Methods that align distributions by minimizing an adversarial distance between them have recently achieved impressive results. However, these approaches are difficult to optimize with gradient descent and they often do not converge well without careful hyperparameter tuning and proper initialization. We investigate whether turning the adversarial min-max problem into an optimization problem by replacing the maximization part with its dual improves the quality of the resulting alignment and explore its connections to Maximum Mean Discrepancy. Our empirical results suggest that using the dual formulation for the restricted family of linear discriminators results in a more stable convergence to a desirable solution when compared with the performance of a primal min-max GAN-like objective and an MMD objective under the same restrictions. We test our hypothesis on the problem of aligning two synthetic point clouds on a plane and on a real-image domain adaptation problem on digits. In both cases, the dual formulation yields an iterative procedure that gives more stable and monotonic improvement over time.
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UC Santa Barbara（加州大学圣巴巴拉分校）
We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matched. We propose symmetric support difference as a divergence measure to quantify the mismatch between supports. We show that select discriminators (e.g. discriminator trained for Jensen-Shannon divergence) are able to map support differences as support differences in their one-dimensional output space. Following this result, our method aligns supports by minimizing a symmetrized relaxed optimal transport cost in the …
Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are vulnerable to adversarial attacks--highlighting the vital need for defensive techniques to detect and mitigate these attacks before they occur. To combat these adversarial attacks, we developed UnMask, an adversarial detection and defense framework based on robust feature alignment. The core idea behind UnMask is to protect these models by verifying that an…
State-of-the-art deep neural networks are sensitive to small input perturbations. Since the discovery of this intriguing vulnerability, many defence methods have been proposed that attempt to improve robustness to adversarial noise. Fast and accurate attacks are required to compare various defence methods. However, evaluating adversarial robustness has proven to be extremely challenging. Existing norm minimisation adversarial attacks require thousands of iterations (e.g. Carlini & Wagner attack), are limited to the specific norms (e.g. Fast Adaptive Boundary), or produce sub-optimal results (e…
The unsupervised task of aligning two or more distributions in a shared latent space has many applications including fair representations, batch effect mitigation, and unsupervised domain adaptation. Existing flow-based approaches estimate multiple flows independently, which is equivalent to learning multiple full generative models. Other approaches require adversarial learning, which can be computationally expensive and challenging to optimize. Thus, we aim to jointly align multiple distributions while avoiding adversarial learning. Inspired by efficient alignment algorithms from optimal tran…
University of Edinburgh（爱丁堡大学）；Samsung AI Center, Cambridge（三星剑桥人工智能中心）
Stochastic Neural Networks (SNNs) that inject noise into their hidden layers have recently been shown to achieve strong robustness against adversarial attacks. However, existing SNNs are usually heuristically motivated, and often rely on adversarial training, which is computationally costly. We propose a new SNN that achieves state-of-the-art performance without relying on adversarial training, and enjoys solid theoretical justification. Specifically, while existing SNNs inject learned or hand-tuned isotropic noise, our SNN learns an anisotropic noise distribution to optimize a learning-theore…
Michigan State University（密歇根州立大学）；HRL Laboratories（HRL实验室）
Network alignment, in general, seeks to discover the hidden underlying correspondence between nodes across two (or more) networks when given their network structure. However, most existing network alignment methods have added assumptions of additional constraints to guide the alignment, such as having a set of seed node-node correspondences across the networks or the existence of side-information. Instead, we seek to develop a general network alignment algorithm that makes no additional assumptions. Recently, network embedding has proven effective in many network analysis tasks, but embeddings…
Beijing Institute of Technology（北京理工大学）；University of Technology Sydney（悉尼科技大学）
Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architecture (DANA) to obtain a domain-invariant representation for network alignment via an adversarial domain classifier. Specifically, we employ the graph convolutional networks to perform network embedding under the domain adversarial principle, given a small set of observed anchors. T…
Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Deakin University（德肯大学）；Harbin Engineering University（哈尔滨工程大学）
Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain. Existing domain adversarial learning methods are not suitable for OSDA because distribution matching with $\textit{unknown}$ classes leads to negative transfer. Previous OSDA methods have focused on matching the source and the target distribution by only utilizing $\textit{known}$ classes. However, this $\textit{known}$-only matching may fail to learn the target-$\textit{unknown}$ feature space. Therefore, we propose Unknown-Aware Domain Adversarial Learning (UA…
