We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our key technical contribution is an adversarial objective that can be used to tractably estimate mutual information assuming only the feasibility of cross entropy calculation. We develop a concrete realization of this general formulation with Markov distributions over binary encodings. We report critical and unexpected findings on practical aspects of the objective such as the choice of variational priors. We apply our model on document hashing and show that it outperforms current best baselines based on discrete and vector quantized variational autoencoders. It also yields highly compressed interpretable representations.
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic features of the input and filter the non-semantic perturbation. FBGAN is pre-trained on the clean dataset in an unsupervised manner, adversarially learning a bidirectional mapping between the high-dimensional data space and the low-dimensional semantic space; also mutual information is …
Variational autoencoders (VAEs) have ushered in a new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representation learning. In this work, we propose a simple yet powerful class of VAEs that simultaneously result in meaningful learned representations. Our solution is to combine traditional VAEs with mutual information maximization, with the goal to enhance amortized inference in VAEs using Information Theoretic techniques. We call this approach InfoMax-VAE, and such an approach can sign…
Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability that captures the maximum change of mutual information between the input and output distributions, under the worst-case input perturbation. Then, we prove a theorem that establishes a lower bound on the minimum adversarial risk that can be achieved for any downstream classifier based on its representation vulner…
One of the most crucial challenges in question answering (QA) is the scarcity of labeled data, since it is costly to obtain question-answer (QA) pairs for a target text domain with human annotation. An alternative approach to tackle the problem is to use automatically generated QA pairs from either the problem context or from large amount of unstructured texts (e.g. Wikipedia). In this work, we propose a hierarchical conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts, while maximizing the mutual information between generated QA pairs to ens…
Multimodal image-to-image translation (I2IT) aims to learn a conditional distribution that explores multiple possible images in the target domain given an input image in the source domain. Conditional generative adversarial networks (cGANs) are often adopted for modeling such a conditional distribution. However, cGANs are prone to ignore the latent code and learn a unimodal distribution in conditional image synthesis, which is also known as the mode collapse issue of GANs. To solve the problem, we propose a simple yet effective method that explicitly estimates and maximizes the mutual informat…
Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the mutual information between two random variables is hard to measure directly in high dimensional spaces, some recent studies have shown that an implicit optimization of MI can be achieved with an encoder-discriminator architecture similar to that of Generative Adversarial Networks (GANs). In this work, we learn representations that capture speaker identities by…
Recently, maximizing mutual information has emerged as a powerful method for unsupervised graph representation learning. The existing methods are typically effective to capture information from the topology view but ignore the feature view. To circumvent this issue, we propose a novel approach by exploiting mutual information maximization across feature and topology views. Specifically, we first utilize a multi-view representation learning module to better capture both local and global information content across feature and topology views on graphs. To model the information shared by the featu…
We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local spatio-temporal context by observing it from different locations (e.g., camera positions within a scene), and via different modalities (e.g., tactile, auditory, or visual). Or, an ImageNet image could provide a context from which one produces multiple views by repeatedly applying data augmentation. Maximizing mutual information between features extracted from these vi…
Unsupervised domain adaptation (UDA) aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization Domain Adaptation) with strong theoretical guarantees. To be specific, SIDA implements adaptation by maximizing mutual information (MI) between features. In the framework, a surrogate joint distribution models the underlying joint distribution of the unlabeled target domain. Our theoretical analysis validates SIDA by bounding the expected risk on target domain …
Seoul National University（首尔国立大学）；Samsung Advanced Institute of Technology（三星综合技术院）
We propose an information-theoretic knowledge distillation approach for the compression of generative adversarial networks, which aims to maximize the mutual information between teacher and student networks via a variational optimization based on an energy-based model. Because the direct computation of the mutual information in continuous domains is intractable, our approach alternatively optimizes the student network by maximizing the variational lower bound of the mutual information. To achieve a tight lower bound, we introduce an energy-based model relying on a deep neural network to repres…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）；Rutgers University（罗格斯大学）
Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistical limitations are inherent to any method of measuring mutual information. More specifically, we show that any distribution-free high-confidence lower bound on mutual information estimated from N samples cannot be larger than O(ln N ).
