January 30, 2020

3238 words 16 mins read

Paper Group ANR 391

UVA: A Universal Variational Framework for Continuous Age Analysis. Real-Time Adversarial Attacks. Automatic Online Quality Control of Synthetic CTs. Early Discovery of Emerging Entities in Microblogs. Optimal Decision Making Under Strategic Behavior. Hierarchical Contextualized Representation for Named Entity Recognition. Scalable Fine-grained Gen …

UVA: A Universal Variational Framework for Continuous Age Analysis


Title	UVA: A Universal Variational Framework for Continuous Age Analysis
Authors	Peipei Li, Huaibo Huang, Yibo Hu, Xiang Wu, Ran He, Zhenan Sun
Abstract	Conventional methods for facial age analysis tend to utilize accurate age labels in a supervised way. However, existing age datasets lies in a limited range of ages, leading to a long-tailed distribution. To alleviate the problem, this paper proposes a Universal Variational Aging (UVA) framework to formulate facial age priors in a disentangling manner. Benefiting from the variational evidence lower bound, the facial images are encoded and disentangled into an age-irrelevant distribution and an age-related distribution in the latent space. A conditional introspective adversarial learning mechanism is introduced to boost the image quality. In this way, when manipulating the age-related distribution, UVA can achieve age translation with arbitrary ages. Further, by sampling noise from the age-irrelevant distribution, we can generate photorealistic facial images with a specific age. Moreover, given an input face image, the mean value of age-related distribution can be treated as an age estimator. These indicate that UVA can efficiently and accurately estimate the age-related distribution by a disentangling manner, even if the training dataset performs a long-tailed age distribution. UVA is the first attempt to achieve facial age analysis tasks, including age translation, age generation and age estimation, in a universal framework. The qualitative and quantitative experiments demonstrate the superiority of UVA on five popular datasets, including CACD2000, Morph, UTKFace, MegaAge-Asian and FG-NET.
Tasks	Age Estimation
Published	2019-03-30
URL	http://arxiv.org/abs/1904.00158v1
PDF	http://arxiv.org/pdf/1904.00158v1.pdf
PWC	https://paperswithcode.com/paper/uva-a-universal-variational-framework-for
Repo
Framework

Real-Time Adversarial Attacks


Title	Real-Time Adversarial Attacks
Authors	Yuan Gong, Boyang Li, Christian Poellabauer, Yiyu Shi
Abstract	In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are very effective, they only focus on scenarios where the target model takes static input, i.e., an attacker can observe the entire original sample and then add a perturbation at any point of the sample. These attack approaches are not applicable to situations where the target model takes streaming input, i.e., an attacker is only able to observe past data points and add perturbations to the remaining (unobserved) data points of the input. In this paper, we propose a real-time adversarial attack scheme for machine learning models with streaming inputs.
Tasks	Adversarial Attack
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13399v2
PDF	https://arxiv.org/pdf/1905.13399v2.pdf
PWC	https://paperswithcode.com/paper/real-time-adversarial-attacks
Repo
Framework

Automatic Online Quality Control of Synthetic CTs


Title	Automatic Online Quality Control of Synthetic CTs
Authors	Louis D. van Harten, Jelmer M. Wolterink, Joost J. C. Verhoeff, Ivana Išgum
Abstract	Accurate MR-to-CT synthesis is a requirement for MR-only workflows in radiotherapy (RT) treatment planning. In recent years, deep learning-based approaches have shown impressive results in this field. However, to prevent downstream errors in RT treatment planning, it is important that deep learning models are only applied to data for which they are trained and that generated synthetic CT (sCT) images do not contain severe errors. For this, a mechanism for online quality control should be in place. In this work, we use an ensemble of sCT generators and assess their disagreement as a measure of uncertainty of the results. We show that this uncertainty measure can be used for two kinds of online quality control. First, to detect input images that are outside the expected distribution of MR images. Second, to identify sCT images that were generated from suitable MR images but potentially contain errors. Such automatic online quality control for sCT generation is likely to become an integral part of MR-only RT workflows.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04986v1
PDF	https://arxiv.org/pdf/1911.04986v1.pdf
PWC	https://paperswithcode.com/paper/automatic-online-quality-control-of-synthetic
Repo
Framework

