January 26, 2020

2995 words 15 mins read

Paper Group ANR 1575

Multi-MotifGAN (MMGAN): Motif-targeted Graph Generation and Prediction. Rényi Fair Inference. Multi-objective Bayesian Optimization using Pareto-frontier Entropy. Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes. PCA-RECT: An Energy-efficient Object Detection Approach for Event Cameras. Minimally Supe …

Multi-MotifGAN (MMGAN): Motif-targeted Graph Generation and Prediction


Title	Multi-MotifGAN (MMGAN): Motif-targeted Graph Generation and Prediction
Authors	Anuththari Gamage, Eli Chien, Jianhao Peng, Olgica Milenkovic
Abstract	Generative graph models create instances of graphs that mimic the properties of real-world networks. Generative models are successful at retaining pairwise associations in the underlying networks but often fail to capture higher-order connectivity patterns known as network motifs. Different types of graphs contain different network motifs, an example of which are triangles that often arise in social and biological networks. It is hence vital to capture these higher-order structures to simulate real-world networks accurately. We propose Multi-MotifGAN (MMGAN), a motif-targeted Generative Adversarial Network (GAN) that generalizes the benchmark NetGAN approach. The generalization consists of combining multiple biased random walks, each of which captures a different motif structure. MMGAN outperforms NetGAN at creating new graphs that accurately reflect the network motif statistics of input graphs such as Citeseer, Cora and Facebook.
Tasks	Graph Generation
Published	2019-11-08
URL	https://arxiv.org/abs/1911.05469v1
PDF	https://arxiv.org/pdf/1911.05469v1.pdf
PWC	https://paperswithcode.com/paper/multi-motifgan-mmgan-motif-targeted-graph
Repo
Framework

Rényi Fair Inference


Title	Rényi Fair Inference
Authors	Sina Baharlouei, Maher Nouiehed, Ahmad Beirami, Meisam Razaviyayn
Abstract	Machine learning algorithms have been increasingly deployed in critical automated decision-making systems that directly affect human lives. When these algorithms are only trained to minimize the training/test error, they could suffer from systematic discrimination against individuals based on their sensitive attributes such as gender or race. Recently, there has been a surge in machine learning society to develop algorithms for fair machine learning. In particular, many adversarial learning procedures have been proposed to impose fairness. Unfortunately, these algorithms either can only impose fairness up to first-order dependence between the variables, or they lack computational convergence guarantees. In this paper, we use R'enyi correlation as a measure of fairness of machine learning models and develop a general training framework to impose fairness. In particular, we propose a min-max formulation which balances the accuracy and fairness when solved to optimality. For the case of discrete sensitive attributes, we suggest an iterative algorithm with theoretical convergence guarantee for solving the proposed min-max problem. Our algorithm and analysis are then specialized to fair classification and the fair clustering problem under disparate impact doctrine. Finally, the performance of the proposed R'enyi fair inference framework is evaluated on Adult and Bank datasets.
Tasks	Decision Making
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12005v2
PDF	https://arxiv.org/pdf/1906.12005v2.pdf
PWC	https://paperswithcode.com/paper/renyi-fair-inference
Repo
Framework

Multi-objective Bayesian Optimization using Pareto-frontier Entropy


Title	Multi-objective Bayesian Optimization using Pareto-frontier Entropy
Authors	Shinya Suzuki, Shion Takeno, Tomoyuki Tamura, Kazuki Shitara, Masayuki Karasuyama
Abstract	This paper studies an entropy-based multi-objective Bayesian optimization (MBO). The entropy search is successful approach to Bayesian optimization. However, for MBO, existing entropy-based methods ignore trade-off among objectives or introduce unreliable approximations. We propose a novel entropy-based MBO called Pareto-frontier entropy search (PFES) by considering the entropy of Pareto-frontier, which is an essential notion of the optimality of the multi-objective problem. Our entropy can incorporate the trade-off relation of the optimal values, and further, we derive an analytical formula without introducing additional approximations or simplifications to the standard entropy search setting. We also show that our entropy computation is practically feasible by using a recursive decomposition technique which has been known in studies of the Pareto hyper-volume computation. Besides the usual MBO setting, in which all the objectives are simultaneously observed, we also consider the “decoupled” setting, in which the objective functions can be observed separately. PFES can easily adapt to the decoupled setting by considering the entropy of the marginal density for each output dimension. This approach incorporates dependency among objectives conditioned on Pareto-frontier, which is ignored by the existing method. Our numerical experiments show effectiveness of PFES through several benchmark datasets.
Tasks
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00127v2
PDF	https://arxiv.org/pdf/1906.00127v2.pdf
PWC	https://paperswithcode.com/paper/190600127
Repo
Framework

Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes


Title	Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes
Authors	Aida Mostafazadeh Davani, Leigh Yeh, Mohammad Atari, Brendan Kennedy, Gwenyth Portillo-Wightman, Elaine Gonzalez, Natalie Delong, Rhea Bhatia, Arineh Mirinjian, Xiang Ren, Morteza Dehghani
Abstract	Official reports of hate crimes in the US are under-reported relative to the actual number of such incidents. Further, despite statistical approximations, there are no official reports from a large number of US cities regarding incidents of hate. Here, we first demonstrate that event extraction and multi-instance learning, applied to a corpus of local news articles, can be used to predict instances of hate crime. We then use the trained model to detect incidents of hate in cities for which the FBI lacks statistics. Lastly, we train models on predicting homicide and kidnapping, compare the predictions to FBI reports, and establish that incidents of hate are indeed under-reported, compared to other types of crimes, in local press.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.02126v1
PDF	https://arxiv.org/pdf/1909.02126v1.pdf
PWC	https://paperswithcode.com/paper/reporting-the-unreported-event-extraction-for
Repo
Framework

PCA-RECT: An Energy-efficient Object Detection Approach for Event Cameras


Title	PCA-RECT: An Energy-efficient Object Detection Approach for Event Cameras
Authors	Bharath Ramesh, Andres Ussa, Luca Della Vedova, Hong Yang, Garrick Orchard
Abstract	We present the first purely event-based, energy-efficient approach for object detection and categorization using an event camera. Compared to traditional frame-based cameras, choosing event cameras results in high temporal resolution (order of microseconds), low power consumption (few hundred mW) and wide dynamic range (120 dB) as attractive properties. However, event-based object recognition systems are far behind their frame-based counterparts in terms of accuracy. To this end, this paper presents an event-based feature extraction method devised by accumulating local activity across the image frame and then applying principal component analysis (PCA) to the normalized neighborhood region. Subsequently, we propose a backtracking-free k-d tree mechanism for efficient feature matching by taking advantage of the low-dimensionality of the feature representation. Additionally, the proposed k-d tree mechanism allows for feature selection to obtain a lower-dimensional dictionary representation when hardware resources are limited to implement dimensionality reduction. Consequently, the proposed system can be realized on a field-programmable gate array (FPGA) device leading to high performance over resource ratio. The proposed system is tested on real-world event-based datasets for object categorization, showing superior classification performance and relevance to state-of-the-art algorithms. Additionally, we verified the object detection method and real-time FPGA performance in lab settings under non-controlled illumination conditions with limited training data and ground truth annotations.
Tasks	Dimensionality Reduction, Feature Selection, Object Detection, Object Recognition
Published	2019-04-24
URL	http://arxiv.org/abs/1904.12665v1
PDF	http://arxiv.org/pdf/1904.12665v1.pdf
PWC	https://paperswithcode.com/paper/190412665
Repo
Framework

