This paper presents correct algorithms for answering the following two questions; (i) Does there exist a causal explanation consistent with a set of background knowledge which explains all of the observed independence facts in a sample? (ii) Given that there is such a causal explanation what are the causal relationships common to every such causal explanation?
IBM Research GmbH（IBM研究院）；Swiss Federal Institute of Technology Zurich（苏黎世联邦理工学院）
Bayesian networks can be used to extract explanations about the observed state of a subset of variables. In this paper, we explicate the desiderata of an explanation and confront them with the concept of explanation proposed by existing methods. The necessity of taking into account causal approaches when a causal graph is available is discussed. We then introduce causal explanation trees, based on the construction of explanation trees using the measure of causal information ow (Ay and Polani, 2006). This approach is compared to several other methods on known networks.
Although standard Machine Learning models are optimized for making predictions about observations, more and more they are used for making predictions about the results of actions. An important goal of Explainable Artificial Intelligence (XAI) is to compensate for this mismatch by offering explanations about the predictions of an ML-model which ensure that they are reliably action-guiding. As action-guiding explanations are causal explanations, the literature on this topic is starting to embrace insights from the literature on causal models. Here I take a step further down this path by formally…
Counterfactual (CF) explanations have been employed as one of the modes of explainability in explainable AI-both to increase the transparency of AI systems and to provide recourse. Cognitive science and psychology, however, have pointed out that people regularly use CFs to express causal relationships. Most AI systems are only able to capture associations or correlations in data so interpreting them as casual would not be justified. In this paper, we present two experiment (total N = 364) exploring the effects of CF explanations of AI system's predictions on lay people's causal beliefs about t…
We examine the practicality for a user of using Answer Set Programming (ASP) for representing logical formalisms. Our example is a formalism aiming at capturing causal explanations from causal information. We show the naturalness and relative efficiency of this translation job. We are interested in the ease for writing an ASP program. Limitations of the earlier systems made that in practice, the ``declarative aspect'' was more theoretical than practical. We show how recent improvements in working ASP systems facilitate the translation.
We define an inference system to capture explanations based on causal statements, using an ontology in the form of an IS-A hierarchy. We first introduce a simple logical language which makes it possible to express that a fact causes another fact and that a fact explains another fact. We present a set of formal inference patterns from causal statements to explanation statements. We introduce an elementary ontology which gives greater expressiveness to the system while staying close to propositional reasoning. We provide an inference system that captures the patterns discussed, firstly in a pure…
Causal Explanations Over Time: Articulated Reasoning for Interactive Environments
Technical University of Darmstadt（德累斯顿技术大学）；Eindhoven University of Technology（埃因霍温理工大学）；Hessian Center for Artificial Intelligence（黑森人工智能中心）；German Research Center for Artificial Intelligence（德国人工智能研究中心）
Imperial College London（伦敦帝国理工学院）；Università degli Studi di Brescia（布雷西亚大学）
Causal models are playing an increasingly important role in machine learning, particularly in the realm of explainable AI. We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for the models' outputs. The conceptualisation is based on reinterpreting desirable properties of semantics of AFs as explanation moulds, which are means for characterising the relations in the causal model argumentatively. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement as an explanation mould t…
This paper examines two related problems that are central to developing an autonomous decision-making agent, such as a robot. Both problems require generating structured representafions from a database of unstructured declarative knowledge that includes many facts and rules that are irrelevant in the problem context. The first problem is how to generate a well structured decision problem from such a database. The second problem is how to generate, from the same database, a well-structured explanation of why some possible world occurred. In this paper it is shown that the problem of generating …
We examine the practicality for a user of using Answer Set Programming (ASP) for representing logical formalisms. We choose as an example a formalism aiming at capturing causal explanations from causal information. We provide an implementation, showing the naturalness and relative efficiency of this translation job. We are interested in the ease for writing an ASP program, in accordance with the claimed ``declarative'' aspect of ASP. Limitations of the earlier systems (poor data structure and difficulty in reusing pieces of programs) made that in practice, the ``declarative aspect'' was more t…
A Computationally Feasible Framework for Causal Probabilistic Explanation
Basis Research Institute（贝西斯研究所）；Sorbus AI（索巴斯人工智能公司）；Massachusetts Institute of Technology（麻省理工学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；HouseIQ（豪斯IQ公司）
Northrop Corporation（诺斯洛普公司）；University of California（加利福尼亚大学）
