Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We describe a new unified class of methods, removal-based explanations, that are based on the principle of simulating feature removal to quantify each feature's influence. These methods vary in several respects, so we develop a framework that characterizes each method along three dimensions: 1) how the method removes features, 2) what model behavior the method explains, and 3) how the method summarizes each feature's influence. Our framework unifies 26 existing methods, including several of the most widely used approaches: SHAP, LIME, Meaningful Perturbations, and permutation tests. This newly understood class of explanation methods has rich connections that we examine using tools that have been largely overlooked by the explainability literature. To anchor removal-based explanations in cognitive psychology, we show that feature removal is a simple application of subtractive counterfactual reasoning. Ideas from cooperative game theory shed light on the relationships and trade-offs among different methods, and we derive conditions under which all removal-based explanations have information-theoretic interpretations. Through this analysis, we develop a unified framework that helps practitioners better understand model explanation tools, and that offers a strong theoretical foundation upon which future explainability research can build.
Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples. Instead, we propose to integrate a generative inpainter into three representative attribution methods to remove an input feature. Our proposed change improved all three methods in (1) generating more plausible counterfactual samples under the true data distribution; (2) being more accurate according to three metrics: object localization, deletion, …
Babylon Health（巴比伦健康公司）；Royal Holloway University of London（伦敦大学皇家霍洛威学院）
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of explaining why a particular classification was made explain how a different outcome can be achieved. This gives the recipients of the explanation a better way to understand the outcome, and provides an actionable suggestion. We show that the introduced method of Constrained Adversa…
ANITI, Université de Toulouse（图卢兹大学ANITI）；IRIT, Université de Toulouse III（图卢兹第三大学IRIT）；Monash University（莫纳什大学）；VMware Research（VMware研究）
Recent work proposed the computation of so-called PI-explanations of Naive Bayes Classifiers (NBCs). PI-explanations are subset-minimal sets of feature-value pairs that are sufficient for the prediction, and have been computed with state-of-the-art exact algorithms that are worst-case exponential in time and space. In contrast, we show that the computation of one PI-explanation for an NBC can be achieved in log-linear time, and that the same result also applies to the more general class of linear classifiers. Furthermore, we show that the enumeration of PI-explanations can be obtained with pol…
Recent work has shown great promise in explaining neural network behavior. In particular, feature attribution methods explain which features were most important to a model's prediction on a given input. However, for many tasks, simply knowing which features were important to a model's prediction may not provide enough insight to understand model behavior. The interactions between features within the model may better help us understand not only the model, but also why certain features are more important than others. In this work, we present Integrated Hessians, an extension of Integrated Gradie…
LaMME（LaMME实验室）；University Paris Saclay（巴黎萨克雷大学）；Stellantis（斯泰兰蒂斯）；ENSIIE（法国国立高等工业工程学院）；Quantmetry（Quantmetry公司）
To explain the decision of any model, we extend the notion of probabilistic Sufficient Explanations (P-SE). For each instance, this approach selects the minimal subset of features that is sufficient to yield the same prediction with high probability, while removing other features. The crux of P-SE is to compute the conditional probability of maintaining the same prediction. Therefore, we introduce an accurate and fast estimator of this probability via random Forests for any data $(\boldsymbol{X}, Y)$ and show its efficiency through a theoretical analysis of its consistency. As a consequence, w…
Avast Software（Avast软件公司）；Czech Technical University in Prague（布拉格捷克理工大学）
Learning from raw data input, thus limiting the need for feature engineering, is a component of many successful applications of machine learning methods in various domains. While many problems naturally translate into a vector representation directly usable in standard classifiers, a number of data sources have the natural form of structured data interchange formats (e.g., security logs in JSON/XML format). Existing methods, such as in Hierarchical Multiple Instance Learning (HMIL), allow learning from such data in their raw form. However, the explanation of the classifiers trained on raw stru…
Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where interpretability plays a key role already during learning have received much less attention. We propose three desiderata for explanations in general -- explicitness, faithfulness, and stability -- and show that existing methods do not satisfy them. In response, we design self-explaining models in stages, progressively generalizing linear classifiers to complex yet…
Carnegie Mellon University（卡内基梅隆大学）；University of Michigan（密歇根大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Determined AI
A common workflow in data exploration is to learn a low-dimensional representation of the data, identify groups of points in that representation, and examine the differences between the groups to determine what they represent. We treat this workflow as an interpretable machine learning problem by leveraging the model that learned the low-dimensional representation to help identify the key differences between the groups. To solve this problem, we introduce a new type of explanation, a Global Counterfactual Explanation (GCE), and our algorithm, Transitive Global Translations (TGT), for computing…
Carnegie Mellon University（卡内基梅隆大学）；Petuum Inc.（Petuum公司）；Arizona State University（亚利桑那州立大学）
Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, informati…
We propose a general model explanation system (MES) for "explaining" the output of black box classifiers. This paper describes extensions to Turner (2015), which is referred to frequently in the text. We use the motivating example of a classifier trained to detect fraud in a credit card transaction history. The key aspect is that we provide explanations applicable to a single prediction, rather than provide an interpretable set of parameters. We focus on explaining positive predictions (alerts). However, the presented methodology is symmetrically applicable to negative predictions.
