We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such). The neural network architecture is viewed as a Structural Causal Model, and a methodology to compute the causal effect of each feature on the output is presented. With reasonable assumptions on the causal structure of the input data, we propose algorithms to efficiently compute the causal effects, as well as scale the approach to data with large dimensionality. We also show how this method can be used for recurrent neural networks. We report experimental results on both simulated and real datasets showcasing the promise and usefulness of the proposed algorithm.
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…
With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing need for effective techniques for explaining such models and their predictions. We aim to address this problem in settings where the predictive model is a black box; That is, we can only observe the response of the model to various inputs, but have no knowledge about the internal structure of the predictive model, its parameters, the objective function, and the algorithm used t…
Causal-discovery-based root-cause analysis and its application in time-series prediction error diagnosis
Graduate School of Interdisciplinary Science and Engineering in Health Systems（交叉学科科学与工程健康系统研究生院）；Toshiba Corporation（东芝公司）；System AI Laboratory（系统人工智能实验室）；Faculty of Data Science（数据科学学院）
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）
Granger causal inference for climate change attribution
Climate and Ecosystem Sciences Division, LBNL（劳伦斯伯克利国家实验室气候与生态系统科学部）；College of Engineering, University of Michigan（密歇根大学工程学院）；Applied Mathematics and Computational Research Division, LBNL（劳伦斯伯克利国家实验室应用数学与计算研究部）
本文探讨了格兰杰因果推断在气候变迁归因中的应用，对比了传统方法，强调其快速性和有效性，主张融合格兰杰与 Pearl 因果方法以提高归因准确性。
While rankings are at the heart of social science research, little is known about how to analyze ranking data in experimental studies. This paper introduces a potential-outcomes framework to perform causal inference when outcome data are ranking data. It introduces a class of causal estimands tailored to ranked outcomes and develops methods for estimation and inference. Furthermore, it extends the framework to partially ranked data. I show that partial rankings can be considered a selection problem and propose nonparametric sharp bounds for the treatment effects. Using the methods, I reanalyze…
We describe a formal approach based on graphical causal models to identify the "root causes" of the change in the probability distribution of variables. After factorizing the joint distribution into conditional distributions of each variable, given its parents (the "causal mechanisms"), we attribute the change to changes of these causal mechanisms. This attribution analysis accounts for the fact that mechanisms often change independently and sometimes only some of them change. Through simulations, we study the performance of our distribution change attribution method. We then present a real-wo…
Causal Attribution of Coastal Water Clarity Degradation to Nickel Processing Expansion at the Indonesia Morowali Industrial Park, Sulawesi
University of California, Riverside（加州大学河滨分校）；State University of New York, Binghamton（纽约州立大学宾汉姆顿分校）；Bandung Institute of Technology（万隆理工学院）；Colorado School of Mines（科罗拉多矿业学院）；Brierley Associates（布莱尔利协会）
SRI International（斯坦福国际研究院）；University of Central Florida（中佛罗里达大学）；University of Wisconsin（威斯康星大学）；U.S. Army Research Laboratory（美国陆军研究实验室）
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally masking high attribution features. We study the robustness of machine learning models on benign and adversarial inputs in this neighborhood. Our study indicates that benign inputs are robust to the masking of high attribution features but adversarial inputs generated by the state-of-the-art adversarial attack methods such as DeepFool, FGSM, CW and PGD, are not r…
In this review, we discuss approaches for learning causal structure from data, also called causal discovery. In particular, we focus on approaches for learning directed acyclic graphs (DAGs) and various generalizations which allow for some variables to be unobserved in the available data. We devote special attention to two fundamental combinatorial aspects of causal structure learning. First, we discuss the structure of the search space over causal graphs. Second, we discuss the structure of equivalence classes over causal graphs, i.e., sets of graphs which represent what can be learned from o…
This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs). As an illustration of the framework we prove a topological causal hierarchy theorem, showing that substantive assumption-free causal inference is possible only in a meager set of SCMs. Thanks to a known correspondence between open sets in the weak topology and statistically verifiable hypotheses, our results show that inductive assumptions sufficient to license valid causal inferences are statistically unverifia…
TCS Research（TCS研究院）；Indraprastha Institute of Information Technology Delhi（因德拉普拉斯信息技术学院德里分校）
Causal inference (CI) in observational studies has received a lot of attention in healthcare, education, ad attribution, policy evaluation, etc. Confounding is a typical hazard, where the context affects both, the treatment assignment and response. In a multiple treatment scenario, we propose the neural network based MultiMBNN, where we overcome confounding by employing generalized propensity score based matching, and learning balanced representations. We benchmark the performance on synthetic and real-world datasets using PEHE, and mean absolute percentage error over ATE as metrics. MultiMBNN…
The causal effect of showing an ad to a potential customer versus not, commonly referred to as "incrementality", is the fundamental question of advertising effectiveness. In digital advertising three major puzzle pieces are central to rigorously quantifying advertising incrementality: ad buying/bidding/pricing, attribution, and experimentation. Building on the foundations of machine learning and causal econometrics, we propose a methodology that unifies these three concepts into a computationally viable model of both bidding and attribution which spans the randomization, training, cross valida…
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.