Kyushu Institute of Technology（九州工业大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；The University of Tokyo（东京大学）
Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that learning a set of diverse solutions is beneficial because diversity enables robust few-shot adaptation. Although existing methods learn diverse solutions by using the mutual information as unsupervised rewards, such an approach often suffers from the bias of the gradient estimator induced by value function approximation. In this study, we propose a novel method that can learn diverse solutions without suffering the bia…
We build a natural connection between the learning problem, co-training, and forecast elicitation without verification (related to peer-prediction) and address them simultaneously using the same information theoretic approach. In co-training/multiview learning, the goal is to aggregate two views of data into a prediction for a latent label. We show how to optimally combine two views of data by reducing the problem to an optimization problem. Our work gives a unified and rigorous approach to the general setting. In forecast elicitation without verification we seek to design a mechanism that eli…
Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
End-to-end speech synthesis methods already achieve close-to-human quality performance. However compared to HMM-based and NN-based frame-to-frame regression methods, they are prone to some synthesis errors, such as missing or repeating words and incomplete synthesis. We attribute the comparatively high utterance error rate to the local information preference of conditional autoregressive models, and the ill-posed training objective of the model, which describes mostly the training status of the autoregressive module, but rarely that of the condition module. Inspired by InfoGAN, we propose to m…
We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, where meta-controller and controller play minimax over the mutual information objective but cooperate on maximizing expected rewards.
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information
ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；Helmholtz AI（亥姆霍兹人工智能研究所）；Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Montréal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所（MILA））；University of Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；The Institute for Data Valorization (IVADO)（数据价值化研究所（IVADO））；Canadian Institute for Advanced Research (CIFAR)（加拿大高级研究院（CIFAR））
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent. We present a handful of applications on which MINE can be used to minimize or maximize mutual information. We apply MINE to improve adversarially trained generative models. We also use MINE to implement Information Bottleneck, applying it to supervised clas…
Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing the mutual information between the representation and given information in an unsupervised fashion. We have evaluated our model on MNIST dataset and achieved 98.9 ($\pm .1$) $\%$ test accuracy while using complete unsupervised training.
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation. We derive a lower bound to the mutual information objective that can be optimized efficiently, and show that our training procedure can be interpreted as a variation of the Wake-Sleep algorithm. Specifically, InfoGAN successfully disentangles writing sty…
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation's suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and competes with fully-superv…
Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard cross-entropy loss for classification has been largely overlooked in DML. On the surface, the cross-entropy may seem unrelated and irrelevant to metric learning as it does not explicitly involve pairwise distances. However, we provide a theoretical analysis that links the cross-entropy to several well-known and recent pairwise losses. Our connections are drawn from…
Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learn…
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but do not actually answer the question. To address this problem, we propose QAInfomax as a regularizer in reading comprehension systems by maximizing mutual information among passages, a question, and its answer. QAInfomax helps regularize the model to not simply learn the superfic…
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce the loss, we extend the GNNs frameworks by exploring the aggregation and iteration scheme in the methodology of mutual information. We propose a new approach of enlarging the normal neighborhood in the aggregation of GNNs, which aims at maximizing mutual information. Based on a …
Northwestern Polytechnical University（西北工业大学）；Monash University（莫纳什大学）；University of Wollongong（伍伦贡大学）
The key towards learning informative node representations in graphs lies in how to gain contextual information from the neighbourhood. In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing. Following InfoNCE, our framework is optimized via a surrogate contrastive loss, where the positive selection underpins the quality and efficiency of representation learning. To t…
A counter-intuitive property of convolutional neural networks (CNNs) is their inherent susceptibility to adversarial examples, which severely hinders the application of CNNs in security-critical fields. Adversarial examples are similar to original examples but contain malicious perturbations. Adversarial training is a simple and effective defense method to improve the robustness of CNNs to adversarial examples. The mechanisms behind adversarial examples and adversarial training are worth exploring. Therefore, this work investigates similarities and differences between normally trained CNNs (NT…
Zhejiang University（浙江大学）；FinVolution Group（信也科技集团）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Unsupervised/self-supervised pre-training methods for graph representation learning have recently attracted increasing research interests, and they are shown to be able to generalize to various downstream applications. Yet, the adversarial robustness of such pre-trained graph learning models remains largely unexplored. More importantly, most existing defense techniques designed for end-to-end graph representation learning methods require pre-specified label definitions, and thus cannot be directly applied to the pre-training methods. In this paper, we propose an unsupervised defense technique …