Nanyang Technological University（南洋理工大学）；University of California, Berkeley（加州大学伯克利分校）
Domain adaptation tackles the problem of transferring knowledge from a label-rich source domain to a label-scarce or even unlabeled target domain. Recently domain-adversarial training (DAT) has shown promising capacity to learn a domain-invariant feature space by reversing the gradient propagation of a domain classifier. However, DAT is still vulnerable in several aspects including (1) training instability due to the overwhelming discriminative ability of the domain classifier in adversarial training, (2) restrictive feature-level alignment, and (3) lack of interpretability or systematic expla…
Queensland University of Technology（昆士兰科技大学）；University of Queensland（昆士兰大学）
Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different. The task of DG is more challenging than DA as the target data is totally unseen during the training phase in DG scenarios. The current state-of-the-art employs adversarial techniques, however, these are rarely considered for the DG problem. Furthermore, these approaches do not consider correlation alignment which has been proven highly beneficial for minimizing domain discrepancy. In this paper, we propose a correlation-…
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）；HEC Montréal（蒙特利尔高等商学院）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院（CIFAR））
This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obtain in many domains. Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i.e., without or with only a few aligned triplets. We propose an unsupervised framework to align the entity and relation embddings of dif…
Existing adversarial domain adaptation methods mainly consider the marginal distribution and these methods may lead to either under transfer or negative transfer. To address this problem, we present a self-adaptive re-weighted adversarial domain adaptation approach, which tries to enhance domain alignment from the perspective of conditional distribution. In order to promote positive transfer and combat negative transfer, we reduce the weight of the adversarial loss for aligned features while increasing the adversarial force for those poorly aligned measured by the conditional entropy. Addition…
Graph alignment, also known as network alignment, is a fundamental task in social network analysis. Many recent works have relied on partially labeled cross-graph node correspondences, i.e., anchor links. However, due to the privacy and security issue, the manual labeling of anchor links for diverse scenarios may be prohibitive. Aligning two graphs without any anchor links is a crucial and challenging task. In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervi…
Bosch Center for Artificial Intelligence（博世人工智能中心）；Saarland University（萨尔大学）；Saarbrücken Graduate School of Computer Science（萨尔布吕肯计算机科学研究生院）
Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers. However, all of them focus on monolingual settings. In this paper, we explore multilingual methods for the extraction of temporal expressions from text and investigate adversarial training for aligning embedding spaces to one common space. With this, we create a single multilingual model that can also be transferred to unseen languages and set the new state of the art in those cross-lingual transfer experiments.
School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；School of Computer Science, University of Technology Sydney（悉尼科技大学计算机学院）；Raiz Invest Limited（Raiz Invest有限公司(公司)）
Most current studies on survey analysis and risk tolerance modelling lack professional knowledge and domain-specific models. Given the effectiveness of generative adversarial learning in cross-domain information, we design an Asymmetric cross-Domain Generative Adversarial Network (ADGAN) for domain scale inequality. ADGAN utilizes the information-sufficient domain to provide extra information to improve the representation learning on the information-insufficient domain via domain alignment. We provide data analysis and user model on two data sources: Consumer Consumption Information and Survey…
Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution. This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning. Most prior works use adversarial learning (i.e., min-max optimization), which can be challenging to optimize and evaluate. A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective and are limited in efficiently aligning multiple d…
We provide a novel new approach for aligning geometric models using a dual graph structure where local features are mapping probabilities. Alignment of non-rigid structures is one of the most challenging computer vision tasks due to the high number of unknowns needed to model the correspondence. We have seen a leap forward using DNN models in template alignment and functional maps, but those methods fail for inter-class alignment where nonisometric deformations exist. Here we propose to rethink this task and use unrolling concepts on a dual graph structure - one for a forward map and one for a…
University of Oxford（牛津大学）；Amazon（亚马逊）；Kings College London（伦敦国王学院）
