
We present a unified framework for estimation and analysis of generalized additive models in high dimensions. The framework defines a large class of penalized regression estimators, encompassing many existing methods. An efficient computational algorithm for this class is presented that easily scales to thousands of observations and features. We prove minimax optimal convergence bounds for this class under a weak compatibility condition. In addition, we characterize the rate of convergence when this compatibility condition is not met. Finally, we also show that the optimal penalty parameters f…
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
In the age of big data and interpretable machine learning, approaches need to work at scale and at the same time allow for a clear mathematical understanding of the method's inner workings. While there exist inherently interpretable semi-parametric regression techniques for large-scale applications to account for non-linearity in the data, their model complexity is still often restricted. One of the main limitations are missing interactions in these models, which are not included for the sake of better interpretability, but also due to untenable computational costs. To address this shortcoming…
HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases
Center for AI Research, VinUniversity（文大人工智能研究中心）；University of Florida（佛罗里达大学）；Posts and Telecommunications Institute of Technology（邮电技术学院）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
The Pennsylvania State University（宾夕法尼亚州立大学）；Duke University（杜克大学）
The main idea of canonical correlation analysis (CCA) is to map different views onto a common latent space with maximum correlation. We propose a deep interpretable variational canonical correlation analysis (DICCA) for multi-view learning. The developed model extends the existing latent variable model for linear CCA to nonlinear models through the use of deep generative networks. DICCA is designed to disentangle both the shared and view-specific variations for multi-view data. To further make the model more interpretable, we place a sparsity-inducing prior on the latent weight with a structur…
Massachusetts Institute of Technology（麻省理工学院）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules. We consider rules in both conjunctive normal form (AND-of-ORs) and disjunctive normal form (OR-of-ANDs). A principled objective function is proposed to trade classification accuracy and interpretability, where we use Hamming loss to characterize accuracy and sparsity to characterize interpretability. We propose efficient procedures to optimize these objectives based on linear programming (LP) relaxation, block coordinate descent, and …
Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models. Since many natural phenomenon exhibit sparse structures, enforcing sparsity on learned models reveals the underlying task relationship. Moreover, different sparsification degrees from a fully connected graph uncover various types of structures, like cliques, trees, lines, clusters or fully disconnected graphs. In this paper, we propose a bilevel formulation of multi-task learning that induces sparse graphs, thus, revealing the underly…
Additive nonparametric regression models provide an attractive tool for variable selection in high dimensions when the relationship between the response and predictors is complex. They offer greater flexibility compared to parametric non-linear regression models and better interpretability and scalability than the non-parametric regression models. However, achieving sparsity simultaneously in the number of nonparametric components as well as in the variables within each nonparametric component poses a stiff computational challenge. In this article, we develop a novel Bayesian additive regressi…
University for Applied Science Würzburg-Schweinfurt（维尔茨堡-施韦因富特应用科学大学）
Transfer learning is focused on the reuse of supervised learning models in a new context. Prominent applications can be found in robotics, image processing or web mining. In these fields, the learning scenarios are naturally changing but often remain related to each other motivating the reuse of existing supervised models. Current transfer learning models are neither sparse nor interpretable. Sparsity is very desirable if the methods have to be used in technically limited environments and interpretability is getting more critical due to privacy regulations. In this work, we propose two transfe…
Many biological learning systems such as the mushroom body, hippocampus, and cerebellum are built from sparsely connected networks of neurons. For a new understanding of such networks, we study the function spaces induced by sparse random features and characterize what functions may and may not be learned. A network with $d$ inputs per neuron is found to be equivalent to an additive model of order $d$, whereas with a degree distribution the network combines additive terms of different orders. We identify three specific advantages of sparsity: additive function approximation is a powerful induc…
University of Washington（华盛顿大学）；Institute for Learning & Brain Sciences（学习与脑科学研究所）
Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data. Far less attention has been paid to making these generative models interpretable. In many scenarios, ranging from scientific applications to finance, the observed variables have a natural grouping. It is often of interest to understand systems of interaction amongst these groups, and latent factor models (LFMs) are an attractive approach. However, traditional LFMs are limited by assuming a linear correlation structure. We present an output interpretable VAE (oi-VAE) for…
Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) Optimizing sparse logical models such as decision trees; (2) Optimiza…
Duke University（杜克大学）；University of British Columbia（不列颠哥伦比亚大学）
We present fast classification techniques for sparse generalized linear and additive models. These techniques can handle thousands of features and thousands of observations in minutes, even in the presence of many highly correlated features. For fast sparse logistic regression, our computational speed-up over other best-subset search techniques owes to linear and quadratic surrogate cuts for the logistic loss that allow us to efficiently screen features for elimination, as well as use of a priority queue that favors a more uniform exploration of features. As an alternative to the logistic loss…
RWTH Aachen（亚琛工业大学）；LMU Munich（慕尼黑大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）
Combining additive models and neural networks allows to broaden the scope of statistical regression and extend deep learning-based approaches by interpretable structured additive predictors at the same time. Existing attempts uniting the two modeling approaches are, however, limited to very specific combinations and, more importantly, involve an identifiability issue. As a consequence, interpretability and stable estimation are typically lost. We propose a general framework to combine structured regression models and deep neural networks into a unifying network architecture. To overcome the in…
Studies involving both randomized experiments as well as observational data typically involve time-to-event outcomes such as time-to-failure, death or onset of an adverse condition. Such outcomes are typically subject to censoring due to loss of follow-up and established statistical practice involves comparing treatment efficacy in terms of hazard ratios between the treated and control groups. In this paper we propose a statistical approach to recovering sparse phenogroups (or subtypes) that demonstrate differential treatment effects as compared to the study population. Our approach involves m…
Harvard University（哈佛大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
Originally designed to model text, topic modeling has become a powerful tool for uncovering latent structure in domains including medicine, finance, and vision. The goals for the model vary depending on the application: in some cases, the discovered topics may be used for prediction or some other downstream task. In other cases, the content of the topic itself may be of intrinsic scientific interest. Unfortunately, even using modern sparse techniques, the discovered topics are often difficult to interpret due to the high dimensionality of the underlying space. To improve topic interpretability…
We consider the problem of estimating a regression function in the common situation where the number of features is small, where interpretability of the model is a high priority, and where simple linear or additive models fail to provide adequate performance. To address this problem, we present GapTV, an approach that is conceptually related both to CART and to the more recent CRISP algorithm, a state-of-the-art alternative method for interpretable nonlinear regression. GapTV divides the feature space into blocks of constant value and fits the value of all blocks jointly via a convex optimizat…
