We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the social sciences, and propose a list of design principles for machine-generated explanations that are meaningful to humans. Using the concept of weight of evidence from information theory, we develop a method for generating explanations that adhere to these principles. We show that this method can be adapted to handle high-dimensional, multi-class settings, yielding a flexible framework for generating explanations. We demonstrate that these explanations can be estimated accurately from finite samples and are robust to small perturbations of the inputs. We also evaluate our method through a qualitative user study with machine learning practitioners, where we observe that the resulting explanations are usable despite some participants struggling with background concepts like prior class probabilities. Finally, we conclude by surfacing~design~implications for interpretability tools in general.
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）
Decision trees (DTs) epitomize the ideal of interpretability of machine learning (ML) models. The interpretability of decision trees motivates explainability approaches by so-called intrinsic interpretability, and it is at the core of recent proposals for applying interpretable ML models in high-risk applications. The belief in DT interpretability is justified by the fact that explanations for DT predictions are generally expected to be succinct. Indeed, in the case of DTs, explanations correspond to DT paths. Since decision trees are ideally shallow, and so paths contain far fewer features th…
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；AXA（安盛集团）；Polish Academy of Science（波兰科学院）
Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a result of some artifacts learned by the model instead of actual knowledge from the data. This paper focuses on the case of counterfactual explanations and asks whether the generated instances can be justified, i.e. continuously connected to some ground-truth data. We evaluate the risk of generating unjustified counterfactual examples by investigating the local neighborhoods of i…
Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
Federal University of Pará (UFPA)（帕拉联邦大学）；Federal Institute of Education, Science and Technology of Pará (IFPA)（帕拉联邦教育、科学和技术学院）；Vale Institute of Technology (ITV DS)（淡水河谷技术研究院）
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；AXA（安盛）；Polish Academy of Science（波兰科学院）
In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating prior knowledge into such interpretability methods aims at improving the explanation understandability and allowing for personalised explanations adapted to each user. In this paper, we propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives: we present a general framework for the optimization problem of post-hoc interpretability methods, and show that user know…
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…
While deep learning makes significant achievements in Artificial Intelligence (AI), the lack of transparency has limited its broad application in various vertical domains. Explainability is not only a gateway between AI and real world, but also a powerful feature to detect flaw of the models and bias of the data. Local Interpretable Model-agnostic Explanation (LIME) is a widely-accepted technique that explains the prediction of any classifier faithfully by learning an interpretable model locally around the predicted instance. As an extension of LIME, this paper proposes an high-interpretabilit…
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education（高可信软件技术教育部重点实验室（北京大学））；School of Computer Science, Peking University（北京大学计算机学院）
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable in the specific context of verification. Suppose we have a machine learning system that predicts X, and we provide rationale for this prediction X. Given an input, an explanation, and an output, is the output consistent with the input and the supposed rationale? Via…
Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification models by modifying the representation to disregard non-contrastive information, and modifying model behavior to only be based on contrastive reasoning. Our method is based on projecting model representation to a latent space that captures only the features that are useful (to the model) to differentiate two potential decisions. We demonstrate the value of contr…
Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this position paper, we propose a distinction between descriptive and persuasive explanations. We discuss reasoning suggesting that functional interpretability may be correlated with cognitive function and user preferences. If this is indeed the case, evaluation and optimization using…
Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations
Jagiellonian University（雅盖隆大学）；Doctoral School of Exact and Natural Sciences, Jagiellonian University（雅盖隆大学精确与自然科学博士学院）；Faculty of Management and Social Communication, Jagiellonian University（雅盖隆大学管理与社会传播学院）；IDEAS NCBR
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Inria（法国国家信息与自动化研究所）；École Polytechnique（巴黎综合理工学院）
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding other users' privacy. In this work, we take a fresh perspective, and present PRINCE: a provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommend…
Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable, they should not be used in critical, high-risk applications where human lives are at risk. To address this issue, researchers and businesses have been focusing on finding ways to improve the interpretability of complex ML systems, and several such methods have been developed. Indeed, there are so many developed techniques that it is difficult for practitioner…
The ubiquity of machine learning based predictive models in modern society naturally leads people to ask how trustworthy those models are? In predictive modeling, it is quite common to induce a trade-off between accuracy and interpretability. For instance, doctors would like to know how effective some treatment will be for a patient or why the model suggested a particular medication for a patient exhibiting those symptoms? We acknowledge that the necessity for interpretability is a consequence of an incomplete formalisation of the problem, or more precisely of multiple meanings adhered to a pa…
Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not look inside the model, inhibiting human trust in the model and explanations. Motivated by the ability of neurons to detect high-level semantic concepts in vision models, we perform a novel analysis on the behaviour of individual GNN neurons to answer questions about GNN interpretability, and propose new metrics for evaluating the interpretability of GNN neuron…
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…
Explaining and interpreting the decisions of recommender systems are becoming extremely relevant both, for improving predictive performance, and providing valid explanations to users. While most of the recent interest has focused on providing local explanations, there has been a much lower emphasis on studying the effects of model dynamics and its impact on explanation. In this paper, we perform a focused study on the impact of model interpretability in the context of calibration. Specifically, we address the challenges of both over-confident and under-confident predictions with interpretabili…
Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models, or describes complicated behaviors in larger models with broad strokes. In this work, we bridge this gap by presenting an explanation for how GPT-2 small performs a natural language task called indirect object identification (IOI). Our explanation encompasses 26 attention heads grouped into 7 main classes, which we discovered using a combination of interpretability approaches relying…
