Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predictions of graph convolutional networks?" A possible approach to answer this question is to visualize evidence substructures responsible for the predictions. For chemical property prediction tasks, the sample size of the training data is often small and/or a label imbalance problem occurs, where a few samples belong to a single class and the majority of samples belong to the other classes. This can lead to uncertainty related to the learned parameters of the machine learning model. To address this uncertainty, we propose BayesGrad, utilizing the Bayesian predictive distribution, to define the importance of each node in an input graph, which is computed efficiently using the dropout technique. We demonstrate that BayesGrad successfully visualizes the substructures responsible for the label prediction in the artificial experiment, even when the sample size is small. Furthermore, we use a real dataset to evaluate the effectiveness of the visualization. The basic idea of BayesGrad is not limited to graph-structured data and can be applied to other data types.
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所（HIIT））；Aalto University（阿尔托大学）
We introduce a method, KL-LIME, for explaining predictions of Bayesian predictive models by projecting the information in the predictive distribution locally to a simpler, interpretable explanation model. The proposed approach combines the recent Local Interpretable Model-agnostic Explanations (LIME) method with ideas from Bayesian projection predictive variable selection methods. The information theoretic basis helps in navigating the trade-off between explanation fidelity and complexity. We demonstrate the method in explaining MNIST digit classifications made by a Bayesian deep convolutional…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University of Mannheim（曼海姆大学）
Convolutional neural networks (CNNs) have achieved astonishing performance on various image classification tasks, but it is difficult for humans to understand how a classification comes about. Recent literature proposes methods to explain the classification process to humans. These focus mostly on visualizing feature maps and filter weights, which are not very intuitive for non-experts in analyzing a CNN classification. In this paper, we propose FilTag, an approach to effectively explain CNNs even to non-experts. The idea is that when images of a class frequently activate a convolutional filte…
Deep convolutional neural networks (CNNs) have been actively adopted in the field of music information retrieval, e.g. genre classification, mood detection, and chord recognition. However, the process of learning and prediction is little understood, particularly when it is applied to spectrograms. We introduce auralisation of a CNN to understand its underlying mechanism, which is based on a deconvolution procedure introduced in [2]. Auralisation of a CNN is converting the learned convolutional features that are obtained from deconvolution into audio signals. In the experiments and discussions,…
Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relev…
Interpretability is an important property for visual models as it helps researchers and users understand the internal mechanism of a complex model. However, generating semantic explanations about the learned representation is challenging without direct supervision to produce such explanations. We propose a general framework, Latent Visual Semantic Explainer (LaViSE), to teach any existing convolutional neural network to generate text descriptions about its own latent representations at the filter level. Our method constructs a mapping between the visual and semantic spaces using generic image …
Institute of Information Systems, University of Liechtenstein（列支敦士登大学信息系统学院）；Department of Information Systems, HEC, University of Lausanne（洛桑大学高等商学院信息系统系）
We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN). It uses a decoder to transform the non-interpretable representation of the given layer to a representation that is more similar to the domain a human is familiar with. In an image recognition problem, one can recognize what information is represented by a layer by contrasting reconstructed images of \emph{ClaDec} with those of a conventional auto-encoder(AE) serving as reference. We also extend \emph{ClaDec} to allow the trade-off betw…
Université Paris Cité（巴黎西岱大学）；EDF R&D（法国电力集团研发中心）；IUF（法国大学研究院）
Data series classification is an important and challenging problem in data science. Explaining the classification decisions by finding the discriminant parts of the input that led the algorithm to some decisions is a real need in many applications. Convolutional neural networks perform well for the data series classification task; though, the explanations provided by this type of algorithm are poor for the specific case of multivariate data series. Addressing this important limitation is a significant challenge. In this paper, we propose a novel method that solves this problem by highlighting …
Recent years, many researches attempt to open the black box of deep neural networks and propose a various of theories to understand it. Among them, Information Bottleneck (IB) theory claims that there are two distinct phases consisting of fitting phase and compression phase in the course of training. This statement attracts many attentions since its success in explaining the inner behavior of feedforward neural networks. In this paper, we employ IB theory to understand the dynamic behavior of convolutional neural networks (CNNs) and investigate how the fundamental features such as convolutiona…
Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating saliency maps. However, they are not applicable when the parameters and the gradients of the underlying models are unavailable. Recently, model-agnostic methods have also received attention. As one of them, \textit{Prediction Difference Analysis} (PDA), a probabilistic sound methodology, was proposed. In this work, we first show that PDA can suffer from saturated classifiers. The sa…
IDLab, Ghent University - imec（根特大学-imec IDLab实验室）
Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us …
CNRS（法国国家科学研究中心）；GIPSA-lab（格勒诺布尔交互物理与声学实验室）；NYU Center for Data Science（纽约大学数据科学中心）；IMB（勃艮第数学研究所）；Inria Paris（法国国家信息与自动化研究所巴黎分院）
We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior on standard models of random graphs, where nodes are represented by random latent variables and edges are drawn according to a similarity kernel. This allows us to overcome the difficulties of dealing with discrete notions such as isomorphisms on very large graphs, by considering instead more natural geometric aspects. We first study the convergence of GCNs to their continuous counterpart as the number of nodes grows. Our results are fully non-asymptotic and are valid for relatively sparse graphs with an ave…
Deep convolutional networks have been quite successful at various image classification tasks. The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on the foreground object as a whole. However, humans typically reason by dissecting an image and pointing out the presence of smaller concepts. The final output is often an aggregation of the presence or absence of these smaller concepts. In this work, we propose MACE: a Model Agnostic Concept Extractor, which can explain the working of a convolutional network…
Because of their state-of-the-art performance in computer vision, CNNs are becoming increasingly popular in a variety of fields, including medicine. However, as neural networks are black box function approximators, it is difficult, if not impossible, for a medical expert to reason about their output. This could potentially result in the expert distrusting the network when he or she does not agree with its output. In such a case, explaining why the CNN makes a certain decision becomes valuable information. In this paper, we try to open the black box of the CNN by inspecting and visualizing the …
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；Korea University（高丽大学）
Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional neural network (CNN) trained on a topic categorization task. Our analysis highlights which words are relevant for a specific prediction of the CNN. We compare our technique to standard sensitivity analysis, both qualitatively and quantitatively, using a "word deleting" perturbatio…
Central University of Finance and Economics（中央财经大学）；Southern University of Science and Technology（南方科技大学）；University of York（约克大学）
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap b…
The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into actionable insight. Here, we propose a framework to analyze predictions in terms of the model's internal features by inspecting information flow through the network. Given a trained network and a test image, we select neurons by two metrics, both measured over a set of images created by perturbations to the input image: (1) magnitude of the correlation between t…
We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed …
We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a) find the most influential training examples during training and b) analyze which classes attributed most to the final representation. Our method is general: it can be wrapped around any iterative optimization procedure and covers a variety of neural network architectures, including feed-forward networks and convolutional neural networks. We first propose a m…
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
Fraunhofer Heinrich-Hertz-Institute（弗劳恩霍夫海因茨·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所（BIFOLD））
Expanding the scope of graph-based, deep-learning models to noncovalent protein-ligand interactions has earned increasing attention in structure-based drug design. Modeling the protein-ligand interactions with graph neural networks (GNNs) has experienced difficulties in the conversion of protein-ligand complex structures into the graph representation and left questions regarding whether the trained models properly learn the appropriate noncovalent interactions. Here, we proposed a GNN architecture, denoted as InteractionNet, which learns two separated molecular graphs, being covalent and nonco…
Knowledge extraction is used to convert neural networks into symbolic descriptions with the objective of producing more comprehensible learning models. The central challenge is to find an explanation which is more comprehensible than the original model while still representing that model faithfully. The distributed nature of deep networks has led many to believe that the hidden features of a neural network cannot be explained by logical descriptions simple enough to be comprehensible. In this paper, we propose a novel layerwise knowledge extraction method using M-of-N rules which seeks to obta…
In the pursuit of explaining implicit regularization in deep learning, prominent focus was given to matrix and tensor factorizations, which correspond to simplified neural networks. It was shown that these models exhibit an implicit tendency towards low matrix and tensor ranks, respectively. Drawing closer to practical deep learning, the current paper theoretically analyzes the implicit regularization in hierarchical tensor factorization, a model equivalent to certain deep convolutional neural networks. Through a dynamical systems lens, we overcome challenges associated with hierarchy, and est…