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所（HIIT））；Aalto University（阿尔托大学）
We introduce a method, KL-LIME, for explaining predictions of Bayesian predictive models by projecting the information in the predictive distribution locally to a simpler, interpretable explanation model. The proposed approach combines the recent Local Interpretable Model-agnostic Explanations (LIME) method with ideas from Bayesian projection predictive variable selection methods. The information theoretic basis helps in navigating the trade-off between explanation fidelity and complexity. We demonstrate the method in explaining MNIST digit classifications made by a Bayesian deep convolutional…
University of Michigan（密歇根大学）；University of Washington（华盛顿大学）
Recently, interpretable models called self-explaining models (SEMs) have been proposed with the goal of providing interpretability robustness. We evaluate the interpretability robustness of SEMs and show that explanations provided by SEMs as currently proposed are not robust to adversarial inputs. Specifically, we successfully created adversarial inputs that do not change the model outputs but cause significant changes in the explanations. We find that even though current SEMs use stable co-efficients for mapping explanations to output labels, they do not consider the robustness of the first s…
Many decision making systems deployed in the real world are not static - a phenomenon known as model adaptation takes place over time. The need for transparency and interpretability of AI-based decision models is widely accepted and thus have been worked on extensively. Usually, explanation methods assume a static system that has to be explained. Explaining non-static systems is still an open research question, which poses the challenge how to explain model adaptations. In this contribution, we propose and (empirically) evaluate a framework for explaining model adaptations by contrastive expla…
Microsoft Research India（微软印度研究院）；University of Colorado Boulder（科罗拉多大学博尔德分校）
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations should satisfy two properties: feasibility of the counterfactual actions given user context and constraints, and diversity among the counterfactuals presented. To this end, we propose a framework for generating and evaluating a diverse set of counterfactual explanations based on deter…
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. Early attempts at explaining this phenomenon focused on nonlinearity and overfitting. We argue instead that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature. This explanation is supported by new quantitative results while giving …
There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, providing explanations of their decisions in some level of detail. These explanations are important to ensure algorithmic fairness, identify potential bias/problems in the training data, and to ensure that the algorithms perform as expected. However, explanations produced by these…
University of Surrey（萨里大学）；Amazon Web Services（亚马逊云科技）；Alan Turing Institute（艾伦·图灵研究所）
We present a novel form of explanation for Reinforcement Learning, based around the notion of intended outcome. These explanations describe the outcome an agent is trying to achieve by its actions. We provide a simple proof that general methods for post-hoc explanations of this nature are impossible in traditional reinforcement learning. Rather, the information needed for the explanations must be collected in conjunction with training the agent. We derive approaches designed to extract local explanations based on intention for several variants of Q-function approximation and prove consistency …
We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system's data inputs that causally drives the decision (i.e., changing the inputs in the set changes the decision) and is irreducible (i.e., changing any subset of the inputs does not change the decision). We (1) demonstrate how this framework may be used to provide explanations for decisions made by general, data-driven AI systems that may incorporate features with arbitrary data types and multiple predictive models,…
While preference modelling is becoming one of the pillars of machine learning, the problem of preference explanation remains challenging and underexplored. In this paper, we propose \textsc{Pref-SHAP}, a Shapley value-based model explanation framework for pairwise comparison data. We derive the appropriate value functions for preference models and further extend the framework to model and explain \emph{context specific} information, such as the surface type in a tennis game. To demonstrate the utility of \textsc{Pref-SHAP}, we apply our method to a variety of synthetic and real-world datasets …
Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limit…
A number of techniques have been proposed to explain a machine learning model's prediction by attributing it to the corresponding input features. Popular among these are techniques that apply the Shapley value method from cooperative game theory. While existing papers focus on the axiomatic motivation of Shapley values, and efficient techniques for computing them, they offer little justification for the game formulations used, and do not address the uncertainty implicit in their methods' outputs. For instance, the popular SHAP algorithm's formulation may give substantial attributions to featur…
Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded. We present a novel, black-box algorithm for computing explanations that uses a principled approach based on causal theory. We have implemented the method in the DEEPCOVER tool. We obtain explanations that are much more accurate than those generated by the existing explanation tools on images with occlusions and observe a level of performance comparable to the state of the art when explaining images without occlusions.