University of Twente（特文特大学）；Freie Universität Berlin（柏林自由大学）
During a research project in which we developed a machine learning (ML) driven visualization system for non-ML experts, we reflected on interpretability research in ML, computer-supported collaborative work and human-computer interaction. We found that while there are manifold technical approaches, these often focus on ML experts and are evaluated in decontextualized empirical studies. We hypothesized that participatory design research may support the understanding of stakeholders' situated sense-making in our project, yet, found guidance regarding ML interpretability inexhaustive. Building on…
Understanding how ML models work is a prerequisite for responsibly designing, deploying, and using ML-based systems. With interpretability approaches, ML can now offer explanations for its outputs to aid human understanding. Though these approaches rely on guidelines for how humans explain things to each other, they ultimately solve for improving the artifact -- an explanation. In this paper, we propose an alternate framework for interpretability grounded in Weick's sensemaking theory, which focuses on who the explanation is intended for. Recent work has advocated for the importance of underst…
This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the used explainer. CNNs for computer vision have shown exceptional performance in critical industries. However, it is a significant barrier when deploying CNNs due to their complexity and lack of interpretability. Recent studies to explain computer vision models have shifted from extracting low-level features (pixel-based explanations) to mid-or high-level feature…
University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）
The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which emulates this format by providing explanations based on the explainee's current mental model. We conduct novel online human experiments where explanations generated by various explanation methods are selected and presented to participants, using policies which observe participants' mental models, in order to optimize an interpretability proxy. Our results su…
Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable artificial intelligence addresses this problem. However, most of the interpretability methods are aligned to the image modality by design. The paper introduces TimeREISE a model agnostic attribution method specifically aligned to success in the context of time series classification. The method shows superior performance compared to existing approaches concerning …
We consider two fundamental and related issues currently faced by Artificial Intelligence (AI) development: the lack of ethics and interpretability of AI decisions. Can interpretable AI decisions help to address ethics in AI? Using a randomized study, we experimentally show that the empirical and liberal turn of the production of explanations tends to select AI explanations with a low denunciatory power. Under certain conditions, interpretability tools are therefore not means but, paradoxically, obstacles to the production of ethical AI since they can give the illusion of being sensitive to et…
Microsoft Research（微软研究院）；University of Maryland（马里兰大学）
Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via $\textit{explanations}$, which justify individual model predictions. In this work, we take a step towards reconciling machine explanations with those that humans produce and prefer by taking inspiration from the study of explanation in philosophy, cognitive science, and the social sciences. We identify key aspects in which these human explanations differ from current machine explanations, distill them into a list of desiderata, and formalize …
University of Science and Technology of China（中国科学技术大学）；Tencent America（腾讯美国）
Despite the recent progress in Graph Neural Networks (GNNs), it remains challenging to explain the predictions made by GNNs. Existing explanation methods mainly focus on post-hoc explanations where another explanatory model is employed to provide explanations for a trained GNN. The fact that post-hoc methods fail to reveal the original reasoning process of GNNs raises the need of building GNNs with built-in interpretability. In this work, we propose Prototype Graph Neural Network (ProtGNN), which combines prototype learning with GNNs and provides a new perspective on the explanations of GNNs. …
ABB Ability Innovation Center, Asea Brown Boveri Company（ABB集团ABB能力创新中心）；Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
With the advancement of technology for artificial intelligence (AI) based solutions and analytics compute engines, machine learning (ML) models are getting more complex day by day. Most of these models are generally used as a black box without user interpretability. Such complex ML models make it more difficult for people to understand or trust their predictions. There are variety of frameworks using explainable AI (XAI) methods to demonstrate explainability and interpretability of ML models to make their predictions more trustworthy. In this manuscript, we propose a methodology that we define…
EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it remains challenging to quantify correctness of their interpretability as current evaluation approaches either require subjective input from humans or incur high computation cost with automated evaluation. In this paper, we propose backdoor trigger patterns--hidden malicious functionalities that cause misclassification--to automate the evaluation of…
Integrated Gradients (IG) as well as its variants are well-known techniques for interpreting the decisions of deep neural networks. While IG-based approaches attain state-of-the-art performance, they often integrate noise into their explanation saliency maps, which reduce their interpretability. To minimize the noise, we examine the source of the noise analytically and propose a new approach to reduce the explanation noise based on our analytical findings. We propose the Important Direction Gradient Integration (IDGI) framework, which can be easily incorporated into any IG-based method that us…
Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impacted by classifiers' decisions. However, their extension to textual data is under-explored and there is little investigation on their vulnerabilities and limitations. This work motivates textual counterfactuals by laying the ground for a novel evaluation scheme inspired by the faithfulness of explanations. Accordingly, we extend the computation of three metrics, proximity,connect…
Indraprastha Institute of Information Technology Delhi（德里英德拉普拉斯信息技术学院）
Deep learning models trained using massive amounts of data tend to capture one view of the data and its associated mapping. Different deep learning models built on the same training data may capture different views of the data based on the underlying techniques used. For explaining the decisions arrived by blackbox deep learning models, we argue that it is essential to reproduce that model's view of the training data faithfully. This faithful reproduction can then be used for explanation generation. We investigate two methods for data view extraction: hill-climbing approach and a GAN-driven ap…
Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop a method to produce explanation masks for pre-trained networks. The mask localizes the most important aspects of each input for prediction of the original network. Masks are created by a secondary network whose goal is to create as small an explanation as possible while still preserving the predictive accuracy of the original network. We demonstrate the appl…
Towards Multi-dimensional Explanation Alignment for Medical Classification
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；HKUST(GZ)（香港科技大学（广州））；Tongji University（同济大学）；Ant Group（蚂蚁集团）；The University of Auckland（奥克兰大学）；RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心）