Early Discovery of Emerging Entities in Microblogs


Title	Early Discovery of Emerging Entities in Microblogs
Authors	Satoshi Akasaki, Naoki Yoshinaga, Masashi Toyoda
Abstract	Keeping up to date on emerging entities that appear every day is indispensable for various applications, such as social-trend analysis and marketing research. Previous studies have attempted to detect unseen entities that are not registered in a particular knowledge base as emerging entities and consequently find non-emerging entities since the absence of entities in knowledge bases does not guarantee their emergence. We therefore introduce a novel task of discovering truly emerging entities when they have just been introduced to the public through microblogs and propose an effective method based on time-sensitive distant supervision, which exploits distinctive early-stage contexts of emerging entities. Experimental results with a large-scale Twitter archive show that the proposed method achieves 83.2% precision of the top 500 discovered emerging entities, which outperforms baselines based on unseen entity recognition with burst detection. Besides notable emerging entities, our method can discover massive long-tail and homographic emerging entities. An evaluation of relative recall shows that the method detects 80.4% emerging entities newly registered in Wikipedia; 92.4% of them are discovered earlier than their registration in Wikipedia, and the average lead-time is more than one year (571 days).
Tasks
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03513v1
PDF	https://arxiv.org/pdf/1907.03513v1.pdf
PWC	https://paperswithcode.com/paper/early-discovery-of-emerging-entities-in
Repo
Framework

Optimal Decision Making Under Strategic Behavior


Title	Optimal Decision Making Under Strategic Behavior
Authors	Behzad Tabibian, Stratis Tsirtsis, Moein Khajehnejad, Adish Singla, Bernhard Schölkopf, Manuel Gomez-Rodriguez
Abstract	We are witnessing an increasing use of data-driven predictive models to inform decisions. As decisions have implications for individuals and society, there is increasing pressure on decision makers to be transparent about their decision policies. At the same time, individuals may use knowledge, gained by transparency, to invest effort strategically in order to maximize their chances of receiving a beneficial decision. Our goal is to find decision policies that are optimal in terms of utility in such a strategic setting. To this end, we first characterize how strategic investment of effort by individuals leads to a change in the feature distribution. Using this characterization, we first show that, in general, we cannot expect to find optimal decision policies in polynomial time and there are cases in which deterministic policies are suboptimal. Then, we demonstrate that, if the cost individuals pay to change their features satisfies a natural monotonicity assumption, we can narrow down the search for the optimal policy to a particular family of decision policies with a set of desirable properties, which allow for a highly effective polynomial time heuristic search algorithm using dynamic programming. Finally, under no assumptions on the cost individuals pay to change their features, we develop an iterative search algorithm that is guaranteed to find locally optimal decision policies also in polynomial time. Experiments on synthetic and real lending data illustrate our theoretical findings and show that the decision policies found by our algorithms achieve higher utility than several competitive baselines.
Tasks	Decision Making
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09239v4
PDF	https://arxiv.org/pdf/1905.09239v4.pdf
PWC	https://paperswithcode.com/paper/optimal-decision-making-under-strategic
Repo
Framework

Hierarchical Contextualized Representation for Named Entity Recognition


Title	Hierarchical Contextualized Representation for Named Entity Recognition
Authors	Ying Luo, Fengshun Xiao, Hai Zhao
Abstract	Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from larger scope, not only in the entire sentence, but also in the entire document (dataset). In this paper, we address these two deficiencies and propose a model augmented with hierarchical contextualized representation: sentence-level representation and document-level representation. In sentence-level, we take different contributions of words in a single sentence into consideration to enhance the sentence representation learned from an independent BiLSTM via label embedding attention mechanism. In document-level, the key-value memory network is adopted to record the document-aware information for each unique word which is sensitive to similarity of context information. Our two-level hierarchical contextualized representations are fused with each input token embedding and corresponding hidden state of BiLSTM, respectively. The experimental results on three benchmark NER datasets (CoNLL-2003 and Ontonotes 5.0 English datasets, CoNLL-2002 Spanish dataset) show that we establish new state-of-the-art results.
Tasks	Named Entity Recognition
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02257v2
PDF	https://arxiv.org/pdf/1911.02257v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-contextualized-representation
Repo
Framework

Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning


Title	Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
Authors	Xinsheng Xuan, Bo Peng, Wei Wang, Jing Dong
Abstract	Recently, generated images could reach very high quality, even human eyes could not tell them apart from real images. Although there are already some methods for detecting generated images in current forensic community, most of these methods are used to detect a single type of generated images. The new types of generated images are emerging one after another, and the existing detection methods cannot cope well. These problems prompted us to propose a scalable framework for multi-class classification based on deep metric learning, which aims to classify the generated images finer. In addition, we have increased the scalability of our framework to cope with the constant emergence of new types of generated images, and through fine-tuning to make the model obtain better detection performance on the new type of generated data.
Tasks	Image Classification, Metric Learning
Published	2019-12-10
URL	https://arxiv.org/abs/1912.11082v1
PDF	https://arxiv.org/pdf/1912.11082v1.pdf
PWC	https://paperswithcode.com/paper/scalable-fine-grained-generated-image
Repo
Framework

Mining Temporal Evolution of Knowledge Graph and Genealogical Features for Literature-based Discovery Prediction


Title	Mining Temporal Evolution of Knowledge Graph and Genealogical Features for Literature-based Discovery Prediction
Authors	Nazim Choudhury, Fahim Faisal, Matloob Khushi
Abstract	Literature-based knowledge discovery process identifies the important but implicit relations among information embedded in published literature. Existing techniques from Information Retrieval and Natural Language Processing attempt to identify the hidden or unpublished connections between information concepts within published literature, however, these techniques undermine the concept of predicting the future and emerging relations among scientific knowledge components encapsulated within the literature. Keyword Co-occurrence Network (KCN), built upon author selected keywords (i.e., knowledge entities), is considered as a knowledge graph that focuses both on these knowledge components and knowledge structure of a scientific domain by examining the relationships between knowledge entities. Using data from two multidisciplinary research domains other than the medical domain, capitalizing on bibliometrics, the dynamicity of temporal KCNs, and a Long Short Term Memory recurrent neural network, this study proposed a framework to successfully predict the future literature-based discoveries - the emerging connections among knowledge units. Framing the problem as a dynamic supervised link prediction task, the proposed framework integrates some novel node and edge-level features. Temporal importance of keywords computed from both bipartite and unipartite networks, communities of keywords, built upon genealogical relations, and relative importance of temporal citation counts used in the feature construction process. Both node and edge-level features were input into an LSTM network to forecast the feature values for positive and negatively labeled non-connected keyword pairs and classify them accurately. High classification performance rates suggest that these features are supportive both in predicting the emerging connections between scientific knowledge units and emerging trend analysis.
Tasks	Information Retrieval, Link Prediction
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09395v2
PDF	https://arxiv.org/pdf/1907.09395v2.pdf
PWC	https://paperswithcode.com/paper/towards-an-lstm-based-predictive-framework
Repo
Framework

Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization


Title	Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization
Authors	Yuqi Cui, Jian Huang, Dongrui Wu
Abstract	Takagi-Sugeno-Kang (TSK) fuzzy systems are flexible and interpretable machine learning models; however, they may not be easily optimized when the data size is large, and/or the data dimensionality is high. This paper proposes a mini-batch gradient descent (MBGD) based algorithm to efficiently and effectively train TSK fuzzy classifiers. It integrates two novel techniques: 1) uniform regularization (UR), which forces the rules to have similar average contributions to the output, and hence to increase the generalization performance of the TSK classifier; and, 2) batch normalization (BN), which extends BN from deep neural networks to TSK fuzzy classifiers to expedite the convergence and improve the generalization performance. Experiments on 12 UCI datasets from various application domains, with varying size and dimensionality, demonstrated that UR and BN are effective individually, and integrating them can further improve the classification performance.
Tasks	Interpretable Machine Learning
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00636v3
PDF	https://arxiv.org/pdf/1908.00636v3.pdf
PWC	https://paperswithcode.com/paper/optimize-tsk-fuzzy-systems-for-big-data-1
Repo
Framework

