January 31, 2020

2919 words 14 mins read

Paper Group ANR 101

Ridesharing with Driver Location Preferences. Hyper: Distributed Cloud Processing for Large-Scale Deep Learning Tasks. Domain Representation for Knowledge Graph Embedding. A Study of the Learnability of Relational Properties (Model Counting Meets Machine Learning). Adapting RNN Sequence Prediction Model to Multi-label Set Prediction. Vulnerability …

Ridesharing with Driver Location Preferences


Title	Ridesharing with Driver Location Preferences
Authors	Duncan Rheingans-Yoo, Scott Duke Kominers, Hongyao Ma, David C. Parkes
Abstract	We study revenue-optimal pricing and driver compensation in ridesharing platforms when drivers have heterogeneous preferences over locations. If a platform ignores drivers’ location preferences, it may make inefficient trip dispatches; moreover, drivers may strategize so as to route towards their preferred locations. In a model with stationary and continuous demand and supply, we present a mechanism that incentivizes drivers to both (i) report their location preferences truthfully and (ii) always provide service. In settings with unconstrained driver supply or symmetric demand patterns, our mechanism achieves (full-information) first-best revenue. Under supply constraints and unbalanced demand, we show via simulation that our mechanism improves over existing mechanisms and has performance close to the first-best.
Tasks
Published	2019-05-30
URL	http://arxiv.org/abs/1905.13191v1
PDF	http://arxiv.org/pdf/1905.13191v1.pdf
PWC	https://paperswithcode.com/paper/ridesharing-with-driver-location-preferences
Repo
Framework

Hyper: Distributed Cloud Processing for Large-Scale Deep Learning Tasks


Title	Hyper: Distributed Cloud Processing for Large-Scale Deep Learning Tasks
Authors	Davit Buniatyan
Abstract	Training and deploying deep learning models in real-world applications require processing large amounts of data. This is a challenging task when the amount of data grows to a hundred terabytes, or even, petabyte-scale. We introduce a hybrid distributed cloud framework with a unified view to multiple clouds and an on-premise infrastructure for processing tasks using both CPU and GPU compute instances at scale. The system implements a distributed file system and failure-tolerant task processing scheduler, independent of the language and Deep Learning framework used. It allows to utilize unstable cheap resources on the cloud to significantly reduce costs. We demonstrate the scalability of the framework on running pre-processing, distributed training, hyperparameter search and large-scale inference tasks utilizing 10,000 CPU cores and 300 GPU instances with the overall processing power of 30 petaflops.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07172v1
PDF	https://arxiv.org/pdf/1910.07172v1.pdf
PWC	https://paperswithcode.com/paper/hyper-distributed-cloud-processing-for-large
Repo
Framework

Domain Representation for Knowledge Graph Embedding


Title	Domain Representation for Knowledge Graph Embedding
Authors	Cunxiang Wang, Feiliang Ren, Zhichao Lin, Chenxv Zhao, Tian Xie, Yue Zhang
Abstract	Embedding entities and relations into a continuous multi-dimensional vector space have become the dominant method for knowledge graph embedding in representation learning. However, most existing models ignore to represent hierarchical knowledge, such as the similarities and dissimilarities of entities in one domain. We proposed to learn a Domain Representations over existing knowledge graph embedding models, such that entities that have similar attributes are organized into the same domain. Such hierarchical knowledge of domains can give further evidence in link prediction. Experimental results show that domain embeddings give a significant improvement over the most recent state-of-art baseline knowledge graph embedding models.
Tasks	Graph Embedding, Knowledge Graph Embedding, Link Prediction, Representation Learning
Published	2019-03-26
URL	https://arxiv.org/abs/1903.10716v4
PDF	https://arxiv.org/pdf/1903.10716v4.pdf
PWC	https://paperswithcode.com/paper/domain-representation-for-knowledge-graph
Repo
Framework

A Study of the Learnability of Relational Properties (Model Counting Meets Machine Learning)