Deep neural networks are powerful statistical learners. However, their predictions do not come with an explanation of their process. To analyze these models, explanation methods are being developed. We present a novel explanation method, called OLM, for natural language processing classifiers. This method combines occlusion and language modeling, which are techniques central to explainability and NLP, respectively. OLM gives explanations that are theoretically sound and easy to understand. We make several contributions to the theory of explanation methods. Axioms for explanation methods are an…
We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on clean and adversarial data. Utilizing this intuition, we propose a framework which can identify whether a given input is adversarial based on the explanations given by the model. Code for our experiments can be found here: https://github.com/seansaito/Explaining-Away-Attacks-Against-Neural-Networks.
Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Singapore General Hospital（新加坡中央医院）；Singapore Health Services（新加坡保健服务集团）；National University of Singapore（新加坡国立大学）
Objective: Shapley additive explanations (SHAP) is a popular post-hoc technique for explaining black box models. While the impact of data imbalance on predictive models has been extensively studied, it remains largely unknown with respect to SHAP-based model explanations. This study sought to investigate the effects of data imbalance on SHAP explanations for deep learning models, and to propose a strategy to mitigate these effects. Materials and Methods: We propose to adjust class distributions in the background and explanation data in SHAP when explaining black box models. Our data balancing …
Graph Neural Networks (GNNs) have become increasingly ubiquitous in numerous applications and systems, necessitating explanations of their predictions, especially when making critical decisions. However, explaining GNNs is challenging due to the complexity of graph data and model execution. Despite additional computational costs, post-hoc explanation approaches have been widely adopted due to the generality of their architectures. Intrinsically interpretable models provide instant explanations but are usually model-specific, which can only explain particular GNNs. Therefore, we propose a novel…
We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for why a classifier may have classified an instance positively or negatively and suggest algorithms for computing these explanations. The first type of explanation identifies a minimal set of the currently active features that is responsible for the current classification, while the second type of explanation identifies a minimal set of features whose current state (active or not…
Self-explaining Neural Network with Concept-based Explanations for ICU Mortality Prediction
Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA（计算机科学与工程系，华盛顿大学圣路易斯分校）；Institute for Informatics, Washington University School of Medicine, St. Louis, MO, USA（信息学院，华盛顿大学医学学院）；Department of Anaesthesiology, Washington University School of Medicine, St. Louis, MO, USA（麻醉学系，华盛顿大学医学学院）；Department of Pulmonary Critical Care and Medicine, Washington University School of Medicine, St. Louis, MO, USA（呼吸科重症医学系，华盛顿大学医学学院）
TU Berlin（柏林工业大学）；MPII（马克斯·普朗克信息学研究所）；Korea University（高丽大学）；Google Research（谷歌研究院）；RIKEN AIP（理化学研究所人工智能项目中心）；TU Kaiserslautern（凯泽斯劳滕工业大学）
Explainable AI (XAI) aims to provide interpretations for predictions made by learning machines, such as deep neural networks, in order to make the machines more transparent for the user and furthermore trustworthy also for applications in e.g. safety-critical areas. So far, however, no methods for quantifying uncertainties of explanations have been conceived, which is problematic in domains where a high confidence in explanations is a prerequisite. We therefore contribute by proposing a new framework that allows to convert any arbitrary explanation method for neural networks into an explanatio…
Random Forest (RFs) are among the most widely used Machine Learning (ML) classifiers. Even though RFs are not interpretable, there are no dedicated non-heuristic approaches for computing explanations of RFs. Moreover, there is recent work on polynomial algorithms for explaining ML models, including naive Bayes classifiers. Hence, one question is whether finding explanations of RFs can be solved in polynomial time. This paper answers this question negatively, by proving that computing one PI-explanation of an RF is D^P-complete. Furthermore, the paper proposes a propositional encoding for compu…
