January 28, 2020

3345 words 16 mins read

Paper Group ANR 1061

Regression via Arbitrary Quantile Modeling. Supervised Anomaly Detection based on Deep Autoregressive Density Estimators. Anatomically-Informed Data Augmentation for functional MRI with Applications to Deep Learning. Oxford Handbook on AI Ethics Book Chapter on Race and Gender. Low-rank matrix recovery with composite optimization: good conditioning …

Regression via Arbitrary Quantile Modeling


Title	Regression via Arbitrary Quantile Modeling
Authors	Faen Zhang, Xinyu Fan, Hui Xu, Pengcheng Zhou, Yujian He, Junlong Liu
Abstract	In the regression problem, L1 and L2 are the most commonly used loss functions, which produce mean predictions with different biases. However, the predictions are neither robust nor adequate enough since they only capture a few conditional distributions instead of the whole distribution, especially for small datasets. To address this problem, we proposed arbitrary quantile modeling to regulate the prediction, which achieved better performance compared to traditional loss functions. More specifically, a new distribution regression method, Deep Distribution Regression (DDR), is proposed to estimate arbitrary quantiles of the response variable. Our DDR method consists of two models: a Q model, which predicts the corresponding value for arbitrary quantile, and an F model, which predicts the corresponding quantile for arbitrary value. Furthermore, the duality between Q and F models enables us to design a novel loss function for joint training and perform a dual inference mechanism. Our experiments demonstrate that our DDR-joint and DDR-disjoint methods outperform previous methods such as AdaBoost, random forest, LightGBM, and neural networks both in terms of mean and quantile prediction.
Tasks
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05441v1
PDF	https://arxiv.org/pdf/1911.05441v1.pdf
PWC	https://paperswithcode.com/paper/regression-via-arbitrary-quantile-modeling
Repo
Framework

Supervised Anomaly Detection based on Deep Autoregressive Density Estimators


Title	Supervised Anomaly Detection based on Deep Autoregressive Density Estimators
Authors	Tomoharu Iwata, Yuki Yamanaka
Abstract	We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score. Density estimators have been widely used for unsupervised anomaly detection. By the recent advance of deep learning, the density estimation performance has been greatly improved. However, the neural density estimators cannot exploit anomaly label information, which would be valuable for improving the anomaly detection performance. The proposed method effectively utilizes the anomaly label information by training the neural density estimator so that the likelihood of normal instances is maximized and the likelihood of anomalous instances is lower than that of the normal instances. We employ an autoregressive model for the neural density estimator, which enables us to calculate the likelihood exactly. With the experiments using 16 datasets, we demonstrate that the proposed method improves the anomaly detection performance with a few labeled anomalous instances, and achieves better performance than existing unsupervised and supervised anomaly detection methods.
Tasks	Anomaly Detection, Density Estimation, Unsupervised Anomaly Detection
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06034v1
PDF	http://arxiv.org/pdf/1904.06034v1.pdf
PWC	https://paperswithcode.com/paper/supervised-anomaly-detection-based-on-deep
Repo
Framework

Anatomically-Informed Data Augmentation for functional MRI with Applications to Deep Learning


Title	Anatomically-Informed Data Augmentation for functional MRI with Applications to Deep Learning
Authors	Kevin P. Nguyen, Cherise Chin Fatt, Alex Treacher, Cooper Mellema, Madhukar H. Trivedi, Albert Montillo
Abstract	The application of deep learning to build accurate predictive models from functional neuroimaging data is often hindered by limited dataset sizes. Though data augmentation can help mitigate such training obstacles, most data augmentation methods have been developed for natural images as in computer vision tasks such as CIFAR, not for medical images. This work helps to fills in this gap by proposing a method for generating new functional Magnetic Resonance Images (fMRI) with realistic brain morphology. This method is tested on a challenging task of predicting antidepressant treatment response from pre-treatment task-based fMRI and demonstrates a 26% improvement in performance in predicting response using augmented images. This improvement compares favorably to state-of-the-art augmentation methods for natural images. Through an ablative test, augmentation is also shown to substantively improve performance when applied before hyperparameter optimization. These results suggest the optimal order of operations and support the role of data augmentation method for improving predictive performance in tasks using fMRI.
Tasks	Data Augmentation, Hyperparameter Optimization
Published	2019-10-17
URL	https://arxiv.org/abs/1910.08112v1
PDF	https://arxiv.org/pdf/1910.08112v1.pdf
PWC	https://paperswithcode.com/paper/anatomically-informed-data-augmentation-for
Repo
Framework