This paper presents a novel approach to automatic fetal brain biometry motivated by needs in low- and medium- income countries. Specifically, we leverage high-end (HE) ultrasound images to build a biometry solution for low-cost (LC) point-of-care ultrasound images. We propose a novel unsupervised domain adaptation approach to train deep models to be invariant to significant image distribution shift between the image types. Our proposed method, which employs a Dual Adversarial Calibration (DAC) framework, consists of adversarial pathways which enforce model invariance to; i) adversarial perturb…
In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set, however, introduces few additional obstacles as training on private source category samples thwart relevant knowledge transfer and mislead the classification process. To mitigate these issues, we devise a mechanism for strategic selection of highly-confident target samples essential for the estimation of class-importance weights. Furthermore, we capture class-discr…
Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices corresponding to polyhedra and edges corresponding to polyhedra sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. When an image passes through a network containing ReLU nodes, the firing or non-firing at a node can be enco…
The University of Melbourne（墨尔本大学）；Deakin University（迪肯大学）
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples/attacks, raising concerns about their reliability in safety-critical applications. A number of defense methods have been proposed to train robust DNNs resistant to adversarial attacks, among which adversarial training has so far demonstrated the most promising results. However, recent studies have shown that there exists an inherent tradeoff between accuracy and robustness in adversarially-trained DNNs. In this paper, we propose a novel technique Dual Head Adversarial Training (DH-AT) to further improve the robustne…
In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-a…
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level. We tackle this problem by introducing a method based on adversarial learning which forces the label uncertainty predictions on the target domain to be indistinguishable from those on the so…
University of Rochester（罗切斯特大学）；Harvard University（哈佛大学）；HUST（华中科技大学）
Deep neural networks are widely known to be vulnerable to adversarial examples, especially showing significantly poor performance on adversarial examples generated under the white-box setting. However, most white-box attack methods rely heavily on the target model and quickly get stuck in local optima, resulting in poor adversarial transferability. The momentum-based methods and their variants are proposed to escape the local optima for better transferability. In this work, we notice that the transferability of adversarial examples generated by the iterative fast gradient sign method (I-FGSM) …
Virginia Tech（弗吉尼亚理工学院）；Georgia Institute of Technology（佐治亚理工学院）
FusionGAN is a novel genre fusion framework for music generation that integrates the strengths of generative adversarial networks and dual learning. In particular, the proposed method offers a dual learning extension that can effectively integrate the styles of the given domains. To efficiently quantify the difference among diverse domains and avoid the vanishing gradient issue, FusionGAN provides a Wasserstein based metric to approximate the distance between the target domain and the existing domains. Adopting the Wasserstein distance, a new domain is created by combining the patterns of the …
University of Bremen（不来梅大学）；University of Cambridge（剑桥大学）
Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps than their non-robust counterparts. We aim to quantify this behavior by considering the alignment between input image and saliency map. We hypothesize that as the distance to the decision boundary grows,so does the alignment. This connection is strictly true in the case of linear models. We confirm these theoretical findings with experiments based on models trained with a local Lipschitz regularization and identify w…
Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition
School of Biological Science and Medical Engineering, Hunan University of Technology（湖南工业大学生物科学与医学工程学院）；School of Biomedical Engineering, Health Science Center, Shenzhen University（深圳大学医学部生物医学工程学院）；Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging（广东省生物医学测量与超声成像重点实验室）；Shenzhen Pengrui Brain Science Technology（深圳鹏瑞脑科学技术有限公司）
RWTH Aachen University（亚琛工业大学）；University Hospital Düsseldorf（杜塞尔多夫大学医院）；University Hospital Aachen（亚琛大学医院）；ARISTRA GmbH（ARISTRA有限公司）；The Institute for Experimental Molecular Imaging, RWTH Aachen University（亚琛工业大学实验分子影像研究所）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）；Comprehensive Diagnostic Center Aachen (CDCA), University Hospital RWTH Aachen（亚琛工业大学医院综合诊断中心）
Unmasking the decision-making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, we demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard counterparts. We let six experienced radiologists rate the interpretability of saliency maps in datasets of X-rays, computed tomography, and magnetic resonance imaging scans. Significant improvements were found for our adversarial models, which could be further improved by the application of dual batch norm…
Adversarial Preference Learning for Robust LLM Alignment
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Northeastern University（东北大学）；University of Science and Technology of China（中国科学技术大学）；MemTensor (Shanghai) Technology Co., Ltd（MemTensor（上海）技术有限公司）；University of Auckland（奥克兰大学）；China Telecom Corporation Limited Beijing Research Institute（中国电信股份有限公司北京研究院）