While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty would be possible. With the ongoing rise of eXplainable AI, a lot of methods for explaining model predictions have been developed. However, understanding why a given input was rejected, instead of being classified by the model, is also of interest. Surprisingly, explanations of rejects have not been considered so far. We propose to use counterfactual explanatio…
Halıcıoğlu Data Science Institute（哈尔奇奥格卢数据科学研究所）；Universiy of California, San Diego（加州大学圣地亚哥分校）；Computer Science and Engineering（计算机科学与工程）；New York University（纽约大学）
Cardiff University（卡迪夫大学）；IBM；US Army Research Laboratory（美国陆军研究实验室）
A small subset of explainability techniques developed initially for image recognition models has recently been applied for interpretability of 3D Convolutional Neural Network models in activity recognition tasks. Much like the models themselves, the techniques require little or no modification to be compatible with 3D inputs. However, these explanation techniques regard spatial and temporal information jointly. Therefore, using such explanation techniques, a user cannot explicitly distinguish the role of motion in a 3D model's decision. In fact, it has been shown that these models do not appro…
University of Southern California（南加州大学）；Fudan University（复旦大学）
The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical explanation of neural network predictions. We identify non-additivity and context independent importance attributions within hierarchies as two desirable properties for highlighting word and phrase compositions. We show some prior efforts on hierarchical explanations, e.g. contextual decomposition, do not satisfy the desired properties mathematically, leadin…
UiT The Arctic University of Norway（挪威北极圈大学）；Technische Universität Berlin（柏林工业大学）
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making strategies. As a remedy, many post-hoc explanation and self-explanatory methods have been developed to interpret the models' behavior. These methods, in addition, enable the identification of artifacts that can be learned by the model as class-relevant features. In this work, we provide a detailed case study of the self-explaining network, ProtoPNet, in the…
University of Toulouse（图卢兹大学）；IRIT, CNRS（法国国家科学研究中心图卢兹计算机科学研究所）
Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations. One alternative are the so-called formal approaches to XAI, that include PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. The computation of relevant features serves to trade off probabilistic precision for the number of features in an explanation. However, even for very simple classifiers, the complexity of computing sets of relevant features is prohibitive. This pap…
Simon Fraser University（西蒙菲莎大学）；Columbia University（哥伦比亚大学）
Obtaining an explanation for an SQL query result can enrich the analysis experience, reveal data errors, and provide deeper insight into the data. Inference query explanation seeks to explain unexpected aggregate query results on inference data; such queries are challenging to explain because an explanation may need to be derived from the source, training, or inference data in an ML pipeline. In this paper, we model an objective function as a black-box function and propose BOExplain, a novel framework for explaining inference queries using Bayesian optimization (BO). An explanation is a predic…
University of Toulouse（图卢兹大学）；Monash University（莫纳什大学）；IRIT（图卢兹信息学研究所）；CNRS（法国国家科学研究中心）
Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifiers, globally referred to as decision graphs, and which include decision trees and binary decision diagrams, but also their multi-valued variants, there exist polynomial-time algorithms for computing one PI-explanation. In addition, the paper also proposes a polynomial-time algorithm for computing one contrastive explanation. These novel algorithms build on explanation graphs (…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Snap Inc.（色拉布公司）
Explaining machine learning models is an important and increasingly popular area of research interest. The Shapley value from game theory has been proposed as a prime approach to compute feature importance towards model predictions on images, text, tabular data, and recently graph neural networks (GNNs) on graphs. In this work, we revisit the appropriateness of the Shapley value for GNN explanation, where the task is to identify the most important subgraph and constituent nodes for GNN predictions. We claim that the Shapley value is a non-ideal choice for graph data because it is by definition…