Oxford Handbook on AI Ethics Book Chapter on Race and Gender


Title	Oxford Handbook on AI Ethics Book Chapter on Race and Gender
Authors	Timnit Gebru
Abstract	From massive face-recognition-based surveillance and machine-learning-based decision systems predicting crime recidivism rates, to the move towards automated health diagnostic systems, artificial intelligence (AI) is being used in scenarios that have serious consequences in people’s lives. However, this rapid permeation of AI into society has not been accompanied by a thorough investigation of the sociopolitical issues that cause certain groups of people to be harmed rather than advantaged by it. For instance, recent studies have shown that commercial face recognition systems have much higher error rates for dark skinned women while having minimal errors on light skinned men. A 2016 ProPublica investigation uncovered that machine learning based tools that assess crime recidivism rates in the US are biased against African Americans. Other studies show that natural language processing tools trained on newspapers exhibit societal biases (e.g. finishing the analogy “Man is to computer programmer as woman is to X” by homemaker). At the same time, books such as Weapons of Math Destruction and Automated Inequality detail how people in lower socioeconomic classes in the US are subjected to more automated decision making tools than those who are in the upper class. Thus, these tools are most often used on people towards whom they exhibit the most bias. While many technical solutions have been proposed to alleviate bias in machine learning systems, we have to take a holistic and multifaceted approach. This includes standardization bodies determining what types of systems can be used in which scenarios, making sure that automated decision tools are created by people from diverse backgrounds, and understanding the historical and political factors that disadvantage certain groups who are subjected to these tools.
Tasks	Decision Making, Face Recognition
Published	2019-08-08
URL	https://arxiv.org/abs/1908.06165v1
PDF	https://arxiv.org/pdf/1908.06165v1.pdf
PWC	https://paperswithcode.com/paper/oxford-handbook-on-ai-ethics-book-chapter-on
Repo
Framework

Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence


Title	Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
Authors	Vasileios Charisopoulos, Yudong Chen, Damek Davis, Mateo Díaz, Lijun Ding, Dmitriy Drusvyatskiy
Abstract	The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undesirable phenomenon: the condition number, classically defined, scales poorly with the dimension of the ambient space. In contrast, we here show that in a variety of concrete circumstances, nonsmooth penalty formulations do not suffer from the same type of ill-conditioning. Consequently, standard algorithms for nonsmooth optimization, such as subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the solution. Moreover, nonsmooth formulations are naturally robust against outliers. Our framework subsumes such important computational tasks as phase retrieval, blind deconvolution, quadratic sensing, matrix completion, and robust PCA. Numerical experiments on these problems illustrate the benefits of the proposed approach.
Tasks	Matrix Completion
Published	2019-04-22
URL	http://arxiv.org/abs/1904.10020v1
PDF	http://arxiv.org/pdf/1904.10020v1.pdf
PWC	https://paperswithcode.com/paper/low-rank-matrix-recovery-with-composite
Repo
Framework

Open Cross-Domain Visual Search


Title	Open Cross-Domain Visual Search
Authors	William Thong, Pascal Mettes, Cees G. M. Snoek
Abstract	This paper introduces open cross-domain visual search, where categories in any target domain are retrieved based on queries from any source domain. Current works usually tackle cross-domain visual search as a domain adaptation problem. This limits the search to a closed setting, with one fixed source domain and one fixed target domain. To make the step towards an open setting where multiple visual domains are available, we introduce a simple yet effective approach. We formulate the search as one of mapping examples from every visual domain to a common semantic space, where categories are represented by hyperspherical prototypes. Cross-domain search is then performed by searching in the common space, regardless of which domains are used as source or target. Having separate mappings for every domain allows us to search in an open setting, and to incrementally add new domains over time without retraining existing mapping functions. Experimentally, we show our capability to perform open cross-domain visual search. Our approach is competitive with respect to traditional closed settings, where we obtain state-of-the-art results on six benchmarks for three sketch-based search tasks.
Tasks	Domain Adaptation
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08621v1
PDF	https://arxiv.org/pdf/1911.08621v1.pdf
PWC	https://paperswithcode.com/paper/open-cross-domain-visual-search
Repo
Framework