Minimally Supervised Learning of Affective Events Using Discourse Relations


Title	Minimally Supervised Learning of Affective Events Using Discourse Relations
Authors	Jun Saito, Yugo Murawaki, Sadao Kurohashi
Abstract	Recognizing affective events that trigger positive or negative sentiment has a wide range of natural language processing applications but remains a challenging problem mainly because the polarity of an event is not necessarily predictable from its constituent words. In this paper, we propose to propagate affective polarity using discourse relations. Our method is simple and only requires a very small seed lexicon and a large raw corpus. Our experiments using Japanese data show that our method learns affective events effectively without manually labeled data. It also improves supervised learning results when labeled data are small.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00694v2
PDF	https://arxiv.org/pdf/1909.00694v2.pdf
PWC	https://paperswithcode.com/paper/minimally-supervised-learning-of-affective
Repo
Framework

Real-time Travel Time Estimation Using Matrix Factorization


Title	Real-time Travel Time Estimation Using Matrix Factorization
Authors	Ebrahim Badrestani, Behnam Bahrak, Ali Elahi, Adib Faramarzi, Pouria Golshanrad, Amin Karimi Monsefi, Hamid Mahini, Armin Zirak
Abstract	Estimating the travel time of any route is of great importance for trip planners, traffic operators, online taxi dispatching and ride-sharing platforms, and navigation provider systems. With the advance of technology, many traveling cars, including online taxi dispatch systems’ vehicles are equipped with Global Positioning System (GPS) devices that can report the location of the vehicle every few seconds. This paper uses GPS data and the Matrix Factorization techniques to estimate the travel times on all road segments and time intervals simultaneously. We aggregate GPS data into a matrix, where each cell of the original matrix contains the average vehicle speed for a segment and a specific time interval. One of the problems with this matrix is its high sparsity. We use Alternating Least Squares (ALS) method along with a regularization term to factorize the matrix. Since this approach can solve the sparsity problem that arises from the absence of cars in many road segments in a specific time interval, matrix factorization is suitable for estimating the travel time. Our comprehensive evaluation results using real data provided by one of the largest online taxi dispatching systems in Iran, shows the strength of our proposed method.
Tasks
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00455v1
PDF	https://arxiv.org/pdf/1912.00455v1.pdf
PWC	https://paperswithcode.com/paper/real-time-travel-time-estimation-using-matrix
Repo
Framework

Interdependency between the Stock Market and Financial News


Title	Interdependency between the Stock Market and Financial News
Authors	EunJeong Hwang, Yong-Hyuk Kim
Abstract	Stock prices are driven by various factors. In particular, many individual investors who have relatively little financial knowledge rely heavily on the information from news stories when making investment decisions in the stock market. However, these stories may not reflect future stock prices because of the subjectivity in the news; stock prices may instead affect the news contents. This study aims to discover whether it is news or stock prices that have a greater impact on the other. To achieve this, we analyze the relationship between news sentiment and stock prices based on time series analysis using five different classification models. Our experimental results show that stock prices have a bigger impact on the news contents than news does on stock prices.
Tasks	Time Series, Time Series Analysis
Published	2019-09-01
URL	https://arxiv.org/abs/1909.00344v1
PDF	https://arxiv.org/pdf/1909.00344v1.pdf
PWC	https://paperswithcode.com/paper/interdependency-between-the-stock-market-and
Repo
Framework

Identity Document to Selfie Face Matching Across Adolescence


Title	Identity Document to Selfie Face Matching Across Adolescence
Authors	Vítor Albiero, Nisha Srinivas, Esteban Villalobos, Jorge Perez-Facuse, Roberto Rosenthal, Domingo Mery, Karl Ricanek, Kevin W. Bowyer
Abstract	Matching live images (``selfies’') to images from ID documents is a problem that can arise in various applications. A challenging instance of the problem arises when the face image on the ID document is from early adolescence and the live image is from later adolescence. We explore this problem using a private dataset called Chilean Young Adult (CHIYA) dataset, where we match live face images taken at age 18-19 to face images on ID documents created at ages 9 to 18. State-of-the-art deep learning face matchers (e.g., ArcFace) have relatively poor accuracy for document-to-selfie face matching. To achieve higher accuracy, we fine-tune the best available open-source model with triplet loss for a few-shot learning. Experiments show that our approach achieves higher accuracy than the DocFace+ model recently developed for this problem. Our fine-tuned model was able to improve the true acceptance rate for the most difficult (largest age span) subset from 62.92% to 96.67% at a false acceptance rate of 0.01%. Our fine-tuned model is available for use by other researchers. \|
Tasks	Few-Shot Learning
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10021v1
PDF	https://arxiv.org/pdf/1912.10021v1.pdf
PWC	https://paperswithcode.com/paper/identity-document-to-selfie-face-matching
Repo
Framework

