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.
University of Utah（犹他大学）；University of Arizona（亚利桑那大学）；Haverford College（哈弗福德学院）
Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. These methods define a cooperative game between the features of a model and distribute influence among these input elements using some form of the game's unique Shapley values. Justification for these methods rests on two pillars: their desirable mathematical properties, and their applicability to specific motivations for explanations. We show that mathematical problems arise when Shapley values are used for feature importance and that the solutions to mitigate these necessarily…
Mathematical Sciences Department, Claremont McKenna College（克莱门特麦肯纳学院数学科学系）；Barcelona Supercomputing Center, Barcelona, Spain（巴塞罗那超级计算中心）；Department of Computer Science and Engineering, New York University（纽约大学计算机科学与工程系）
Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration
Ludwig-Maximilians-Universität (LMU) Munich（慕尼黑大学）；John A. Paulson Harvard School of Engineering and Applied Sciences, Harvard University（哈佛大学约翰·保尔森工程与应用科学学院）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Wyss Institute for Biologically Inspired Engineering, Harvard University（哈佛大学怀斯生物启发工程研究所）
Explaining AI systems is fundamental both to the development of high performing models and to the trust placed in them by their users. The Shapley framework for explainability has strength in its general applicability combined with its precise, rigorous foundation: it provides a common, model-agnostic language for AI explainability and uniquely satisfies a set of intuitive mathematical axioms. However, Shapley values are too restrictive in one significant regard: they ignore all causal structure in the data. We introduce a less restrictive framework, Asymmetric Shapley values (ASVs), which are…
MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems
University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Virtue AI；University of Chicago（芝加哥大学）；Wells Fargo（摩根大通）；Salesforce；University of California, Santa Barbara（加州大学圣芭芭拉分校）
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Departamento de Computación, Facultad de Ciencias Exactas y Naturales, UBA（布宜诺斯艾利斯大学自然科学与精确科学学院计算机科学系）；Instituto de Ciencias de la Computación (ICC), CONICET（国家科学与技术研究理事会计算机科学研究所）
Explaining the predictions of opaque machine learning algorithms is an important and challenging task, especially as complex models are increasingly used to assist in high-stakes decisions such as those arising in healthcare and finance. Most popular tools for post-hoc explainable artificial intelligence (XAI) are either insensitive to context (e.g., feature attributions) or difficult to summarize (e.g., counterfactuals). In this paper, I introduce $\textit{rational Shapley values}$, a novel XAI method that synthesizes and extends these seemingly incompatible approaches in a rigorous, flexible…
Digital University Kerala (IIITMK)（喀拉拉数字大学（印度信息技术与管理学院喀拉拉邦分院））
In recent years, causal modelling has been used widely to improve generalization and to provide interpretability in machine learning models. To determine cause-effect relationships in the absence of a randomized trial, we can model causal systems with counterfactuals and interventions given enough domain knowledge. However, there are several cases where domain knowledge is almost absent and the only recourse is using a statistical method to estimate causal relationships. While there have been several works done in estimating causal relationships in unstructured data, we are yet to find a well-…
Department of Statistics, LMU Munich（LMU慕尼黑统计系）；Department of Electrical Engineering and Computer Science, UC Berkeley（伯克利电子工程与计算机科学系）；Mathematical Sciences Department, Claremont McKenna College（克莱门茨麦肯纳学院数学科学系）
A new method is proposed for exploiting causal independencies in exact Bayesian network inference. A Bayesian network can be viewed as representing a factorization of a joint probability into the multiplication of a set of conditional probabilities. We present a notion of causal independence that enables one to further factorize the conditional probabilities into a combination of even smaller factors and consequently obtain a finer-grain factorization of the joint probability. The new formulation of causal independence lets us specify the conditional probability of a variable given its parents…
In the field of machine learning there is a growing interest towards more robust and generalizable algorithms. This is for example important to bridge the gap between the environment in which the training data was collected and the environment where the algorithm is deployed. Machine learning algorithms have increasingly been shown to excel in finding patterns and correlations from data. Determining the consistency of these patterns and for example the distinction between causal correlations and nonsensical spurious relations has proven to be much more difficult. In this paper a regularization…
Hong Kong University of Science & Technology（香港科技大学）
This paper explores the role of independence of causal influence (ICI) in Bayesian network inference. ICI allows one to factorize a conditional probability table into smaller pieces. We describe a method for exploiting the factorization in clique tree propagation (CTP) - the state-of-the-art exact inference algorithm for Bayesian networks. We also present empirical results showing that the resulting algorithm is significantly more efficient than the combination of CTP and previous techniques for exploiting ICI.
Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
KU Leuven（KU Leuven（天主教鲁汶大学））；Laboratory of Multi-omics Integrative Bioinformatics（多组学整合生物信息学实验室）；KU Leuven Institute for Single Cell Omics (LISCO)（KU Leuven单细胞组学研究所（LISCO））；Department of Electrical Engineering, KU Leuven（KU Leuven电气工程系）；Department of Development and Regeneration, KU Leuven（KU Leuven发育与再生系）
VU Amsterdam（阿姆斯特丹自由大学）；University of Amsterdam（阿姆斯特丹大学）；Radboud University Nijmegen（内梅亨大学）
Constraint-based causal discovery from limited data is a notoriously difficult challenge due to the many borderline independence test decisions. Several approaches to improve the reliability of the predictions by exploiting redundancy in the independence information have been proposed recently. Though promising, existing approaches can still be greatly improved in terms of accuracy and scalability. We present a novel method that reduces the combinatorial explosion of the search space by using a more coarse-grained representation of causal information, drastically reducing computation time. Add…
University of California Santa Cruz（加州大学圣克鲁兹分校）；Information Sciences Institute（信息科学研究所）
Knowledge bases (KB) constructed through information extraction from text play an important role in query answering and reasoning. In this work, we study a particular reasoning task, the problem of discovering causal relationships between entities, known as causal discovery. There are two contrasting types of approaches to discovering causal knowledge. One approach attempts to identify causal relationships from text using automatic extraction techniques, while the other approach infers causation from observational data. However, extractions alone are often insufficient to capture complex patte…