Title	A Study of the Learnability of Relational Properties (Model Counting Meets Machine Learning)
Authors	Muhammad Usman, Wenxi Wang, Kaiyuan Wang, Marko Vasic, Haris Vikalo, Sarfraz Khurshid
Abstract	Relational properties, e.g., the connectivity structure of nodes in a distributed system, have many applications in software design and analysis. However, such properties often have to be written manually, which can be costly and error-prone. This paper introduces the MCML approach for empirically studying the learnability of a key class of such properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire input spaces (up to a bound on the input size), and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art approximate and exact model counters for high efficiency. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1 score) at learning relational properties when evaluated in the common setting of using training and test datasets – even when the training dataset is much smaller than the test dataset – indicating the seeming simplicity of learning these properties. However, the use of MCML metrics based on model counting shows that the performance can degrade substantially when tested against the whole (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true accuracy.
Tasks
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11580v1
PDF	https://arxiv.org/pdf/1912.11580v1.pdf
PWC	https://paperswithcode.com/paper/a-study-of-the-learnability-of-relational
Repo
Framework

Adapting RNN Sequence Prediction Model to Multi-label Set Prediction


Title	Adapting RNN Sequence Prediction Model to Multi-label Set Prediction
Authors	Kechen Qin, Cheng Li, Virgil Pavlu, Javed A. Aslam
Abstract	We present an adaptation of RNN sequence models to the problem of multi-label classification for text, where the target is a set of labels, not a sequence. Previous such RNN models define probabilities for sequences but not for sets; attempts to obtain a set probability are after-thoughts of the network design, including pre-specifying the label order, or relating the sequence probability to the set probability in ad hoc ways. Our formulation is derived from a principled notion of set probability, as the sum of probabilities of corresponding permutation sequences for the set. We provide a new training objective that maximizes this set probability, and a new prediction objective that finds the most probable set on a test document. These new objectives are theoretically appealing because they give the RNN model freedom to discover the best label order, which often is the natural one (but different among documents). We develop efficient procedures to tackle the computation difficulties involved in training and prediction. Experiments on benchmark datasets demonstrate that we outperform state-of-the-art methods for this task.
Tasks	Multi-Label Classification
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05829v1
PDF	http://arxiv.org/pdf/1904.05829v1.pdf
PWC	https://paperswithcode.com/paper/adapting-rnn-sequence-prediction-model-to
Repo
Framework

Vulnerability of Face Recognition to Deep Morphing


Title	Vulnerability of Face Recognition to Deep Morphing
Authors	Pavel Korshunov, Sébastien Marcel
Abstract	It is increasingly easy to automatically swap faces in images and video or morph two faces into one using generative adversarial networks (GANs). The high quality of the resulted deep-morph raises the question of how vulnerable the current face recognition systems are to such fake images and videos. It also calls for automated ways to detect these GAN-generated faces. In this paper, we present the publicly available dataset of the Deepfake videos with faces morphed with a GAN-based algorithm. To generate these videos, we used open source software based on GANs, and we emphasize that training and blending parameters can significantly impact the quality of the resulted videos. We show that the state of the art face recognition systems based on VGG and Facenet neural networks are vulnerable to the deep morph videos, with 85.62 and 95.00 false acceptance rates, respectively, which means methods for detecting these videos are necessary. We consider several baseline approaches for detecting deep morphs and find that the method based on visual quality metrics (often used in presentation attack detection domain) leads to the best performance with 8.97 equal error rate. Our experiments demonstrate that GAN-generated deep morph videos are challenging for both face recognition systems and existing detection methods, and the further development of deep morphing technologies will make it even more so.
Tasks	Face Recognition, Face Swapping
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01933v1
PDF	https://arxiv.org/pdf/1910.01933v1.pdf
PWC	https://paperswithcode.com/paper/vulnerability-of-face-recognition-to-deep
Repo
Framework

Using Background Knowledge to Rank Itemsets


Title	Using Background Knowledge to Rank Itemsets
Authors	Nikolaj Tatti, Michael Mampaey
Abstract	Assessing the quality of discovered results is an important open problem in data mining. Such assessment is particularly vital when mining itemsets, since commonly many of the discovered patterns can be easily explained by background knowledge. The simplest approach to screen uninteresting patterns is to compare the observed frequency against the independence model. Since the parameters for the independence model are the column margins, we can view such screening as a way of using the column margins as background knowledge. In this paper we study techniques for more flexible approaches for infusing background knowledge. Namely, we show that we can efficiently use additional knowledge such as row margins, lazarus counts, and bounds of ones. We demonstrate that these statistics describe forms of data that occur in practice and have been studied in data mining. To infuse the information efficiently we use a maximum entropy approach. In its general setting, solving a maximum entropy model is infeasible, but we demonstrate that for our setting it can be solved in polynomial time. Experiments show that more sophisticated models fit the data better and that using more information improves the frequency prediction of itemsets.
Tasks
Published	2019-02-08
URL	http://arxiv.org/abs/1902.03102v1
PDF	http://arxiv.org/pdf/1902.03102v1.pdf
PWC	https://paperswithcode.com/paper/using-background-knowledge-to-rank-itemsets
Repo
Framework

Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks


Title	Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
Authors	Mokanarangan Thayaparan, Marco Valentino, Viktor Schlegel, Andre Freitas
Abstract	Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, complex Question Answering (QA) typically requires multi-hop reasoning - i.e. the integration of supporting facts from different sources, to infer the correct answer. This paper proposes Document Graph Network (DGN), a message passing architecture for the identification of supporting facts over a graph-structured representation of text. The evaluation on HotpotQA shows that DGN obtains competitive results when compared to a reading comprehension baseline operating on raw text, confirming the relevance of structured representations for supporting multi-hop reasoning.
Tasks	Question Answering, Reading Comprehension
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00290v1
PDF	https://arxiv.org/pdf/1910.00290v1.pdf
PWC	https://paperswithcode.com/paper/identifying-supporting-facts-for-multi-hop
Repo
Framework

Dunhuang Grottoes Painting Dataset and Benchmark


Title	Dunhuang Grottoes Painting Dataset and Benchmark
Authors	Tianxiu Yu, Shijie Zhang, Cong Lin, Shaodi You, Jian Wu, Jiawan Zhang, Xiaohong Ding, Huili An
Abstract	This document introduces the background and the usage of the Dunhuang Grottoes Dataset and the benchmark. The documentation first starts with the background of the Dunhuang Grotto, which is widely recognised as an priceless heritage. Given that digital method is the modern trend for heritage protection and restoration. Follow the trend, we release the first public dataset for Dunhuang Grotto Painting restoration. The rest of the documentation details the painting data generation. To enable a data driven fashion, this dataset provided a large number of training and testing example which is sufficient for a deep learning approach. The detailed usage of the dataset as well as the benchmark is described.
Tasks
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04589v2
PDF	https://arxiv.org/pdf/1907.04589v2.pdf
PWC	https://paperswithcode.com/paper/dunhuang-grotto-painting-dataset-and
Repo
Framework

Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping


Title	Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping
Authors	Matthias Freiberger, Peter Bienstman, Joni Dambre
Abstract	Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths. Despite recent successes, there are bounds to what one can achieve simply by making photonic reservoirs larger. Therefore, a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable. Given that backpropagation can not be used directly to train multi-reservoir systems in our targeted setting, we propose an alternative approach that still uses its power to derive intermediate targets. In this work we report our findings on a conducted experiment to evaluate the general feasibility of our approach by training a network of 3 Echo State Networks to perform the well-known NARMA-10 task using targets derived through backpropagation. Our results indicate that our proposed method is well-suited to train multi-reservoir systems in a efficient way.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.13332v1
PDF	https://arxiv.org/pdf/1910.13332v1.pdf
PWC	https://paperswithcode.com/paper/towards-deep-physical-reservoir-computing
Repo
Framework

Shallow Neural Network can Perfectly Classify an Object following Separable Probability Distribution


Title	Shallow Neural Network can Perfectly Classify an Object following Separable Probability Distribution
Authors	Youngjae Min, Hye Won Chung
Abstract	Guiding the design of neural networks is of great importance to save enormous resources consumed on empirical decisions of architectural parameters. This paper constructs shallow sigmoid-type neural networks that achieve 100% accuracy in classification for datasets following a linear separability condition. The separability condition in this work is more relaxed than the widely used linear separability. Moreover, the constructed neural network guarantees perfect classification for any datasets sampled from a separable probability distribution. This generalization capability comes from the saturation of sigmoid function that exploits small margins near the boundaries of intervals formed by the separable probability distribution.
Tasks
Published	2019-04-19
URL	http://arxiv.org/abs/1904.09109v1
PDF	http://arxiv.org/pdf/1904.09109v1.pdf
PWC	https://paperswithcode.com/paper/shallow-neural-network-can-perfectly-classify
Repo
Framework

Tumor Saliency Estimation for Breast Ultrasound Images via Breast Anatomy Modeling


