April 3, 2020

3312 words 16 mins read

Paper Group AWR 46

RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies. Explainable outlier detection through decision tree conditioning. Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates. Text classification with word embedding regularization and soft similarity measure. Planning and E …

RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies


Title	RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies
Authors	Zhe Li, Chunhua Sun, Chunli Liu, Xiayu Chen, Meng Wang, Yezheng Liu
Abstract	Outlier detection is an important task in data mining and many technologies have been explored in various applications. However, due to the default assumption that outliers are non-concentrated, unsupervised outlier detection may not correctly detect group anomalies with higher density levels. As for the supervised outlier detection, although high detection rates and optimal parameters can usually be achieved, obtaining sufficient and correct labels is a time-consuming task. To address these issues, we focus on semi-supervised outlier detection with few identified anomalies, in the hope of using limited labels to achieve high detection accuracy. First, we propose a novel detection model Dual-GAN, which can directly utilize the potential information in identified anomalies to detect discrete outliers and partially identified group anomalies simultaneously. And then, considering the instances with similar output values may not all be similar in a complex data structure, we replace the two MO-GAN components in Dual-GAN with the combination of RCC and M-GAN (RCC-Dual-GAN). In addition, to deal with the evaluation of Nash equilibrium and the selection of optimal model, two evaluation indicators are created and introduced into the two models to make the detection process more intelligent. Extensive experiments on both benchmark datasets and two practical tasks demonstrate that our proposed approaches (i.e., Dual-GAN and RCC-Dual-GAN) can significantly improve the accuracy of outlier detection even with only a few identified anomalies. Moreover, compared with the two MO-GAN components in Dual-GAN, the network structure combining RCC and M-GAN has greater stability in various situations.
Tasks	Outlier Detection
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03609v1
PDF	https://arxiv.org/pdf/2003.03609v1.pdf
PWC	https://paperswithcode.com/paper/rcc-dual-gan-an-efficient-approach-for
Repo	https://github.com/leibinghe/RCC-Dual-GAN
Framework	tf

Explainable outlier detection through decision tree conditioning


Title	Explainable outlier detection through decision tree conditioning
Authors	David Cortes
Abstract	This work describes an outlier detection procedure (named “OutlierTree”) loosely based on the GritBot software developed by RuleQuest research, which works by evaluating and following supervised decision tree splits on variables, in whose branches 1-d confidence intervals are constructed for the target variable and potential outliers flagged according to these confidence intervals. Under this logic, it’s possible to produce human-readable explanations for why a given value of a variable in an observation can be considered as outlier, by considering the decision tree branch conditions along with general distribution statistics among the non-outlier observations that fell into the same branch, which can then be contrasted against the value which lies outside the CI. The supervised splits help to ensure that the generated conditions are not spurious, but rather related to the target variable and having logical breakpoints.
Tasks	Outlier Detection
Published	2020-01-02
URL	https://arxiv.org/abs/2001.00636v1
PDF	https://arxiv.org/pdf/2001.00636v1.pdf
PWC	https://paperswithcode.com/paper/explainable-outlier-detection-through
Repo	https://github.com/david-cortes/outliertree
Framework	none

Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates


Title	Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates
Authors	Amin Ghiasi, Ali Shafahi, Tom Goldstein
Abstract	To deflect adversarial attacks, a range of “certified” classifiers have been proposed. In addition to labeling an image, certified classifiers produce (when possible) a certificate guaranteeing that the input image is not an $\ell_p$-bounded adversarial example. We present a new attack that exploits not only the labelling function of a classifier, but also the certificate generator. The proposed method applies large perturbations that place images far from a class boundary while maintaining the imperceptibility property of adversarial examples. The proposed “Shadow Attack” causes certifiably robust networks to mislabel an image and simultaneously produce a “spoofed” certificate of robustness.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.08937v1
PDF	https://arxiv.org/pdf/2003.08937v1.pdf
PWC	https://paperswithcode.com/paper/breaking-certified-defenses-semantic-1
Repo	https://github.com/AminJun/BreakingCertifiableDefenses
Framework	pytorch

