Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive performance. New advances in (unsupervised) representation learning and transfer learning, however, raise the need for an explanatory framework for networks that are trained without a specific downstream task. We address these challenges by showing how explainability can be an aid, rather than an obstacle, towards better and more efficient representations. Specifically, we propose a natural aggregation method generalizing attribution maps between any two (convolutional) layers of a neural network. Additionally, we employ such attributions to define two novel scores for evaluating the informativeness and the disentanglement of latent embeddings. Extensive experiments show that the proposed scores do correlate with the desired properties. We also confirm and extend previously known results concerning the independence of some common saliency strategies from the model parameters. Finally, we show that adopting our proposed scores as constraints during the training of a representation learning task improves the downstream performance of the model.
UiT The Arctic University of Norway（挪威北极圈大学）；Technische Universität Berlin（柏林工业大学）
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making strategies. As a remedy, many post-hoc explanation and self-explanatory methods have been developed to interpret the models' behavior. These methods, in addition, enable the identification of artifacts that can be learned by the model as class-relevant features. In this work, we provide a detailed case study of the self-explaining network, ProtoPNet, in the…
University of St.Gallen (HSG)（圣加仑大学（HSG））；Deutsche Bundesbank（德意志联邦银行）
Detecting accounting anomalies is a recurrent challenge in financial statement audits. Recently, novel methods derived from Deep-Learning (DL) have been proposed to audit the large volumes of a statement's underlying accounting records. However, due to their vast number of parameters, such models exhibit the drawback of being inherently opaque. At the same time, the concealing of a model's inner workings often hinders its real-world application. This observation holds particularly true in financial audits since auditors must reasonably explain and justify their audit decisions. Nowadays, vario…
BaBE: Enhancing Fairness via Estimation of Latent Explaining Variables
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Università di Roma “La Sapienza”（罗马第一大学（萨皮恩扎大学））；Inria Saclay（法国国家信息与自动化研究所萨克雷分所）；École Polytechnique（巴黎综合理工学院）
Unsupervised Framework for Evaluating and Explaining Structural Node Embeddings of Graphs
Toronto Metropolitan University（多伦多都会大学）；SGH Warsaw School of Economics（华沙经济学院）；Patagona Technologies（帕塔戈纳科技公司）；Simons Institute for the Theory of Computing（西蒙斯计算理论研究所）
We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for why a classifier may have classified an instance positively or negatively and suggest algorithms for computing these explanations. The first type of explanation identifies a minimal set of the currently active features that is responsible for the current classification, while the second type of explanation identifies a minimal set of features whose current state (active or not…
Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Adversarial attacks are often generated by maximizing standard losses such as the cross-entropy loss or maximum-margin loss within a constraint set using Projected Gradient Descent (PGD). In this work, we introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adv…
Grapheme-to-phoneme (G2P) conversion is the process of converting the written form of words to their pronunciations. It has an important role for text-to-speech (TTS) synthesis and automatic speech recognition (ASR) systems. In this paper, we aim to evaluate and enhance the robustness of G2P models. We show that neural G2P models are extremely sensitive to orthographical variations in graphemes like spelling mistakes. To solve this problem, we propose three controlled noise introducing methods to synthesize noisy training data. Moreover, we incorporate the contextual information with the basel…
Graphs are ubiquitous in many applications, such as social networks, knowledge graphs, smart grids, etc.. Graph neural networks (GNN) are the current state-of-the-art for these applications, and yet remain obscure to humans. Explaining the GNN predictions can add transparency. However, as many graphs are not static but continuously evolving, explaining changes in predictions between two graph snapshots is different but equally important. Prior methods only explain static predictions or generate coarse or irrelevant explanations for dynamic predictions. We define the problem of explaining evolv…
Towards Few-shot Self-explaining Graph Neural Networks
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
the University of Auckland（奥克兰大学）；the University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；RIKEN AIP（理化学研究所人工智能项目）；Hong Kong Baptist University（香港浸会大学）；the University of Sydney（悉尼大学）；Shandong University（山东大学）；Shandong Research Institute of Industrial Technology（山东工业技术研究院）；the University of Tokyo（东京大学）
Texas State University（德克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）
In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contribu…
In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natural language processing into the ambit of these agents, with a recurring thread being the use of external knowledge to mimic and better human-level performance. We present one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments.
Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan（通讯工程研究院，国立台湾大学）；MediaTek Research, Taipei, Taiwan（联发科研究，台北，台湾）；Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan（电气工程系，国立台湾大学）；Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan（电气工程系，国立清华大学）；AI Research Center (AINTU), National Taiwan University, Taipei, Taiwan（人工智能研究中心（AINTU），国立台湾大学）
Technische Universität Braunschweig（布伦瑞克工业大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by developing methods for explaining the predictions of neural networks. While several of these approaches have been successfully applied in the area of computer vision, their application in security has received little attention so far. It is an open question which explanation methods are appropriate for computer security and what requirements they need to sa…
Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks
Institute of Mathematics（数学研究所）；University of Würzburg（维尔茨堡大学）；Technical University of Munich（慕尼黑工业大学）；Institute of Computer Science（计算机科学研究所）；CAIDAS；Institute of Mathematics, CAIDAS（CAIDAS数学研究所）
Simon Fraser University（西蒙弗雷泽大学）；The University of British Columbia（不列颠哥伦比亚大学）
Being able to explain the prediction to clinical end-users is a necessity to leverage the power of AI models for clinical decision support. For medical images, saliency maps are the most common form of explanation. The maps highlight important features for AI model's prediction. Although many saliency map methods have been proposed, it is unknown how well they perform on explaining decisions on multi-modal medical images, where each modality/channel carries distinct clinical meanings of the same underlying biomedical phenomenon. Understanding such modality-dependent features is essential for c…
IIT Madras（印度理工学院马德拉斯分校）；IBM Research（IBM研究院）；IBM（国际商业机器公司）；IBM Data and AI（IBM数据与人工智能部门）
Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose automatic evaluation approaches for GNN Explanations.