By their nature, the composition of black box models is opaque. This makes the ability to generate explanations for the response to stimuli challenging. The importance of explaining black box models has become increasingly important given the prevalence of AI and ML systems and the need to build legal and regulatory frameworks around them. Such explanations can also increase trust in these uncertain systems. In our paper we present RICE, a method for generating explanations of the behaviour of black box models by (1) probing a model to extract model output examples using sensitivity analysis; …
We introduce a method for explaining the results of various linear and hierarchical multi-criteria decision-making (MCDM) techniques such as WSM and AHP. The two key ideas are (A) to maintain a fine-grained representation of the values manipulated by these techniques and (B) to derive explanations from these representations through merging, filtering, and aggregating operations. An explanation in our model presents a high-level comparison of two alternatives in an MCDM problem, presumably an optimal and a non-optimal one, illuminating why one alternative was preferred over the other one. We sh…
Lenovo Research（联想研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results. Explainability is not only a gateway between AI and society but also a powerful tool to detect flaws in the model and biases in the data. Local Interpretable Model-agnostic Explanation (LIME) is a recent approach that uses an interpretable model to form a local explanation for the individual prediction result. The current implementation of LIME adopts the linear r…
Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems. However, as the number of trees and their individual size can be large, their decision making process is often incomprehensible. In order to reason about the decision process, we propose representing it as an argumentation problem. We generalize sufficient and necessary argumentative explanations using a Markov network encoding, discuss the relevance of these explanations and establish relationships to families of abductive explanations from the literature. As the complexity of the expl…
University College Dublin（都柏林大学学院）；Accenture Labs（埃森哲实验室）；Insight Centre for Data Analytics（洞察数据分析中心）；VistaMilk SFI Research Centre（VistaMilk SFI研究中心）
Counterfactual explanations are an increasingly popular form of post hoc explanation due to their (i) applicability across problem domains, (ii) proposed legal compliance (e.g., with GDPR), and (iii) reliance on the contrastive nature of human explanation. Although counterfactual explanations are normally used to explain individual predictive-instances, we explore a novel use case in which groups of similar instances are explained in a collective fashion using ``group counterfactuals'' (e.g., to highlight a repeating pattern of illness in a group of patients). These group counterfactuals meet …
Towards Few-shot Self-explaining Graph Neural Networks
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Decision trees (DTs) epitomize what have become to be known as interpretable machine learning (ML) models. This is informally motivated by paths in DTs being often much smaller than the total number of features. This paper shows that in some settings DTs can hardly be deemed interpretable, with paths in a DT being arbitrarily larger than a PI-explanation, i.e. a subset-minimal set of feature values that entails the prediction. As a result, the paper proposes a novel model for computing PI-explanations of DTs, which enables computing one PI-explanation in polynomial time. Moreover, it is shown …
TU Darmstadt（达姆施塔特工业大学）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心）；German Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Centre for Cognitive Science, TU Darmstadt（达姆施塔特工业大学认知科学中心）
University of Glasgow（格拉斯哥大学）；University of Warwick（华威大学）
Analysts wishing to explore multivariate data spaces, typically pose queries involving selection operators, i.e., range or radius queries, which define data subspaces of possible interest and then use aggregation functions, the results of which determine their exploratory analytics interests. However, such aggregate query (AQ) results are simple scalars and as such, convey limited information about the queried subspaces for exploratory analysis. We address this shortcoming aiding analysts to explore and understand data subspaces by contributing a novel explanation mechanism coined XAXA: eXplai…
We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a) find the most influential training examples during training and b) analyze which classes attributed most to the final representation. Our method is general: it can be wrapped around any iterative optimization procedure and covers a variety of neural network architectures, including feed-forward networks and convolutional neural networks. We first propose a m…