Text classification with word embedding regularization and soft similarity measure


Title	Text classification with word embedding regularization and soft similarity measure
Authors	Vít Novotný, Eniafe Festus Ayetiran, Michal Štefánik, Petr Sojka
Abstract	Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures extracted from word embeddings, such as the soft cosine measure (SCM) and the Word Mover’s Distance (WMD), were reported to achieve state-of-the-art performance on semantic text similarity and text classification. Despite the strong performance of the WMD on text classification and semantic text similarity, its super-cubic average time complexity is impractical. The SCM has quadratic worst-case time complexity, but its performance on text classification has never been compared with the WMD. Recently, two word embedding regularization techniques were shown to reduce storage and memory costs, and to improve training speed, document processing speed, and task performance on word analogy, word similarity, and semantic text similarity. However, the effect of these techniques on text classification has not yet been studied. In our work, we investigate the individual and joint effect of the two word embedding regularization techniques on the document processing speed and the task performance of the SCM and the WMD on text classification. For evaluation, we use the $k$NN classifier and six standard datasets: BBCSPORT, TWITTER, OHSUMED, REUTERS-21578, AMAZON, and 20NEWS. We show 39% average $k$NN test error reduction with regularized word embeddings compared to non-regularized word embeddings. We describe a practical procedure for deriving such regularized embeddings through Cholesky factorization. We also show that the SCM with regularized word embeddings significantly outperforms the WMD on text classification and is over 10,000 times faster.
Tasks	Text Classification, Word Embeddings
Published	2020-03-10
URL	https://arxiv.org/abs/2003.05019v1
PDF	https://arxiv.org/pdf/2003.05019v1.pdf
PWC	https://paperswithcode.com/paper/text-classification-with-word-embedding
Repo	https://github.com/MIR-MU/regularized-embeddings
Framework	none

Planning and Execution using Inaccurate Models with Provable Guarantees


Title	Planning and Execution using Inaccurate Models with Provable Guarantees
Authors	Anirudh Vemula, Yash Oza, J. Andrew Bagnell, Maxim Likhachev
Abstract	Models used in modern planning problems to simulate outcomes of real world action executions are becoming increasingly complex, ranging from simulators that do physics-based reasoning to precomputed analytical motion primitives. However, robots operating in the real world often face situations not modeled by these models before execution. This imperfect modeling can lead to highly suboptimal or even incomplete behavior during execution. In this paper, we propose an approach for interleaving planning and execution that adapts online using real world execution and accounts for any discrepancies in dynamics during planning, without requiring updates to the dynamics of the model. This is achieved by biasing the planner away from transitions whose dynamics are discovered to be inaccurately modeled, thereby leading to robot behavior that tries to complete the task despite having an inaccurate model. We provide provable guarantees on the completeness and efficiency of the proposed planning and execution framework under specific assumptions on the model, for both small and large state spaces. Our approach is shown to be efficient empirically in simulated robotic tasks including 4D planar pushing, and in real robotic experiments using PR2 involving a 3D pick-and-place task where the mass of the object is incorrectly modeled, and a 7D arm planning task where one of the joints is not operational leading to discrepancy in dynamics. Video can be found at https://youtu.be/eQmAeWIhjO8
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04394v3
PDF	https://arxiv.org/pdf/2003.04394v3.pdf
PWC	https://paperswithcode.com/paper/planning-and-execution-using-inaccurate
Repo	https://github.com/vvanirudh/CMAX
Framework	none

ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning


Title	ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
Authors	Weihao Yu, Zihang Jiang, Yanfei Dong, Jiashi Feng
Abstract	Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more comprehensive reasoning of text. In this paper, we introduce a new Reading Comprehension dataset requiring logical reasoning (ReClor) extracted from standardized graduate admission examinations. As earlier studies suggest, human-annotated datasets usually contain biases, which are often exploited by models to achieve high accuracy without truly understanding the text. In order to comprehensively evaluate the logical reasoning ability of models on ReClor, we propose to identify biased data points and separate them into EASY set while the rest as HARD set. Empirical results show that state-of-the-art models have an outstanding ability to capture biases contained in the dataset with high accuracy on EASY set. However, they struggle on HARD set with poor performance near that of random guess, indicating more research is needed to essentially enhance the logical reasoning ability of current models.
Tasks	Reading Comprehension
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04326v1
PDF	https://arxiv.org/pdf/2002.04326v1.pdf
PWC	https://paperswithcode.com/paper/reclor-a-reading-comprehension-dataset-1
Repo	https://github.com/yuweihao/reclor
Framework	pytorch

Disease State Prediction From Single-Cell Data Using Graph Attention Networks


Title	Disease State Prediction From Single-Cell Data Using Graph Attention Networks
Authors	Neal G. Ravindra, Arijit Sehanobish, Jenna L. Pappalardo, David A. Hafler, David van Dijk
Abstract	Single-cell RNA sequencing (scRNA-seq) has revolutionized biological discovery, providing an unbiased picture of cellular heterogeneity in tissues. While scRNA-seq has been used extensively to provide insight into both healthy systems and diseases, it has not been used for disease prediction or diagnostics. Graph Attention Networks (GAT) have proven to be versatile for a wide range of tasks by learning from both original features and graph structures. Here we present a graph attention model for predicting disease state from single-cell data on a large dataset of Multiple Sclerosis (MS) patients. MS is a disease of the central nervous system that can be difficult to diagnose. We train our model on single-cell data obtained from blood and cerebrospinal fluid (CSF) for a cohort of seven MS patients and six healthy adults (HA), resulting in 66,667 individual cells. We achieve 92 % accuracy in predicting MS, outperforming other state-of-the-art methods such as a graph convolutional network and a random forest classifier. Further, we use the learned graph attention model to get insight into the features (cell types and genes) that are important for this prediction. The graph attention model also allow us to infer a new feature space for the cells that emphasizes the differences between the two conditions. Finally we use the attention weights to learn a new low-dimensional embedding that can be visualized. To the best of our knowledge, this is the first effort to use graph attention, and deep learning in general, to predict disease state from single-cell data. We envision applying this method to single-cell data for other diseases.
Tasks	Disease Prediction
Published	2020-02-14
URL	https://arxiv.org/abs/2002.07128v2
PDF	https://arxiv.org/pdf/2002.07128v2.pdf
PWC	https://paperswithcode.com/paper/disease-state-prediction-from-single-cell
Repo	https://github.com/vandijklab/scGAT
Framework	none

Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning


Title	Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
Authors	Rui Zhao, Volker Tresp, Wei Xu
Abstract	In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized efficiently. Lastly, we evaluate the developed framework in different robotic manipulation and navigation tasks and demonstrate the efficacy of our approach. A video showing experimental results is available at \url{https://youtu.be/CT4CKMWBYz0}.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01963v1
PDF	https://arxiv.org/pdf/2002.01963v1.pdf
PWC	https://paperswithcode.com/paper/mutual-information-based-state-control-for
Repo	https://github.com/ruizhaogit/misc
Framework	tf

Optimal binning: mathematical programming formulation


Title	Optimal binning: mathematical programming formulation
Authors	Guillermo Navas-Palencia
Abstract	The optimal binning is the optimal discretization of a variable into bins given a discrete or continuous numeric target. We present a rigorous and extensible mathematical programming formulation to solving the optimal binning problem for a binary, continuous and multi-class target type, incorporating constraints not previously addressed. For all three target types, we introduce a convex mixed-integer programming formulation. Several algorithmic enhancements such as automatic determination of the most suitable monotonic trend via a Machine-Learning-based classifier and implementation aspects are thoughtfully discussed. The new mathematical programming formulations are carefully implemented in the open-source python library OptBinning.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08025v1
PDF	https://arxiv.org/pdf/2001.08025v1.pdf
PWC	https://paperswithcode.com/paper/optimal-binning-mathematical-programming
Repo	https://github.com/guillermo-navas-palencia/optbinning
Framework	none

Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem


Title	Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem
Authors	Johannes Hofmanninger, Florian Prayer, Jeanny Pan, Sebastian Rohrich, Helmut Prosch, Georg Langs
Abstract	Automated segmentation of anatomical structures is a crucial step in many medical image analysis tasks. For lung segmentation, a variety of approaches exist, involving sophisticated pipelines trained and validated on a range of different data sets. However, during translation to clinical routine the applicability of these approaches across diseases remains limited. Here, we show that the accuracy and reliability of lung segmentation algorithms on demanding cases primarily does not depend on methodology, but on the diversity of training data. We compare 4 generic deep learning approaches and 2 published lung segmentation algorithms on routine imaging data with more than 6 different disease patterns and 3 published data sets. We show that a basic approach - U-net - performs either better, or competitively with other approaches on both routine data and published data sets, and outperforms published approaches once trained on a diverse data set covering multiple diseases. Training data composition consistently has a bigger impact than algorithm choice on accuracy across test data sets. We carefully analyse the impact of data diversity, and the specifications of annotations on both training and validation sets to provide a reference for algorithms, training data, and annotation. Results on a seemingly well understood task of lung segmentation suggest the critical importance of training data diversity compared to model choice.
Tasks
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11767v1
PDF	https://arxiv.org/pdf/2001.11767v1.pdf
PWC	https://paperswithcode.com/paper/automatic-lung-segmentation-in-routine
Repo	https://github.com/JoHof/lungmask
Framework	pytorch

ManyModalQA: Modality Disambiguation and QA over Diverse Inputs


Title	ManyModalQA: Modality Disambiguation and QA over Diverse Inputs
Authors	Darryl Hannan, Akshay Jain, Mohit Bansal
Abstract	We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs. Our questions are ambiguous, in that the modality that contains the answer is not easily determined based solely upon the question. To demonstrate this ambiguity, we construct a modality selector (or disambiguator) network, and this model gets substantially lower accuracy on our challenge set, compared to existing datasets, indicating that our questions are more ambiguous. By analyzing this model, we investigate which words in the question are indicative of the modality. Next, we construct a simple baseline ManyModalQA model, which, based on the prediction from the modality selector, fires a corresponding pre-trained state-of-the-art unimodal QA model. We focus on providing the community with a new manymodal evaluation set and only provide a fine-tuning set, with the expectation that existing datasets and approaches will be transferred for most of the training, to encourage low-resource generalization without large, monolithic training sets for each new task. There is a significant gap between our baseline models and human performance; therefore, we hope that this challenge encourages research in end-to-end modality disambiguation and multimodal QA models, as well as transfer learning. Code and data available at: https://github.com/hannandarryl/ManyModalQA
Tasks	Question Answering, Transfer Learning
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08034v1
PDF	https://arxiv.org/pdf/2001.08034v1.pdf
PWC	https://paperswithcode.com/paper/manymodalqa-modality-disambiguation-and-qa
Repo	https://github.com/hannandarryl/ManyModalQA
Framework	none

AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning


Title	AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
Authors	Jianhong Zhang, Manli Zhang, Zhiwu Lu, Tao Xiang, Jirong Wen
Abstract	Existing few-shot learning (FSL) methods assume that there exist sufficient training samples from source classes for knowledge transfer to target classes with few training samples. However, this assumption is often invalid, especially when it comes to fine-grained recognition. In this work, we define a new FSL setting termed few-shot fewshot learning (FSFSL), under which both the source and target classes have limited training samples. To overcome the source class data scarcity problem, a natural option is to crawl images from the web with class names as search keywords. However, the crawled images are inevitably corrupted by large amount of noise (irrelevant images) and thus may harm the performance. To address this problem, we propose a graph convolutional network (GCN)-based label denoising (LDN) method to remove the irrelevant images. Further, with the cleaned web images as well as the original clean training images, we propose a GCN-based FSL method. For both the LDN and FSL tasks, a novel adaptive aggregation GCN (AdarGCN) model is proposed, which differs from existing GCN models in that adaptive aggregation is performed based on a multi-head multi-level aggregation module. With AdarGCN, how much and how far information carried by each graph node is propagated in the graph structure can be determined automatically, therefore alleviating the effects of both noisy and outlying training samples. Extensive experiments show the superior performance of our AdarGCN under both the new FSFSL and the conventional FSL settings.
Tasks	Denoising, Few-Shot Learning, Transfer Learning
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12641v2
PDF	https://arxiv.org/pdf/2002.12641v2.pdf
PWC	https://paperswithcode.com/paper/adargcn-adaptive-aggregation-gcn-for-few-shot
Repo	https://github.com/RiceZJH/AdarGCN
Framework	pytorch