This paper describes a practical system for Multi Touch Attribution (MTA) for use by a publisher of digital ads. We developed this system for JD.com, an eCommerce company, which is also a publisher of digital ads in China. The approach has two steps. The first step ('response modeling') fits a user-level model for purchase of a product as a function of the user's exposure to ads. The second ('credit allocation') uses the fitted model to allocate the incremental part of the observed purchase due to advertising, to the ads the user is exposed to over the previous T days. To implement step one, w…
Indian Institute of Technology, Kharagpur（印度理工学院克勒格布尔分校）；TCS Research & Innovation（塔塔咨询服务公司研究与创新部）；IIIT-Delhi（德里印度信息技术学院）
Advertising channels have evolved from conventional print media, billboards and radio advertising to online digital advertising (ad), where the users are exposed to a sequence of ad campaigns via social networks, display ads, search etc. While advertisers revisit the design of ad campaigns to concurrently serve the requirements emerging out of new ad channels, it is also critical for advertisers to estimate the contribution from touch-points (view, clicks, converts) on different channels, based on the sequence of customer actions. This process of contribution measurement is often referred to a…
Causal Attribution of Model Performance Gaps in Medical Imaging Under Distribution Shifts
CIBM Center for Biomedical Imaging（生物医学成像中心）；Department of Radiology, Lausanne University Hospital and University of Lausanne（拉沃大学医院放射科）；MedGIFT, Institute of Informatics, School of Management, HES–SO Valais–Wallis University of Applied Sciences and Arts Western Switzerland（MedGIFT，信息学院，管理学院，瓦莱-瓦莱大学应用科学和艺术西瑞士）
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
School of Computer Science, Guangdong University of Technology（广东工业大学计算机学院）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））；University of Cambridge（剑桥大学）；Shantou University（汕头大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
Department of Computer Science, Fu Foundation School of Engineering and Applied Science, Columbia University, New York, NY, USA（计算机科学系，工程与应用科学基金会学院，哥伦比亚大学，纽约，纽约州，美国）
Penn State University（宾夕法尼亚州立大学）；University of Mississippi（密西西比大学）
Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO). Given an artifact, especially a text t in question, an AA solution aims to accurately attribute t to its true author out of many candidate authors while an AO solution aims to modify t to hide its true authorship. Traditionally, the notion of authorship and its accompanying privacy concern is only toward human authors. However, in recent years, due to the explosive advancements in Neural Text Generation (NTG) techniques in NLP, capable of s…
Fair feature attribution for multi-output prediction: a Shapley-based perspective
\, Chair of Computational Mathematics, DeustoTech, University of Deusto, Avenida de las Universidades 24, 48007 Bilbao, Basque Country, Spain \, Chair for dynamics, control, machine learning；numerics (Alexander Von Humboldt-Professorship), Department of Mathematics, Friedrich-Alexander-Universit\"at Erlangen-N\"urnberg, 91058, Erlangen, Germany. \, Universidad Aut\'onoma de Madrid, Departamento de Matem\'aticas, Ciudad Universitaria de Cantoblanco, 28049 Madrid, Spain. \, ATLAS Molecular Pharma, Parque Tecnol\'ogico de Bizkaia, Ed. 800, 48160 Derio, Spain. \, Precision Medicine；Metabolism Laboratory, CIC bioGUNE, Basque Research
Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective
University of Science and Technology of China（中国科学技术大学）；National Lab of Pattern Recognition, Institute of Automation, CAS（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
University of Science and Technology of China（中国科学技术大学）；CCCD Key Lab of Ministry of Culture and Tourism（文化和旅游部CCCD重点实验室）；National University of Singapore（新加坡国立大学）
Explainability is crucial for probing graph neural networks (GNNs), answering questions like "Why the GNN model makes a certain prediction?". Feature attribution is a prevalent technique of highlighting the explanatory subgraph in the input graph, which plausibly leads the GNN model to make its prediction. Various attribution methods exploit gradient-like or attention scores as the attributions of edges, then select the salient edges with top attribution scores as the explanation. However, most of these works make an untenable assumption - the selected edges are linearly independent - thus lea…
Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
School of Computer Science and Technology, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院）；School of Cyber Science and Engineering, Xi’an Jiaotong University（西安交通大学网络安全工程学院）；Department of Computer Science and Engineering, the John Hopcroft Center, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系、霍夫曼中心）；Department of Data Science, New Jersey Institute of Technology（新泽西理工学院数据科学系）