We propose a novel estimator of the mutual information between two ordinal vectors $x$ and $y$. Our approach is inductive (as opposed to deductive) in that it depends on the data generating distribution solely through some nonparametric properties revealing associations in the data, and does not require having enough data to fully characterize the true joint distributions $P_{x, y}$. Specifically, our approach consists of (i) noting that $I\left(y; x\right) = I\left(u_y; u_x\right)$ where $u_y$ and $u_x$ are the copula-uniform dual representations of $y$ and $x$ (i.e. their images under the pr…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；DeepMind
This paper deals with the problem of learning a skill-conditioned policy that acts meaningfully in the absence of a reward signal. Mutual information based objectives have shown some success in learning skills that reach a diverse set of states in this setting. These objectives include a KL-divergence term, which is maximized by visiting distinct states even if those states are not far apart in the MDP. This paper presents an approach that rewards the agent for learning skills that maximize the Wasserstein distance of their state visitation from the start state of the skill. It shows that such…
In this paper, we propose a novel pooling layer for graph neural networks based on maximizing the mutual information between the pooled graph and the input graph. Since the maximum mutual information is difficult to compute, we employ the Shannon capacity of a graph as an inductive bias to our pooling method. More precisely, we show that the input graph to the pooling layer can be viewed as a representation of a noisy communication channel. For such a channel, sending the symbols belonging to an independent set of the graph yields a reliable and error-free transmission of information. We show …
University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Google Research（谷歌研究院）
Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate problems: For example, MI is notoriously hard to estimate, and using it as an objective for representation learning may lead to highly entangled representations due to its invariance under arbitrary invertible transformations. Nevertheless, these methods have been repeatedly shown to excel in practice. In this paper we argue, and provide empirical evidence, that th…
We propose a new method for learning image attention masks in a semi-supervised setting based on the Information Bottleneck principle. Provided with a set of labeled images, the mask generation model is minimizing mutual information between the input and the masked image while maximizing the mutual information between the same masked image and the image label. In contrast with other approaches, our attention model produces a Boolean rather than a continuous mask, entirely concealing the information in masked-out pixels. Using a set of synthetic datasets based on MNIST and CIFAR10 and the SVHN …
A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use datasets that are aligned, require objects to be reconstructed and suffer from deteriorated performance on downstream tasks. To solve these issues, we propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the mutual information between 3D objects and their "chunks" to improve the representations in aligned da…
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）
Feature selection is one of the most fundamental problems in machine learning. An extensive body of work on information-theoretic feature selection exists which is based on maximizing mutual information between subsets of features and class labels. Practical methods are forced to rely on approximations due to the difficulty of estimating mutual information. We demonstrate that approximations made by existing methods are based on unrealistic assumptions. We formulate a more flexible and general class of assumptions based on variational distributions and use them to tractably generate lower boun…
Zhejiang University（浙江大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Alibaba Group（阿里巴巴集团）
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within thi…
Laboratoire de Physique de l’École normale supérieure（巴黎高等师范学院物理实验室）；CNRS（法国国家科学研究中心）；PSL University（巴黎文理研究大学）；Sorbonne Université（索邦大学）；Université Paris Cité（巴黎西岱大学）；Max Planck Institute for Dynamics and Self-organization（马克斯·普朗克动力学与自组织研究所）；University of Washington（华盛顿大学）；Fred Hutchinson Cancer Research Center（弗雷德·哈钦森癌症研究中心）
Simulation-based inference enables learning the parameters of a model even when its likelihood cannot be computed in practice. One class of methods uses data simulated with different parameters to infer models of the likelihood-to-evidence ratio, or equivalently the posterior function. Here we frame the inference task as an estimation of an energy function parametrized with an artificial neural network. We present an intuitive approach where the optimal model of the likelihood-to-evidence ratio is found by maximizing the likelihood of simulated data. Within this framework, the connection betwe…
Xi’an Jiaotong University（西安交通大学）；Tsinghua University（清华大学）；Tencent AI Lab（腾讯人工智能实验室）
The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision. This paper investigates how to preserve and extract the abundant information from graph-structured data into embedding space in an unsupervised manner. To this end, we propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations. GMI generalizes the idea of conventional mutual infor…
Tsinghua University（清华大学）；University of Texas Austin（德克萨斯大学奥斯汀分校）
Feature selection is a process of choosing a subset of relevant features so that the quality of prediction models can be improved. An extensive body of work exists on information-theoretic feature selection, based on maximizing Mutual Information (MI) between subsets of features and class labels. The prior methods use a lower order approximation, by treating the joint entropy as a summation of several single variable entropies. This leads to locally optimal selections and misses multi-way feature combinations. We present a higher order MI based approximation technique called Higher Order Featu…
Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supervised formality style transfer model that utilizes a language model-based discriminator to maximize the likelihood of the output sentence being formal, which allows us to use maximization of token-level conditional probabilities for training. We further propose to maximize mutual information between source and target styles as our training objective instead of maximizing the r…