A Little Fog for a Large Turn


Title	A Little Fog for a Large Turn
Authors	Harshitha Machiraju, Vineeth N Balasubramanian
Abstract	Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the predictions of these systems. These weather conditions are capable of acting like natural adversaries that can help in testing models. To this end, we introduce a general notion of adversarial perturbations, which can be created using generative models and provide a methodology inspired by Cycle-Consistent Generative Adversarial Networks to generate adversarial weather conditions for a given image. Our formulation and results show that these images provide a suitable testbed for steering models used in Autonomous navigation models. Our work also presents a more natural and general definition of Adversarial perturbations based on Perceptual Similarity.
Tasks	Adversarial Attack, Autonomous Navigation, Safety Perception Recognition
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05873v1
PDF	https://arxiv.org/pdf/2001.05873v1.pdf
PWC	https://paperswithcode.com/paper/a-little-fog-for-a-large-turn
Repo	https://github.com/code-Assasin/A_Little_fog_for_a_Large_Turn
Framework	pytorch

A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation


Title	A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation
Authors	Sizhang Dai, Weibing Huang
Abstract	We propose a learning-based network for depth map estimation from multi-view stereo (MVS) images. Our proposed network consists of three sub-networks: 1) a base network for initial depth map estimation from an unstructured stereo image pair, 2) a novel refinement network that leverages both photometric and geometric information, and 3) an attentional multi-view aggregation framework that enables efficient information exchange and integration among different stereo image pairs. The proposed network, called A-TVSNet, is evaluated on various MVS datasets and shows the ability to produce high quality depth map that outperforms competing approaches. Our code is available at https://github.com/daiszh/A-TVSNet.
Tasks	Depth Estimation, Stereo Depth Estimation
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00711v1
PDF	https://arxiv.org/pdf/2003.00711v1.pdf
PWC	https://paperswithcode.com/paper/a-tvsnet-aggregated-two-view-stereo-network
Repo	https://github.com/daiszh/A-TVSNet
Framework	tf

Hypercomplex-Valued Recurrent Correlation Neural Networks


Title	Hypercomplex-Valued Recurrent Correlation Neural Networks
Authors	Marcos Eduardo Valle, Rodolfo Anibal Lobo
Abstract	Recurrent correlation neural networks (RCNNs), introduced by Chiueh and Goodman as an improved version of the bipolar correlation-based Hopfield neural network, can be used to implement high-capacity associative memories. In this paper, we extend the bipolar RCNNs for processing hypercomplex-valued data. Precisely, we present the mathematical background for a broad class of hypercomplex-valued RCNNs. Then, we provide the necessary conditions which ensure that a hypercomplex-valued RCNN always settles at an equilibrium using either synchronous or asynchronous update modes. Examples with bipolar, complex, hyperbolic, quaternion, and octonion-valued RCNNs are given to illustrate the theoretical results. Finally, computational experiments confirm the potential application of hypercomplex-valued RCNNs as associative memories designed for the storage and recall of gray-scale images.
Tasks
Published	2020-01-31
URL	https://arxiv.org/abs/2002.00027v1
PDF	https://arxiv.org/pdf/2002.00027v1.pdf
PWC	https://paperswithcode.com/paper/hypercomplex-valued-recurrent-correlation
Repo	https://github.com/mevalle/Hypercomplex-Valued-Recurrent-Correlation-Neural-Networks
Framework	none