Rensselaer Polytechnic Institute（伦斯勒理工学院）；United Imaging Intelligence（联影智能）；University of California Riverside（加州大学河滨分校）；Northeastern University（东北大学）
Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent effort in using visual attention maps as a means for visual explanations. A key problem, however, is these methods are designed for classification and categorization tasks, and their extension to explaining generative models, e.g. variational autoencoders (VAE) is not trivial. In this work, we take a step towards bridging this crucial gap, proposing the firs…
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. Speci…
Georgia Institute of Technology（佐治亚理工学院）；Oregon State University（俄勒冈州立大学）
The success of deep learning solving previously-thought hard problems has inspired many non-experts to learn and understand this exciting technology. However, it is often challenging for learners to take the first steps due to the complexity of deep learning models. We present our ongoing work, CNN 101, an interactive visualization system for explaining and teaching convolutional neural networks. Through tightly integrated interactive views, CNN 101 offers both overview and detailed descriptions of how a model works. Built using modern web technologies, CNN 101 runs locally in users' web brows…
Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explana…
We study algebraic neural networks (AlgNNs) with commutative algebras which unify diverse architectures such as Euclidean convolutional neural networks, graph neural networks, and group neural networks under the umbrella of algebraic signal processing. An AlgNN is a stacked layered information processing structure where each layer is conformed by an algebra, a vector space and a homomorphism between the algebra and the space of endomorphisms of the vector space. Signals are modeled as elements of the vector space and are processed by convolutional filters that are defined as the images of the …
Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学）；St. Pölten University of Applied Sciences（圣珀尔滕应用科学大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；TU Wien（维也纳工业大学）
State-of-the-art machine learning (ML) models are highly effective in classifying gait analysis data, however, they lack in providing explanations for their predictions. This "black-box" characteristic makes it impossible to understand on which input patterns, ML models base their predictions. The present study investigates whether Explainable Artificial Intelligence methods, i.e., Layer-wise Relevance Propagation (LRP), can be useful to enhance the explainability of ML predictions in gait classification. The research question was: Which input patterns are most relevant for an automated gender…
Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI). However, there is a lack of methods that can predict compound-protein affinity from sequences alone with high applicability, accuracy, and interpretability. Results: We present a seamless integration of domain knowledges and learning-based approaches. Under novel representations of structurally-annotated protein sequences, a semi-supervised deep learning model that unifies recurrent and convolutional neural networks has been proposed to exploit both unlabeled and labeled data, for jointly encoding mo…
St. Pölten University of Applied Sciences（圣珀尔滕应用科学大学）；Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；TU Wien（维也纳工业大学）
Machine learning (ML) models have proven effective in classifying gait analysis data, e.g., binary classification of young vs. older adults. ML models, however, lack in providing human understandable explanations for their predictions. This "black-box" behavior impedes the understanding of which input features the model predictions are based on. We investigated an Explainable Artificial Intelligence method, i.e., Layer-wise Relevance Propagation (LRP), for gait analysis data. The research question was: Which input features are used by ML models to classify age-related differences in walking pa…
Quality and Usability Lab, TU Berlin（柏林工业大学质量与可用性实验室）；Language Technology, DFKI Berlin（柏林德国人工智能研究中心语言技术部）
Estimating quality of transmitted speech is known to be a non-trivial task. While traditionally, test participants are asked to rate the quality of samples; nowadays, automated methods are available. These methods can be divided into: 1) intrusive models, which use both, the original and the degraded signals, and 2) non-intrusive models, which only require the degraded signal. Recently, non-intrusive models based on neural networks showed to outperform signal processing based models. However, the advantages of deep learning based models come with the cost of being more challenging to interpret…
Technische Universität Berlin（柏林工业大学）；Nota AI GmbH（诺塔人工智能有限公司）；Aignostics GmbH（艾格诺斯蒂克斯有限公司）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Singapore University of Technology and Design（新加坡科技设计大学）；University of Oslo（奥斯陆大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所（BIFOLD））；Korea University（高丽大学）；Max Planck Institut für Informatik（马克斯·普朗克信息学研究所）
The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the weights of various layers while at the same time aiming to not sacrifice performance. In this paper, we propose a novel criterion for CNN pruning inspired by neural network interpretability: The most relevant units, i.e. weights or filters, are automatically found using their relevance scores obtained from concepts of explainable AI (XAI). By exploring this id…