Online Learning with Continuous Variations: Dynamic Regret and Reductions


Title	Online Learning with Continuous Variations: Dynamic Regret and Reductions
Authors	Ching-An Cheng, Jonathan Lee, Ken Goldberg, Byron Boots
Abstract	Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called Continuous Online Learning (COL), where the gradient of online loss function changes continuously across rounds with respect to the learner’s decisions. We show that COL covers and more appropriately describes many interesting applications, from general equilibrium problems (EPs) to optimization in episodic MDPs. In particular, we show monotone EPs admits a reduction to achieving sublinear static regret in COL. Using this new setup, we revisit the difficulty of sublinear dynamic regret. We prove a fundamental equivalence between achieving sublinear dynamic regret in COL and solving certain EPs. With this insight, we offer conditions for efficient algorithms that achieve sublinear dynamic regret, even when the losses are chosen adaptively without any a priori variation budget. Furthermore, we show for COL a reduction from dynamic regret to both static regret and convergence in the associated EP, allowing us to analyze the dynamic regret of many existing algorithms.
Tasks
Published	2019-02-19
URL	https://arxiv.org/abs/1902.07286v2
PDF	https://arxiv.org/pdf/1902.07286v2.pdf
PWC	https://paperswithcode.com/paper/online-learning-with-continuous-variations
Repo
Framework

Composing Distributed Data-intensive Web Services Using a Flexible Memetic Algorithm


Title	Composing Distributed Data-intensive Web Services Using a Flexible Memetic Algorithm
Authors	Soheila Sadeghiram, Hui Ma, Gang Chen
Abstract	Web Service Composition (WSC) is a particularly promising application of Web services, where multiple individual services with specific functionalities are composed to accomplish a more complex task, which must fulfil functional requirements and optimise Quality of Service (QoS) attributes, simultaneously. Additionally, large quantities of data, produced by technological advances, need to be exchanged between services. Data-intensive Web services, which manipulate and deal with those data, are of great interest to implement data-intensive processes, such as distributed Data-intensive Web Service Composition (DWSC). Researchers have proposed Evolutionary Computing (EC) fully-automated WSC techniques that meet all the above factors. Some of these works employed Memetic Algorithms (MAs) to enhance the performance of EC through increasing its exploitation ability of in searching neighbourhood area of a solution. However, those works are not efficient or effective. This paper proposes an MA-based approach to solving the problem of distributed DWSC in an effective and efficient manner. In particular, we develop an MA that hybridises EC with a flexible local search technique incorporating distance of services. An evaluation using benchmark datasets is carried out, comparing existing state-of-the-art methods. Results show that our proposed method has the highest quality and an acceptable execution time overall.
Tasks
Published	2019-01-26
URL	http://arxiv.org/abs/1901.09894v1
PDF	http://arxiv.org/pdf/1901.09894v1.pdf
PWC	https://paperswithcode.com/paper/composing-distributed-data-intensive-web
Repo
Framework