Duke University（杜克大学）；PA Consulting Group（PA咨询集团）；University College London（伦敦大学学院）
We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label (based on a Shannon entropy measure). By harnessing a recent theoretical result on the gradient of mutual information, the above optimization problem can be solved directly using gradient descent, without requiring simplification of the objective function. Theoretical analysis and empirical comparison are made between the proposed method and two closely relate…
Guangdong University of Technology（广东工业大学）；Foshan University（佛山科学技术学院）
Named entity recognition (NER) for identifying proper nouns in unstructured text is one of the most important and fundamental tasks in natural language processing. However, despite the widespread use of NER models, they still require a large-scale labeled data set, which incurs a heavy burden due to manual annotation. Domain adaptation is one of the most promising solutions to this problem, where rich labeled data from the relevant source domain are utilized to strengthen the generalizability of a model based on the target domain. However, the mainstream cross-domain NER models are still affec…
The University of British Columbia（不列颠哥伦比亚大学）；Shenzhen Polytechnic（深圳职业技术大学）
Recent advances in unsupervised domain adaptation have shown that mitigating the domain divergence by extracting the domain-invariant representation could significantly improve the generalization of a model to an unlabeled data domain. Nevertheless, the existing methods fail to effectively preserve the representation that is private to the label-missing domain, which could adversely affect the generalization. In this paper, we propose an approach to preserve such representation so that the latent distribution of the unlabeled domain could represent both the domain-invariant features and the in…
Osaka University（大阪大学）；University of Alberta（阿尔伯塔大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
Cancer subtyping is crucial for understanding the nature of tumors and providing suitable therapy. However, existing labelling methods are medically controversial, and have driven the process of subtyping away from teaching signals. Moreover, cancer genetic expression profiles are high-dimensional, scarce, and have complicated dependence, thereby posing a serious challenge to existing subtyping models for outputting sensible clustering. In this study, we propose a novel clustering method for exploiting genetic expression profiles and distinguishing subtypes in an unsupervised manner. The propo…
Beihang University（北京航空航天大学）；Macquarie University（麦考瑞大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Lehigh University（理海大学）
Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substructures' semantics, and suffering from interpretation enigmas. This paper presents a novel hierarchical subgraph-level selection and embedding based graph neural network for graph classification, namely SUGAR, to learn more discriminative subgraph representations and respond in an explanatory way. SUGAR reconstructs a sketched graph by extracting striking subgraphs as the repre…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Visa Research（Visa研究院）
We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together. Existing studies target persistent groups with substantial activity history, while ephemeral groups lack historical interactions. To overcome group interaction sparsity, we propose data-driven regularization strategies to exploit both the preference covariance amongst users who are in the same group, as well as the contextual relevance of users' individual preferences to each group. We make two contributions. First, we present a recommender architectu…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Futurewei Seattle Cloud Lab（Futurewei西雅图云实验室）
We present the Topology Transformation Equivariant Representation learning, a general paradigm of self-supervised learning for node representations of graph data to enable the wide applicability of Graph Convolutional Neural Networks (GCNNs). We formalize the proposed model from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations. We derive that maximizing such mutual information can be relaxed to minimizing the cross entropy between the applied topology transformation and its …
In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent. This set is learned by maximizing the number of different states an agent can reliably reach, as measured by the mutual information between the set of options and option termination states. To this end, we instantiate two policy gradient based algorithms, one that creates an explicit embedding space of options and one that represents options implicitly. The algorithms also provide an explicit measure of empowerment in a given state that can be used by …
Massachusetts Institute of Technology（麻省理工学院）；Santa Fe Institute（圣塔菲研究所）；Victoria University of Wellington（惠灵顿维多利亚大学）
Information bottleneck (IB) is a method for extracting information from one random variable $X$ that is relevant for predicting another random variable $Y$. To do so, IB identifies an intermediate "bottleneck" variable $T$ that has low mutual information $I(X;T)$ and high mutual information $I(Y;T)$. The "IB curve" characterizes the set of bottleneck variables that achieve maximal $I(Y;T)$ for a given $I(X;T)$, and is typically explored by maximizing the "IB Lagrangian", $I(Y;T) - βI(X;T)$. In some cases, $Y$ is a deterministic function of $X$, including many classification problems in supervi…
Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences（数学科学国家重点实验室，数学与系统科学研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；College of AI, Tsinghua University（清华大学人工智能学院）；Shanghai Qi Zhi Institute（上海启智研究院）
Xidian University（西安电子科技大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；Hong Kong Baptist University（香港浸会大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；JD Explore Academy（京东探索研究院）；The University of Sydney（悉尼大学）
Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method. Specifically, we first measure the dependence by estimating the mutual information (MI) between outputs and the natural patterns of inputs (called natural MI) and MI between outputs and the adversarial patterns of …