In a previous paper [Pearl and Verma, 1991] we presented an algorithm for extracting causal influences from independence information, where a causal influence was defined as the existence of a directed arc in all minimal causal models consistent with the data. In this paper we address the question of deciding whether there exists a causal model that explains ALL the observed dependencies and independencies. Formally, given a list M of conditional independence statements, it is required to decide whether there exists a directed acyclic graph (dag) D that is perfectly consistent with M, namely, …
King's College London（伦敦国王学院）；Amazon.com, Inc.（亚马逊公司）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Manchester（曼彻斯特大学）
We evaluate four computational models of explanation in Bayesian networks by comparing model predictions to human judgments. In two experiments, we present human participants with causal structures for which the models make divergent predictions and either solicit the best explanation for an observed event (Experiment 1) or have participants rate provided explanations for an observed event (Experiment 2). Across two versions of two causal structures and across both experiments, we find that the Causal Explanation Tree and Most Relevant Explanation models provide better fits to human data than …
Understanding causality has vital importance for various Natural Language Processing (NLP) applications. Beyond the labeled instances, conceptual explanations of the causality can provide deep understanding of the causal facts to facilitate the causal reasoning process. However, such explanation information still remains absent in existing causal reasoning resources. In this paper, we fill this gap by presenting a human-annotated explainable CAusal REasoning dataset (e-CARE), which contains over 21K causal reasoning questions, together with natural language formed explanations of the causal qu…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；General Motors Research（通用汽车研究院）
We introduce a novel framework for causal explanations of stochastic, sequential decision-making systems built on the well-studied structural causal model paradigm for causal reasoning. This single framework can identify multiple, semantically distinct explanations for agent actions -- something not previously possible. In this paper, we establish exact methods and several approximation techniques for causal inference on Markov decision processes using this framework, followed by results on the applicability of the exact methods and some run time bounds. We discuss several scenarios that illus…
Dipartimento di Informatica e Sistemistica, Universita di Roma "La Sapienza"（罗马大学信息与系统系）
This paper is directed towards combining Pearl's structural-model approach to causal reasoning with high-level formalisms for reasoning about actions. More precisely, we present a combination of Pearl's structural-model approach with Poole's independent choice logic. We show how probabilistic theories in the independent choice logic can be mapped to probabilistic causal models. This mapping provides the independent choice logic with appealing concepts of causality and explanation from the structural-model approach. We illustrate this along Halpern and Pearl's sophisticated notions of actual ca…
University of South Australia（南澳大学）；Hefei University of Technology（合肥工业大学）
This paper studies the problem of estimating the contributions of features to the prediction of a specific instance by a machine learning model and the overall contribution of a feature to the model. The causal effect of a feature (variable) on the predicted outcome reflects the contribution of the feature to a prediction very well. A challenge is that most existing causal effects cannot be estimated from data without a known causal graph. In this paper, we define an explanatory causal effect based on a hypothetical ideal experiment. The definition brings several benefits to model agnostic exp…
Institut de Recherche en Informatique de Toulouse (IRIT)（图卢兹信息研究所（IRIT））；Centre de Recherche Cerveau et Cognition (CerCo)（脑与认知研究中心（CerCo））；CNRS（国家科学研究中心）
Bosch Center for Artificial Intelligence（博世人工智能中心）；Technical University of Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森州人工智能中心（hessian.AI））
CNRS（法国国家科学研究中心）；IRIT（图卢兹信息学研究所）；Université de Toulouse（图卢兹大学）；Université de Rennes I（雷恩第一大学）；INRIA Bretagne Atlantique（法国国家数字科学与技术研究院布列塔尼-大西洋中心）；IRISA（信息与随机系统研究所）
We investigate an approach to reasoning about causes through argumentation. We consider a causal model for a physical system, and look for arguments about facts. Some arguments are meant to provide explanations of facts whereas some challenge these explanations and so on. At the root of argumentation here, are causal links ({A_1, ... ,A_n} causes B) and ontological links (o_1 is_a o_2). We present a system that provides a candidate explanation ({A_1, ... ,A_n} explains {B_1, ... ,B_m}) by resorting to an underlying causal link substantiated with appropriate ontological links. Argumentation is …
Rutgers University（罗格斯大学）；Renmin University of China（中国人民大学）
State-of-the-art recommender systems have the ability to generate high-quality recommendations, but usually cannot provide intuitive explanations to humans due to the usage of black-box prediction models. The lack of transparency has highlighted the critical importance of improving the explainability of recommender systems. In this paper, we propose to extract causal rules from the user interaction history as post-hoc explanations for the black-box sequential recommendation mechanisms, whilst maintain the predictive accuracy of the recommendation model. Our approach firstly achieves counterfac…
Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI
Insight SFI Centre for Data Analytics, School of Computer Science, University College Dublin（都柏林大学学院计算机科学学院Insight SFI数据分析中心）；VistaMilk SFI Research Centre, School of Computer Science, University College Dublin（都柏林大学学院计算机科学学院VistaMilk SFI研究中心）；School of Psychology and Institute of Neuroscience, Trinity College Dublin, University of Dublin（都柏林圣三一学院心理学院和神经科学研究所）