Towards Probabilistic Generative Models Harnessing Graph Neural Networks for Disease-Gene Prediction


Title	Towards Probabilistic Generative Models Harnessing Graph Neural Networks for Disease-Gene Prediction
Authors	Vikash Singh, Pietro Lio’
Abstract	Disease-gene prediction (DGP) refers to the computational challenge of predicting associations between genes and diseases. Effective solutions to the DGP problem have the potential to accelerate the therapeutic development pipeline at early stages via efficient prioritization of candidate genes for various diseases. In this work, we introduce the variational graph auto-encoder (VGAE) as a promising unsupervised approach for learning powerful latent embeddings in disease-gene networks that can be used for the DGP problem, the first approach using a generative model involving graph neural networks (GNNs). In addition to introducing the VGAE as a promising approach to the DGP problem, we further propose an extension (constrained-VGAE or C-VGAE) which adapts the learning algorithm for link prediction between two distinct node types in heterogeneous graphs. We evaluate and demonstrate the effectiveness of the VGAE on general link prediction in a disease-gene association network and the C-VGAE on disease-gene prediction in the same network, using popular random walk driven methods as baselines. While the methodology presented demonstrates potential solely based on utilizing the topology of a disease-gene association network, it can be further enhanced and explored through the integration of additional biological networks such as gene/protein interaction networks and additional biological features pertaining to the diseases and genes represented in the disease-gene association network.
Tasks	Link Prediction
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05628v1
PDF	https://arxiv.org/pdf/1907.05628v1.pdf
PWC	https://paperswithcode.com/paper/towards-probabilistic-generative-models
Repo
Framework

An Introduction to Deep Morphological Networks


Title	An Introduction to Deep Morphological Networks
Authors	Keiller Nogueira, Jocelyn Chanussot, Mauro Dalla Mura, William Robson Schwartz, Jefersson A. dos Santos
Abstract	The recent impressive results of deep learning-based methods on computer vision applications brought fresh air to the research and industrial community. This success is mainly due to the process that allows those methods to learn data-driven features, generally based upon linear operations. However, in some scenarios, such operations do not have a good performance because of their inherited process that blurs edges, losing notions of corners, borders, and geometry of objects. Overcoming this, non-linear operations, such as morphological ones, may preserve such properties of the objects, being preferable and even state-of-the-art in some applications. Encouraged by this, in this work, we propose a novel network, called Deep Morphological Network (DeepMorphNet), capable of doing non-linear morphological operations while performing the feature learning process by optimizing the structuring elements. The DeepMorphNets can be trained and optimized end-to-end using traditional existing techniques commonly employed in the training of deep learning approaches. A systematic evaluation of the proposed algorithm is conducted using two synthetic and two traditional image classification datasets. Results show that the proposed DeepMorphNets is a promising technique that can learn distinct features when compared to the ones learned by current deep learning methods.
Tasks	Image Classification
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01751v1
PDF	https://arxiv.org/pdf/1906.01751v1.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-deep-morphological
Repo
Framework

Differential Privacy Has Disparate Impact on Model Accuracy


Title	Differential Privacy Has Disparate Impact on Model Accuracy
Authors	Eugene Bagdasaryan, Vitaly Shmatikov
Abstract	Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model’s accuracy. We demonstrate that in the neural networks trained using differentially private stochastic gradient descent (DP-SGD), this cost is not borne equally: accuracy of DP models drops much more for the underrepresented classes and subgroups. For example, a gender classification model trained using DP-SGD exhibits much lower accuracy for black faces than for white faces. Critically, this gap is bigger in the DP model than in the non-DP model, i.e., if the original model is unfair, the unfairness becomes worse once DP is applied. We demonstrate this effect for a variety of tasks and models, including sentiment analysis of text and image classification. We then explain why DP training mechanisms such as gradient clipping and noise addition have disproportionate effect on the underrepresented and more complex subgroups, resulting in a disparate reduction of model accuracy.
Tasks	Image Classification, Sentiment Analysis
Published	2019-05-28
URL	https://arxiv.org/abs/1905.12101v2
PDF	https://arxiv.org/pdf/1905.12101v2.pdf
PWC	https://paperswithcode.com/paper/differential-privacy-has-disparate-impact-on
Repo
Framework