Uncertainty-sensitive Learning and Planning with Ensembles


Title	Uncertainty-sensitive Learning and Planning with Ensembles
Authors	Piotr Miłoś, Łukasz Kuciński, Konrad Czechowski, Piotr Kozakowski, Maciek Klimek
Abstract	We propose a reinforcement learning framework for discrete environments in which an agent makes both strategic and tactical decisions. The former manifests itself through the use of value function, while the latter is powered by a tree search planner. These tools complement each other. The planning module performs a local \textit{what-if} analysis, which allows to avoid tactical pitfalls and boost backups of the value function. The value function, being global in nature, compensates for inherent locality of the planner. In order to further solidify this synergy, we introduce an exploration mechanism with two distinctive components: uncertainty modelling and risk measurement. To model the uncertainty we use value function ensembles, and to reflect risk we use propose several functionals that summarize the implied by the ensemble. We show that our method performs well on hard exploration environments: Deep-sea, toy Montezuma’s Revenge, and Sokoban. In all the cases, we obtain speed-up in learning and boost in performance.
Tasks	Montezuma’s Revenge
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09996v3
PDF	https://arxiv.org/pdf/1912.09996v3.pdf
PWC	https://paperswithcode.com/paper/uncertainty-sensitive-learning-and-planning-1
Repo
Framework

Neural Word Decomposition Models for Abusive Language Detection


Title	Neural Word Decomposition Models for Abusive Language Detection
Authors	Sravan Babu Bodapati, Spandana Gella, Kasturi Bhattacharjee, Yaser Al-Onaizan
Abstract	User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written differently compared to traditional text such as news involving either explicit mention of abusive words, obfuscated words and typological errors or implicit abuse i.e., indicating or targeting negative stereotypes. Thus, processing this text poses several robustness challenges when we apply natural language processing techniques developed for traditional text. For example, using word or token based models to process such text can treat two spelling variants of a word as two different words. Following recent work, we analyze how character, subword and byte pair encoding (BPE) models can be aid some of the challenges posed by user generated text. In our work, we analyze the effectiveness of each of the above techniques, compare and contrast various word decomposition techniques when used in combination with others. We experiment with finetuning large pretrained language models, and demonstrate their robustness to domain shift by studying Wikipedia attack, toxicity and Twitter hatespeech datasets
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01043v1
PDF	https://arxiv.org/pdf/1910.01043v1.pdf
PWC	https://paperswithcode.com/paper/neural-word-decomposition-models-for-abusive-1
Repo
Framework

Non-technical Loss Detection with Statistical Profile Images Based on Semi-supervised Learning


Title	Non-technical Loss Detection with Statistical Profile Images Based on Semi-supervised Learning
Authors	Jiangteng Li, Fei Wang
Abstract	In order to keep track of the operational state of power grid, the world’s largest sensor systems, smart grid, was built by deploying hundreds of millions of smart meters. Such system makes it possible to discover and make quick response to any hidden threat to the entire power grid. Non-technical losses (NTLs) have always been a major concern for its consequent security risks as well as immeasurable revenue loss. However, various causes of NTL may have different characteristics reflected in the data. Accurately capturing these anomalies faced with such large scale of collected data records is rather tricky as a result. In this paper, we proposed a new methodology of detecting abnormal electricity consumptions. We did a transformation of the collected time-series data which turns it into an image representation that could well reflect users’ relatively long term consumption behaviors. Inspired by the excellent neural network architecture used for objective detection in computer vision domain, we designed our deep learning model that takes the transformed images as input and yields joint featured inferred from the multiple aspects the input provides. Considering the limited labeled samples, especially the abnormal ones, we used our model in a semi-supervised fashion that is brought out in recent years. The model is tested on samples which are verified by on-field inspections and our method showed significant improvement.
Tasks	Time Series
Published	2019-07-09
URL	https://arxiv.org/abs/1907.03925v1
PDF	https://arxiv.org/pdf/1907.03925v1.pdf
PWC	https://paperswithcode.com/paper/non-technical-loss-detection-with-statistical
Repo
Framework

Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization


Title	Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization
Authors	Tian Xia, Agisilaos Chartsias, Sotirios A. Tsaftaris
Abstract	Pseudo healthy synthesis, i.e. the creation of a subject-specific `healthy’ image from a pathological one, could be helpful in tasks such as anomaly detection, understanding changes induced by pathology and disease or even as data augmentation. We treat this task as a factor decomposition problem: we aim to separate what appears to be healthy and where disease is (as a map). The two factors are then recombined (by a network) to reconstruct the input disease image. We train our models in an adversarial way using either paired or unpaired settings, where we pair disease images and maps (as segmentation masks) when available. We quantitatively evaluate the quality of pseudo healthy images. We show in a series of experiments, performed in ISLES and BraTS datasets, that our method is better than conditional GAN and CycleGAN, highlighting challenges in using adversarial methods in the image translation task of pseudo healthy image generation. \|
Tasks	Anomaly Detection, Data Augmentation, Image Generation
Published	2019-01-10
URL	http://arxiv.org/abs/1901.07295v1
PDF	http://arxiv.org/pdf/1901.07295v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-pseudo-healthy-synthesis-needs
Repo
Framework