Wasserstein Diffusion Tikhonov Regularization


Title	Wasserstein Diffusion Tikhonov Regularization
Authors	Alex Tong Lin, Yonatan Dukler, Wuchen Li, Guido Montufar
Abstract	We propose regularization strategies for learning discriminative models that are robust to in-class variations of the input data. We use the Wasserstein-2 geometry to capture semantically meaningful neighborhoods in the space of images, and define a corresponding input-dependent additive noise data augmentation model. Expanding and integrating the augmented loss yields an effective Tikhonov-type Wasserstein diffusion smoothness regularizer. This approach allows us to apply high levels of regularization and train functions that have low variability within classes but remain flexible across classes. We provide efficient methods for computing the regularizer at a negligible cost in comparison to training with adversarial data augmentation. Initial experiments demonstrate improvements in generalization performance under adversarial perturbations and also large in-class variations of the input data.
Tasks	Data Augmentation
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06860v1
PDF	https://arxiv.org/pdf/1909.06860v1.pdf
PWC	https://paperswithcode.com/paper/wasserstein-diffusion-tikhonov-regularization
Repo
Framework

Identifying disease-free chest X-ray images with deep transfer learning


Title	Identifying disease-free chest X-ray images with deep transfer learning
Authors	Ken C. L. Wong, Mehdi Moradi, Joy Wu, Tanveer Syeda-Mahmood
Abstract	Chest X-rays (CXRs) are among the most commonly used medical image modalities. They are mostly used for screening, and an indication of disease typically results in subsequent tests. As this is mostly a screening test used to rule out chest abnormalities, the requesting clinicians are often interested in whether a CXR is normal or not. A machine learning algorithm that can accurately screen out even a small proportion of the “real normal” exams out of all requested CXRs would be highly beneficial in reducing the workload for radiologists. In this work, we report a deep neural network trained for classifying CXRs with the goal of identifying a large number of normal (disease-free) images without risking the discharge of sick patients. We use an ImageNet-pretrained Inception-ResNet-v2 model to provide the image features, which are further used to train a model on CXRs labelled by expert radiologists. The probability threshold for classification is optimized for 100% precision for the normal class, ensuring no sick patients are released. At this threshold we report an average recall of 50%. This means that the proposed solution has the potential to cut in half the number of disease-free CXRs examined by radiologists, without risking the discharge of sick patients.
Tasks	Transfer Learning
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01654v1
PDF	http://arxiv.org/pdf/1904.01654v1.pdf
PWC	https://paperswithcode.com/paper/identifying-disease-free-chest-x-ray-images
Repo
Framework

Semantic Image Completion and Enhancement using Deep Learning


Title	Semantic Image Completion and Enhancement using Deep Learning
Authors	Vaishnav Chandak, Priyansh Saxena, Manisha Pattanaik, Gaurav Kaushal
Abstract	In real-life applications, certain images utilized are corrupted in which the image pixels are damaged or missing, which increases the complexity of computer vision tasks. In this paper, a deep learning architecture is proposed to deal with image completion and enhancement. Generative Adversarial Networks (GAN), has been turned out to be helpful in picture completion tasks. Therefore, in GANs, Wasserstein GAN architecture is used for image completion which creates the coarse patches to filling the missing region in the distorted picture, and the enhancement network will additionally refine the resultant pictures utilizing residual learning procedures and hence give better complete pictures for computer vision applications. Experimental outcomes show that the proposed approach improves the Peak Signal to Noise ratio and Structural Similarity Index values by 2.45% and 4% respectively when compared to the recently reported data.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02222v2
PDF	https://arxiv.org/pdf/1911.02222v2.pdf
PWC	https://paperswithcode.com/paper/semantic-image-completion-and-enhancement
Repo
Framework

Can generalised relative pose estimation solve sparse 3D registration?