School of Electrical & Computer Engineering（电气与计算机工程学院）；Georgia Institute of Technology（佐治亚理工学院）
We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a change in the classifier output statistics. To construct these explanations, we design a learning framework that leverages a generative model and information-theoretic measures of causal influence. Our objective function encourages both the generative model to faithfully represent the data distribution and the latent factors to have a large causal influence o…
Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents. For humans, language--particularly in the form of explanations--plays a considerable role in overcoming this challenge. Here, we show that language can play a similar role for deep RL agents in complex environments. While agents typically struggle to acquire relational and causal knowledge, augmenting their experience by training them to predict language descriptions and explanations can overcome these limitations. We show that language can help agents learn challeng…
Faculty of Electrical Engineering, Chalmers University of Technology（查尔姆斯理工大学电气工程学院）
Robot failures in human-centered environments are inevitable. Therefore, the ability of robots to explain such failures is paramount for interacting with humans to increase trust and transparency. To achieve this skill, the main challenges addressed in this paper are I) acquiring enough data to learn a cause-effect model of the environment and II) generating causal explanations based on that model. We address I) by learning a causal Bayesian network from simulation data. Concerning II), we propose a novel method that enables robots to generate contrastive explanations upon task failures. The e…
Prevalent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen. In this paper, we use causal models to derive causal explanations of behaviour of reinforcement learning agents. We present an approach that learns a structural causal model during reinforcement learning and encodes causal relationships between variables of interest. This model is then used to generat…
We propose an abductive diagnosis theory that integrates probabilistic, causal and taxonomic knowledge. Probabilistic knowledge allows us to select the most likely explanation; causal knowledge allows us to make reasonable independence assumptions; taxonomic knowledge allows causation to be modeled at different levels of detail, and allows observations be described in different levels of precision. Unlike most other approaches where a causal explanation is a hypothesis that one or more causative events occurred, we define an explanation of a set of observations to be an occurrence of a chain o…
SKEMA Business School（SKEMA商学院）；Millennium Institute for Foundations of Data Research（千禧数据基础研究所）
In this expository article we highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in {\em explainable AI}, referring to origins and connections of and among different approaches. We describe in simple terms, explanations in data management and machine learning that are based on attribution-scores, and counterfactuals as found in the area of causality. We elaborate on the importance of logical reasoning when dealing with counterfactuals, and their use for score computation.
We present CLEAR, a method for learning session-specific causal graphs, in the possible presence of latent confounders, from attention in pre-trained attention-based recommenders. These causal graphs describe user behavior, within the context captured by attention, and can provide a counterfactual explanation for a recommendation. In essence, these causal graphs allow answering "why" questions uniquely for any specific session. Using empirical evaluations we show that, compared to naively using attention weights to explain input-output relations, counterfactual explanations found by CLEAR are …
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop methods to extract salient concepts throughout a target network by using autoencoders trained to extract human-understandable representations of network activations. We then build a bayesian causal model using these extracted concepts as variables in order to explain image class…
Inspired by a novel action-theoretic formalization of actual cause, Khan and Lespérance (2021) recently proposed a first account of causal knowledge that supports epistemic effects, models causal knowledge dynamics, and allows sensing actions to be causes of observed effects. To date, no other study has looked specifically at these issues. But their formalization is not sufficiently expressive enough to model explanations via causal analysis of mental states as it ignores a crucial aspect of theory of mind, namely motivations. In this paper, we build on their work to support causal reasoning a…
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Causal reasoning is the main learning and explanation tool used by humans. AI systems should possess causal reasoning capabilities to be deployed in the real world with trust and reliability. Introducing the ideas of causality to machine learning helps in providing better learning and explainable models. Explainability, causal disentanglement are some important aspects of any machine learning model. Causal explanations are required to believe in a model's decision and causal disentanglement learning is important for transfer learning applications. We exploit the ideas of causality to be used i…
Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases. While there are tools that can help understand whether such biases exist, they do not distinguish between correlation and causation, and might be ill-suited for text-based models and for reasoning about high level language concepts. A key problem of estimating the causal effect of a concept of interest on a given model is that this estimation requires the ge…