Deep Joint Source-Channel Coding for Wireless Image Retrieval


Title	Deep Joint Source-Channel Coding for Wireless Image Retrieval
Authors	Mikolaj Jankowski, Deniz Gunduz, Krystian Mikolajczyk
Abstract	Motivated by surveillance applications with wireless cameras or drones, we consider the problem of image retrieval over a wireless channel. Conventional systems apply lossy compression on query images to reduce the data that must be transmitted over the bandwidth and power limited wireless link. We first note that reconstructing the original image is not needed for retrieval tasks; hence, we introduce a deep neutral network (DNN) based compression scheme targeting the retrieval task. Then, we completely remove the compression step, and propose another DNN-based communication scheme that directly maps the feature vectors to channel inputs. This joint source-channel coding (JSCC) approach not only improves the end-to-end accuracy, but also simplifies and speeds up the encoding operation which is highly beneficial for power and latency constrained IoT applications.
Tasks	Image Retrieval
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12703v1
PDF	https://arxiv.org/pdf/1910.12703v1.pdf
PWC	https://paperswithcode.com/paper/deep-joint-source-channel-coding-for-wireless-1
Repo
Framework

Experiments in Cuneiform Language Identification


Title	Experiments in Cuneiform Language Identification
Authors	Gustavo Henrique Paetzold, Marcos Zampieri
Abstract	This paper presents methods to discriminate between languages and dialects written in Cuneiform script, one of the first writing systems in the world. We report the results obtained by the PZ team in the Cuneiform Language Identification (CLI) shared task organized within the scope of the VarDial Evaluation Campaign 2019. The task included two languages, Sumerian and Akkadian. The latter is divided into six dialects: Old Babylonian, Middle Babylonian peripheral, Standard Babylonian, Neo Babylonian, Late Babylonian, and Neo Assyrian. We approach the task using a meta-classifier trained on various SVM models and we show the effectiveness of the system for this task. Our submission achieved 0.738 F1 score in discriminating between the seven languages and dialects and it was ranked fourth in the competition among eight teams.
Tasks	Language Identification
Published	2019-04-27
URL	http://arxiv.org/abs/1904.12087v1
PDF	http://arxiv.org/pdf/1904.12087v1.pdf
PWC	https://paperswithcode.com/paper/experiments-in-cuneiform-language
Repo
Framework

Finite Sample Analysis of Stochastic System Identification


Title	Finite Sample Analysis of Stochastic System Identification
Authors	Anastasios Tsiamis, George J. Pappas
Abstract	In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics. An unknown discrete-time linear system evolves over time under Gaussian noise without external inputs. The objective is to recover the system parameters as well as the Kalman filter gain, given a single trajectory of output measurements over a finite horizon of length $N$. Based on a subspace identification algorithm and a finite number of $N$ output samples, we provide non-asymptotic high-probability upper bounds for the system parameter estimation errors. Our analysis uses recent results from random matrix theory, self-normalized martingales and SVD robustness, in order to show that with high probability the estimation errors decrease with a rate of $1/\sqrt{N}$. Our non-asymptotic bounds not only agree with classical asymptotic results, but are also valid even when the system is marginally stable.
Tasks
Published	2019-03-21
URL	http://arxiv.org/abs/1903.09122v1
PDF	http://arxiv.org/pdf/1903.09122v1.pdf
PWC	https://paperswithcode.com/paper/finite-sample-analysis-of-stochastic-system
Repo
Framework