Title	Can generalised relative pose estimation solve sparse 3D registration?
Authors	Siddhant Ranade, Xin Yu, Shantnu Kakkar, Pedro Miraldo, Srikumar Ramalingam
Abstract	Popular 3D scan registration projects, such as Stanford digital Michelangelo or KinectFusion, exploit the high-resolution sensor data for scan alignment. It is particularly challenging to solve the registration of sparse 3D scans in the absence of RGB components. In this case, we can not establish point correspondences since the same 3D point cannot be captured in two successive scans. In contrast to correspondence based methods, we take a different viewpoint and formulate the sparse 3D registration problem based on the constraints from the intersection of line segments from adjacent scans. We obtain the line segments by modeling every horizontal and vertical scan-line as piece-wise linear segments. We propose a new alternating projection algorithm for solving the scan alignment problem using line intersection constraints. We develop two new minimal solvers for scan alignment in the presence of plane correspondences: 1) 3 line intersections and 1 plane correspondence, and 2) 1 line intersection and 2 plane correspondences. We outperform other competing methods on Kinect and LiDAR datasets.
Tasks	Pose Estimation
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05888v1
PDF	https://arxiv.org/pdf/1906.05888v1.pdf
PWC	https://paperswithcode.com/paper/can-generalised-relative-pose-estimation
Repo
Framework

Improved Few-Shot Visual Classification


Title	Improved Few-Shot Visual Classification
Authors	Peyman Bateni, Raghav Goyal, Vaden Masrani, Frank Wood, Leonid Sigal
Abstract	Few-shot learning is a fundamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data. Most few-shot learning approaches to date have focused on progressively more complex neural feature extractors and classifier adaptation strategies, as well as the refinement of the task definition itself. In this paper, we explore the hypothesis that a simple class-covariance-based distance metric, namely the Mahalanobis distance, adopted into a state of the art few-shot learning approach (CNAPS) can, in and of itself, lead to a significant performance improvement. We also discover that it is possible to learn adaptive feature extractors that allow useful estimation of the high dimensional feature covariances required by this metric from surprisingly few samples. The result of our work is a new “Simple CNAPS” architecture which has up to 9.2% fewer trainable parameters than CNAPS and performs up to 6.1% better than state of the art on the standard few-shot image classification benchmark dataset.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Image Classification
Published	2019-12-07
URL	https://arxiv.org/abs/1912.03432v2
PDF	https://arxiv.org/pdf/1912.03432v2.pdf
PWC	https://paperswithcode.com/paper/improved-few-shot-visual-classification
Repo
Framework

Towards Multicellular Biological Deep Neural Nets Based on Transcriptional Regulation


Title	Towards Multicellular Biological Deep Neural Nets Based on Transcriptional Regulation
Authors	Sihao Huang
Abstract	Artificial neurons built on synthetic gene networks have potential applications ranging from complex cellular decision-making to bioreactor regulation. Furthermore, due to the high information throughput of natural systems, it provides an interesting candidate for biologically-based supercomputing and analog simulations of traditionally intractable problems. In this paper, we propose an architecture for constructing multicellular neural networks and programmable nonlinear systems. We design an artificial neuron based on gene regulatory networks and optimize its dynamics for modularity. Using gene expression models, we simulate its ability to perform arbitrary linear classifications from multiple inputs. Finally, we construct a two-layer neural network to demonstrate scalability and nonlinear decision boundaries and discuss future directions for utilizing uncontrolled neurons in computational tasks.
Tasks	Decision Making
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11423v2
PDF	https://arxiv.org/pdf/1912.11423v2.pdf
PWC	https://paperswithcode.com/paper/towards-multicellular-biological-deep-neural
Repo
Framework