Title	Tumor Saliency Estimation for Breast Ultrasound Images via Breast Anatomy Modeling
Authors	Fei Xu, Yingtao Zhang, Min Xian, H. D. Cheng, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang
Abstract	Tumor saliency estimation aims to localize tumors by modeling the visual stimuli in medical images. However, it is a challenging task for breast ultrasound due to the complicated anatomic structure of the breast and poor image quality; and existing saliency estimation approaches only model generic visual stimuli, e.g., local and global contrast, location, and feature correlation, and achieve poor performance for tumor saliency estimation. In this paper, we propose a novel optimization model to estimate tumor saliency by utilizing breast anatomy. First, we model breast anatomy and decompose breast ultrasound image into layers using Neutro-Connectedness; then utilize the layers to generate the foreground and background maps; and finally propose a novel objective function to estimate the tumor saliency by integrating the foreground map, background map, adaptive center bias, and region-based correlation cues. The extensive experiments demonstrate that the proposed approach obtains more accurate foreground and background maps with the assistance of the breast anatomy; especially, for the images having large or small tumors; meanwhile, the new objective function can handle the images without tumors. The newly proposed method achieves state-of-the-art performance when compared to eight tumor saliency estimation approaches using two breast ultrasound datasets.
Tasks	Saliency Prediction
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07760v1
PDF	https://arxiv.org/pdf/1906.07760v1.pdf
PWC	https://paperswithcode.com/paper/tumor-saliency-estimation-for-breast
Repo
Framework

Translation Insensitive CNNs


Title	Translation Insensitive CNNs
Authors	Ganesh Sundaramoorthi, Timothy E. Wang
Abstract	We address the problem that state-of-the-art Convolution Neural Networks (CNN) classifiers are not invariant to small shifts. The problem can be solved by the removal of sub-sampling operations such as stride and max pooling, but at a cost of severely degraded training and test efficiency. We present a novel usage of Gaussian-Hermite basis to efficiently approximate arbitrary filters within the CNN framework to obtain translation invariance. This is shown to be invariant to small shifts, and preserves the efficiency of training. Further, to improve efficiency in memory usage as well as computational speed, we show that it is still possible to sub-sample with this approach and retain a weaker form of invariance that we call \emph{translation insensitivity}, which leads to stability with respect to shifts. We prove these claims analytically and empirically. Our analytic methods further provide a framework for understanding any architecture in terms of translation insensitivity, and provide guiding principles for design.
Tasks
Published	2019-11-25
URL	https://arxiv.org/abs/1911.11238v1
PDF	https://arxiv.org/pdf/1911.11238v1.pdf
PWC	https://paperswithcode.com/paper/translation-insensitive-cnns
Repo
Framework

Element Level Differential Privacy: The Right Granularity of Privacy


Title	Element Level Differential Privacy: The Right Granularity of Privacy
Authors	Hilal Asi, John Duchi, Omid Javidbakht
Abstract	Differential Privacy (DP) provides strong guarantees on the risk of compromising a user’s data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To address this, we propose element level differential privacy, which extends differential privacy to provide protection against leaking information about any particular “element” a user has, allowing better utility and more robust results than classical DP. By carefully choosing these “elements,” it is possible to provide privacy protections at a desired granularity. We provide definitions, associated privacy guarantees, and analysis to identify the tradeoffs with the new definition; we also develop several private estimation and learning methodologies, providing careful examples for item frequency and M-estimation (empirical risk minimization) with concomitant privacy and utility analysis. We complement our theoretical and methodological advances with several real-world applications, estimating histograms and fitting several large-scale prediction models, including deep networks.
Tasks
Published	2019-12-05
URL	https://arxiv.org/abs/1912.04042v1
PDF	https://arxiv.org/pdf/1912.04042v1.pdf
PWC	https://paperswithcode.com/paper/element-level-differential-privacy-the-right
Repo
Framework

Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data


Title	Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
Authors	David W. Romero, Mark Hoogendoorn
Abstract	Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never appear (e.g. an upright face with a horizontal nose), current equivariant architectures consider the set of all possible transformations in a transformation group when learning feature representations. Contrarily, the human visual system is able to attend to the set of relevant transformations occurring in the environment and utilizes this information to assist and improve object recognition. Based on this observation, we modify conventional equivariant feature mappings such that they are able to attend to the set of co-occurring transformations in data and generalize this notion to act on groups consisting of multiple symmetries. We show that our proposed co-attentive equivariant neural networks consistently outperform conventional rotation equivariant and rotation & reflection equivariant neural networks on rotated MNIST and CIFAR-10.
Tasks	Object Recognition
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07849v2
PDF	https://arxiv.org/pdf/1911.07849v2.pdf
PWC	https://paperswithcode.com/paper/co-attentive-equivariant-neural-networks-1
Repo
Framework