Supervised machine learning explainability has developed rapidly in recent years. However, clustering explainability has lagged behind. Here, we demonstrate the first adaptation of model-agnostic explainability methods to explain unsupervised clustering. We present two novel "algorithm-agnostic" explainability methods - global permutation percent change (G2PC) and local perturbation percent change (L2PC) - that identify feature importance globally to a clustering algorithm and locally to the clustering of individual samples. The methods are (1) easy to implement and (2) broadly applicable across clustering algorithms, which could make them highly impactful. We demonstrate the utility of the methods for explaining five popular clustering methods on low-dimensional synthetic datasets and on high-dimensional functional network connectivity data extracted from a resting-state functional magnetic resonance imaging dataset of 151 individuals with schizophrenia and 160 controls. Our results are consistent with existing literature while also shedding new light on how changes in brain connectivity may lead to schizophrenia symptoms. We further compare the explanations from our methods to an interpretable classifier and find them to be highly similar. Our proposed methods robustly explain multiple clustering algorithms and could facilitate new insights into many applications. We hope this study will greatly accelerate the development of the field of clustering explainability.
Deep neural networks that yield human interpretable decisions by architectural design have lately become an increasingly popular alternative to post hoc interpretation of traditional black-box models. Among these networks, the arguably most widespread approach is so-called prototype learning, where similarities to learned latent prototypes serve as the basis of classifying an unseen data point. In this work, we point to an important shortcoming of such approaches. Namely, there is a semantic gap between similarity in latent space and similarity in input space, which can corrupt interpretability. We design two experiments that exemplify this issue on the so-called ProtoPNet. Specifically, we find that this network's interpretability mechanism can be led astray by intentionally crafted or even JPEG compression artefacts, which can produce incomprehensible decisions. We argue that practitioners ought to have this shortcoming in mind when deploying prototype-based models in practice.
Feature attribution is often loosely presented as the process of selecting a subset of relevant features as a rationale of a prediction. Task-dependent by nature, precise definitions of "relevance" encountered in the literature are however not always consistent. This lack of clarity stems from the fact that we usually do not have access to any notion of ground-truth attribution and from a more general debate on what good interpretations are. In this paper we propose to formalise feature selection/attribution based on the concept of relaxed functional dependence. In particular, we extend our notions to the instance-wise setting and derive necessary properties for candidate selection solutions, while leaving room for task-dependence. By computing ground-truth attributions on synthetic datasets, we evaluate many state-of-the-art attribution methods and show that, even when optimised, some fail to verify the proposed properties and provide wrong solutions.
Artificial intelligence (AI) is becoming increasingly more popular and can be found in workplaces and homes around the world. The decisions made by such "black box" systems are often opaque; that is, so complex as to be functionally impossible to understand. How do we ensure that these systems are behaving as desired? TrustyAI is an initiative which looks into explainable artificial intelligence (XAI) solutions to address this issue of explainability in the context of both AI models and decision services. This paper presents the TrustyAI Explainability Toolkit, a Java and Python library that provides XAI explanations of decision services and predictive models for both enterprise and data science use-cases. We describe the TrustyAI implementations and extensions to techniques such as LIME, SHAP and counterfactuals, which are benchmarked against existing implementations in a variety of experiments.
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches. To evaluate the appropriateness of the proposal, we compare different CAM-based visualization methods on the entire ImageNet validation set, fostering proper comparisons and reproducibility.
A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation process, we portray their knowledge difference with image translation. Specifically, we feed a translated image and its original version to the two models respectively, formulating two branches. Through updating the translated image, we force similar outputs from the two branches. When such requirements are met, differences between the two images can compensate for and hence represent the knowledge difference between models. To enforce similar outputs from the two branches and depict the adapted knowledge, we propose a source-free image translation method that generates source-style images using only target images and the two models. We visualize the adapted knowledge on several datasets with different UDA methods and find that generated images successfully capture the style difference between the two domains. For application, we show that generated images enable further tuning of the target model without accessing source data. Code available at https://github.com/hou-yz/DA_visualization.