Reinforcing an Image Caption Generator Using Off-Line Human Feedback


Title	Reinforcing an Image Caption Generator Using Off-Line Human Feedback
Authors	Paul Hongsuck Seo, Piyush Sharma, Tomer Levinboim, Bohyung Han, Radu Soricut
Abstract	Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset. In this paper, we show that the signal from instance-level human caption ratings can be leveraged to improve captioning models, even when the amount of caption ratings is several orders of magnitude less than the caption training data. We employ a policy gradient method to maximize the human ratings as rewards in an off-policy reinforcement learning setting, where policy gradients are estimated by samples from a distribution that focuses on the captions in a caption ratings dataset. Our empirical evidence indicates that the proposed method learns to generalize the human raters’ judgments to a previously unseen set of images, as judged by a different set of human judges, and additionally on a different, multi-dimensional side-by-side human evaluation procedure.
Tasks	Image Captioning
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09753v1
PDF	https://arxiv.org/pdf/1911.09753v1.pdf
PWC	https://paperswithcode.com/paper/reinforcing-an-image-caption-generator-using
Repo
Framework

A Deep Regression Model for Seed Identification in Prostate Brachytherapy


Title	A Deep Regression Model for Seed Identification in Prostate Brachytherapy
Authors	Yading Yuan, Ren-Dih Sheu, Luke Fu, Yeh-Chi Lo
Abstract	Post-implant dosimetry (PID) is an essential step of prostate brachytherapy that utilizes CT to image the prostate and allow the location and dose distribution of the radioactive seeds to be directly related to the actual prostate. However, it it a very challenging task to identify these seeds in CT images due to the severe metal artifacts and high-overlapped appearance when multiple seeds clustered together. In this paper, we propose an automatic and efficient algorithm based on 3D deep fully convolutional network for identifying implanted seeds in CT images. Our method models the seed localization task as a supervised regression problem that projects the input CT image to a map where each element represents the probability that the corresponding input voxel belongs to a seed. This deep regression model significantly suppresses image artifacts and makes the post-processing much easier and more controllable. The proposed method is validated on a large clinical database with 7820 seeds in 100 patients, in which 5534 seeds from 70 patients were used for model training and validation. Our method correctly detected 2150 of 2286 (94.1%) seeds in the 30 testing patients, yielding 16% improvement as compared to a widely-used commercial seed finder software (VariSeed, Varian, Palo Alto, CA).
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10183v1
PDF	https://arxiv.org/pdf/1906.10183v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-regression-model-for-seed
Repo
Framework

Fine-grained Object Semantic Understanding from Correspondences


Title	Fine-grained Object Semantic Understanding from Correspondences
Authors	Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu
Abstract	Fine-grained semantic understanding of 3D objects is crucial in many applications such as object manipulation. However, it is hard to give a universal definition of point-level semantics that everyone would agree on. We observe that people are pretty sure about semantic correspondences between two areas from different objects, but less certain about what each area means in semantics. Therefore, we argue that by providing human labeled correspondences between different objects from the same category, one can recover rich semantic information of an object. In this paper, we propose a method that outputs dense semantic embeddings based on a novel geodesic consistency loss. Accordingly, a new dataset named CorresPondenceNet and its corresponding benchmark are designed. Several state-of-the-art networks are evaluated based on our proposed method. We show that our method could boost the fine-grained understanding of heterogeneous objects and the inference of dense semantic information is possible.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12577v1
PDF	https://arxiv.org/pdf/1912.12577v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-object-semantic-understanding
Repo
Framework