LITIS Lab（LITIS实验室）；University of Rouen Normandy（鲁昂诺曼底大学）
This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. The obtained general framework allows to lead a spectral analysis of the most popular ConvGNNs, explaining their performance and showing their limits. Moreover, the proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain…
CSAIL, MIT（麻省理工学院计算机科学与人工智能实验室）；GoogleX（谷歌X实验室）；Center for Brains, Minds and Machines, MIT（麻省理工学院大脑、心智与机器中心）；IIT（意大利理工学院）；Claremont Graduate University（克莱蒙特研究生大学）；Alphabet (Google) X（Alphabet（谷歌）X实验室）
A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics associated to gradient descent minimization of nonlinear networks is topologically equivalent, near the asymptotically stable minima of the empirical error, to linear gradient system in a quadratic potential with a degenerate (for square loss) or almost degenerate (for logistic or crossentropy loss) Hessian. The proposition depends on the qualitative theory…
The rapid development of Convolutional Neural Networks (CNNs) in recent years has triggered significant breakthroughs in many machine learning (ML) applications. The ability to understand and compare various CNN models available is thus essential. The conventional approach with visualizing each model's quantitative features, such as classification accuracy and computational complexity, is not sufficient for a deeper understanding and comparison of the behaviors of different models. Moreover, most of the existing tools for assessing CNN behaviors only support comparison between two models and l…
University of Bonn（波恩大学）；University of Iowa（爱荷华大学）；Iowa State University（爱荷华州立大学）；Wuhan University（武汉大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Crop yield forecasting depends on many interactive factors, including crop genotype, weather, soil, and management practices. This study analyzes the performance of machine learning and deep learning methods for winter wheat yield prediction using an extensive dataset of weather, soil, and crop phenology variables in 271 counties across Germany from 1999 to 2019. We proposed a Convolutional Neural Network (CNN) model, which uses a 1-dimensional convolution operation to capture the time dependencies of environmental variables. We used eight supervised machine learning models as baselines and ev…
Slovak University of Technology（斯洛伐克理工大学）；Johannes Kepler University（约翰内斯·开普勒大学）
In many practical applications, deep neural networks have been typically deployed to operate as a black box predictor. Despite the high amount of work on interpretability and high demand on the reliability of these systems, they typically still have to include a human actor in the loop, to validate the decisions and handle unpredictable failures and unexpected corner cases. This is true in particular for failure-critical application domains, such as medical diagnosis. We present a novel approach to explain and support an interpretation of the decision-making process to a human expert operating…
Colorado State University（科罗拉多州立大学）；Cooperative Institute for Research in the Atmosphere（大气研究合作研究所）
Convolutional neural networks (CNNs) have recently attracted great attention in geoscience due to their ability to capture non-linear system behavior and extract predictive spatiotemporal patterns. Given their black-box nature however, and the importance of prediction explainability, methods of explainable artificial intelligence (XAI) are gaining popularity as a means to explain the CNN decision-making strategy. Here, we establish an intercomparison of some of the most popular XAI methods and investigate their fidelity in explaining CNN decisions for geoscientific applications. Our goal is to…
Computer Science Department, University College London（伦敦大学学院计算机科学系）
3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs. An equivariant representation vector has two components: the invariant identity part, and a discernable encoding of the transformation. Models that can't explain pose-differences r…
In recent years convolutional neural networks (CNN) have shown striking progress in various tasks. However, despite the high performance, the training and prediction process remains to be a black box, leaving it a mystery to extract what neurons learn in CNN. In this paper, we address the problem of interpreting a CNN from the aspects of the input image's focus and preference, and the neurons' domination, activation and contribution to a concrete final prediction. Specifically, we use two techniques - visualization and clustering - to tackle the problems above. Visualization means the method o…
Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open question. The purpose of this article is to describe and substantiate the geometric and topological view of the learning process of neural networks. Our attention is focused on the internal representation of neural networks and on the dynamics of changes in the topology and geometry of the data manifold on different layers. We also propose a method for assessing the generalizing ability of neural networks based on top…
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network bandwidth is limited. In this paper, we propose a novel end-to-end Neural Image Compression and Explanation (NICE) framework that learns to (1) explain the predictions of convolutional neural networks (CNNs), and (2) subsequently compress the input images for efficient storage or t…