The performance of text classification methods has improved greatly over the last decade for text instances of less than 512 tokens. This limit has been adopted by most state-of-the-research transformer models due to the high computational cost of analyzing longer text instances. To mitigate this problem and to improve classification for longer texts, researchers have sought to resolve the underlying causes of the computational cost and have proposed optimizations for the attention mechanism, which is the key element of every transformer model. In our study, we are not pursuing the ultimate goal of long text classification, i.e., the ability to analyze entire text instances at one time while preserving high performance at a reasonable computational cost. Instead, we propose a text truncation method called Text Guide, in which the original text length is reduced to a predefined limit in a manner that improves performance over naive and semi-naive approaches while preserving low computational costs. Text Guide benefits from the concept of feature importance, a notion from the explainable artificial intelligence domain. We demonstrate that Text Guide can be used to improve the performance of recent language models specifically designed for long text classification, such as Longformer. Moreover, we discovered that parameter optimization is the key to Text Guide performance and must be conducted before the method is deployed. Future experiments may reveal additional benefits provided by this new method.
One of the key elements of explanatory analysis of a predictive model is to assess the importance of individual variables. Rapid development of the area of predictive model exploration (also called explainable artificial intelligence or interpretable machine learning) has led to the popularization of methods for local (instance level) and global (dataset level) methods, such as Permutational Variable Importance, Shapley Values (SHAP), Local Interpretable Model Explanations (LIME), Break Down and so on. However, these methods do not use information about the correlation between features which significantly reduce the explainability of the model behaviour. In this work, we propose new methods to support model analysis by exploiting the information about the correlation between variables. The dataset level aspect importance measure is inspired by the block permutations procedure, while the instance level aspect importance measure is inspired by the LIME method. We show how to analyze groups of variables (aspects) both when they are proposed by the user and when they should be determined automatically based on the hierarchical structure of correlations between variables. Additionally, we present the new type of model visualisation, triplot, which exploits a hierarchical structure of variable grouping to produce a high information density model visualisation. This visualisation provides a consistent illustration for either local or global model and data exploration. We also show an example of real-world data with 5k instances and 37 features in which a significant correlation between variables affects the interpretation of the effect of variable importance. The proposed method is, to our knowledge, the first to allow direct use of the correlation between variables in exploratory model analysis.
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We provide a sound and complete algorithm for computing explanatory factors with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on various tasks.
State-of-the-art deep-learning systems use decision rules that are challenging for humans to model. Explainable AI (XAI) attempts to improve human understanding but rarely accounts for how people typically reason about unfamiliar agents. We propose explicitly modeling the human explainee via Bayesian Teaching, which evaluates explanations by how much they shift explainees' inferences toward a desired goal. We assess Bayesian Teaching in a binary image classification task across a variety of contexts. Absent intervention, participants predict that the AI's classifications will match their own, but explanations generated by Bayesian Teaching improve their ability to predict the AI's judgements by moving them away from this prior belief. Bayesian Teaching further allows each case to be broken down into sub-examples (here saliency maps). These sub-examples complement whole examples by improving error detection for familiar categories, whereas whole examples help predict correct AI judgements of unfamiliar cases.
In this paper we introduce a tool called Principal Image Sections Mapping - PRISM, dedicated for PyTorch, but can be easily ported to other deep learning frameworks. Presented software relies on Principal Component Analysis to visualize the most significant features recognized by a given Convolutional Neural Network. Moreover, it allows to display comparative set features between images processed in the same batch, therefore PRISM can be a method well synerging with technique Explanation by Example.
Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of "black-box" models. In this paper, a novel XAI visual explanation algorithm known as the Similarity Difference and Uniqueness (SIDU) method that can effectively localize entire object regions responsible for prediction is presented in full detail. The SIDU algorithm robustness and effectiveness is analyzed through various computational and human subject experiments. In particular, the SIDU algorithm is assessed using three different types of evaluations (Application, Human and Functionally-Grounded) to demonstrate its superior performance. The robustness of SIDU is further studied in the presence of adversarial attack on "black-box" models to better understand its performance. Our code is available at: https://github.com/satyamahesh84/SIDU_XAI_CODE.
The sudden outbreak and uncontrolled spread of COVID-19 disease is one of the most important global problems today. In a short period of time, it has led to the development of many deep neural network models for COVID-19 detection with modules for explainability. In this work, we carry out a systematic analysis of various aspects of proposed models. Our analysis revealed numerous mistakes made at different stages of data acquisition, model development, and explanation construction. In this work, we overview the approaches proposed in the surveyed Machine Learning articles and indicate typical errors emerging from the lack of deep understanding of the radiography domain. We present the perspective of both: experts in the field - radiologists and deep learning engineers dealing with model explanations. The final result is a proposed checklist with the minimum conditions to be met by a reliable COVID-19 diagnostic model.
In this era of active development of autonomous vehicles, it becomes crucial to provide driving systems with the capacity to explain their decisions. In this work, we focus on generating high-level driving explanations as the vehicle drives. We present BEEF, for BEhavior Explanation with Fusion, a deep architecture which explains the behavior of a trajectory prediction model. Supervised by annotations of human driving decisions justifications, BEEF learns to fuse features from multiple levels. Leveraging recent advances in the multi-modal fusion literature, BEEF is carefully designed to model the correlations between high-level decisions features and mid-level perceptual features. The flexibility and efficiency of our approach are validated with extensive experiments on the HDD and BDD-X datasets.
When it comes to complex machine learning models, commonly referred to as black boxes, understanding the underlying decision making process is crucial for domains such as healthcare and financial services, and also when it is used in connection with safety critical systems such as autonomous vehicles. As such interest in explainable artificial intelligence (xAI) tools and techniques has increased in recent years. However, the effectiveness of existing xAI frameworks, especially concerning algorithms that work with data as opposed to images, is still an open research question. In order to address this gap, in this paper we examine the effectiveness of the Local Interpretable Model-Agnostic Explanations (LIME) xAI framework, one of the most popular model agnostic frameworks found in the literature, with a specific focus on its performance in terms of making tabular models more interpretable. In particular, we apply several state of the art machine learning algorithms on a tabular dataset, and demonstrate how LIME can be used to supplement conventional performance assessment methods. In addition, we evaluate the understandability of the output produced by LIME both via a usability study, involving participants who are not familiar with LIME, and its overall usability via an assessment framework, which is derived from the International Organisation for Standardisation 9241-11:1998 standard.
Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model. Being based on solid game-theoretic principles, Shapley values uniquely satisfy several desirable properties, which is why they are increasingly used to explain the predictions of possibly complex and highly non-linear machine learning models. Shapley values are well calibrated to a user's intuition when features are independent, but may lead to undesirable, counterintuitive explanations when the independence assumption is violated. In this paper, we propose a novel framework for computing Shapley values that generalizes recent work that aims to circumvent the independence assumption. By employing Pearl's do-calculus, we show how these 'causal' Shapley values can be derived for general causal graphs without sacrificing any of their desirable properties. Moreover, causal Shapley values enable us to separate the contribution of direct and indirect effects. We provide a practical implementation for computing causal Shapley values based on causal chain graphs when only partial information is available and illustrate their utility on a real-world example.
The growing availability of data and computing power fuels the development of predictive models. In order to ensure the safe and effective functioning of such models, we need methods for exploration, debugging, and validation. New methods and tools for this purpose are being developed within the eXplainable Artificial Intelligence (XAI) subdomain of machine learning. In this work (1) we present the taxonomy of methods for model explanations, (2) we identify and compare 27 packages available in R to perform XAI analysis, (3) we present an example of an application of particular packages, (4) we acknowledge recent trends in XAI. The article is primarily devoted to the tools available in R, but since it is easy to integrate the Python code, we will also show examples for the most popular libraries from Python.
COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources.
Explainable artificial intelligence has been gaining attention in the past few years. However, most existing methods are based on gradients or intermediate features, which are not directly involved in the decision-making process of the classifier. In this paper, we propose a slot attention-based classifier called SCOUTER for transparent yet accurate classification. Two major differences from other attention-based methods include: (a) SCOUTER's explanation is involved in the final confidence for each category, offering more intuitive interpretation, and (b) all the categories have their corresponding positive or negative explanation, which tells "why the image is of a certain category" or "why the image is not of a certain category." We design a new loss tailored for SCOUTER that controls the model's behavior to switch between positive and negative explanations, as well as the size of explanatory regions. Experimental results show that SCOUTER can give better visual explanations in terms of various metrics while keeping good accuracy on small and medium-sized datasets.
In explainable artificial intelligence, there is increasing interest in understanding the behaviour of autonomous agents to build trust and validate performance. Modern agent architectures, such as those trained by deep reinforcement learning, are currently so lacking in interpretable structure as to effectively be black boxes, but insights may still be gained from an external, behaviourist perspective. Inspired by conceptual spaces theory, we suggest that a versatile first step towards general understanding is to discretise the state space into convex regions, jointly capturing similarities over the agent's action, value function and temporal dynamics within a dataset of observations. We create such a representation using a novel variant of the CART decision tree algorithm, and demonstrate how it facilitates practical understanding of black box agents through prediction, visualisation and rule-based explanation.