April 3, 2020

3517 words 17 mins read

Paper Group AWR 9

Paper Group AWR 9

Blue River Controls: A toolkit for Reinforcement Learning Control Systems on Hardware. Seshat: A tool for managing and verifying annotation campaigns of audio data. S$^{2}$OMGAN: Shortcut from Remote Sensing Images to Online Maps. Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods. Artificial Benchmark for …

Blue River Controls: A toolkit for Reinforcement Learning Control Systems on Hardware

Title Blue River Controls: A toolkit for Reinforcement Learning Control Systems on Hardware
Authors Kirill Polzounov, Ramitha Sundar, Lee Redden
Abstract We provide a simple hardware wrapper around the Quanser’s hardware-in-the-loop software development kit (HIL SDK) to allow for easy development of new Quanser hardware. To connect to the hardware we use a module written in Cython. The internal QuanserWrapper class handles most of the difficult aspects of interacting with hardware, including the timing (using a hardware timer), and ensuring the data sent to hardware is safe and correct, where safety corresponds to safe operating voltage and current for the specified hardware. Much of the recent success of Reinforcement learning (RL) has been made possible with training and testing tools like OpenAI Gym and Deepmind Control Suite. Unfortunately, tools for quickly testing and transferring high-frequency RL algorithms from simulation to real hardware environment remain mostly absent. We present Blue River Controls, a tool that allows to train and test reinforcement learning algorithms on real-world hardware. It features a simple interface based on OpenAI Gym, that works directly on both simulation and hardware. We use Quanser’s Qube Servo2-USB platform, an underactuated rotary pendulum as an initial testing device. We also provide tools to simplify training RL algorithms on other hardware. Several baselines, from both classical controllers and pretrained RL agents are included to compare performance across tasks. Blue River Controls is available at this https URL: https://github.com/BlueRiverTech/quanser-openai-driver
Published 2020-01-07
URL https://arxiv.org/abs/2001.02254v1
PDF https://arxiv.org/pdf/2001.02254v1.pdf
PWC https://paperswithcode.com/paper/blue-river-controls-a-toolkit-for
Repo https://github.com/BlueRiverTech/quanser-openai-driver
Framework none

Seshat: A tool for managing and verifying annotation campaigns of audio data

Title Seshat: A tool for managing and verifying annotation campaigns of audio data
Authors Hadrien Titeux, Rachid Riad, Xuan-Nga Cao, Nicolas Hamilakis, Kris Madden, Alejandrina Cristia, Anne-Catherine Bachoud-Lévi, Emmanuel Dupoux
Abstract We introduce Seshat, a new, simple and open-source software to efficiently manage annotations of speech corpora. The Seshat software allows users to easily customise and manage annotations of large audio corpora while ensuring compliance with the formatting and naming conventions of the annotated output files. In addition, it includes procedures for checking the content of annotations following specific rules are implemented in personalised parsers. Finally, we propose a double-annotation mode, for which Seshat computes automatically an associated inter-annotator agreement with the $\gamma$ measure taking into account the categorisation and segmentation discrepancies.
Published 2020-03-03
URL https://arxiv.org/abs/2003.01472v1
PDF https://arxiv.org/pdf/2003.01472v1.pdf
PWC https://paperswithcode.com/paper/seshat-a-tool-for-managing-and-verifying
Repo https://github.com/bootphon/seshat
Framework none

S$^{2}$OMGAN: Shortcut from Remote Sensing Images to Online Maps

Title S$^{2}$OMGAN: Shortcut from Remote Sensing Images to Online Maps
Authors X. Chen, S. Chen, T. Xu, B. Yin, X. Mei, J. Peng, H. Li
Abstract Traditional online maps, widely used on Internet such as Google map and Baidu map, are rendered from vector data. Timely updating online maps from vector data, of which the generating is time-consuming, is a difficult mission. It is a shortcut to generate online maps in time from remote sensing images, which can be acquired timely without vector data. However, this mission used to be challenging or even impossible. Inspired by image-to-image translation (img2img) techniques based on generative adversarial network (GAN), we propose a semi-supervised structure-augmented online map GAN (S$^{2}$OMGAN) model to generate online maps directly from remote sensing images. In this model, we designed a semi-supervised learning strategy to pre-train S$^{2}$OMGAN on rich unpaired samples and finetune it on limited paired samples in reality. We also designed image gradient L1 loss and image gradient structure loss to generate an online map with global topological relationship and detailed edge curves of objects, which are important in cartography. Moreover, we propose edge structural similarity index (ESSI) as a metric to evaluate the quality of topological consistency between generated online maps and ground truths. Experimental results present that S$^{2}$OMGAN outperforms state-of-the-art (SOTA) works according to mean squared error, structural similarity index and ESSI. Also, S$^{2}$OMGAN wins more approval than SOTA in the human perceptual test on visual realism of cartography. Our work shows that S$^{2}$OMGAN is potentially a new paradigm to produce online maps. Our implementation of the S$^{2}$OMGAN is available at \url{https://github.com/imcsq/S2OMGAN}.
Tasks Image-to-Image Translation
Published 2020-01-21
URL https://arxiv.org/abs/2001.07712v1
PDF https://arxiv.org/pdf/2001.07712v1.pdf
PWC https://paperswithcode.com/paper/s2omgan-shortcut-from-remote-sensing-images
Repo https://github.com/imcsq/S2OMGAN
Framework pytorch

Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods

Title Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
Authors Daniel Otero Baguer, Johannes Leuschner, Maximilian Schmidt
Abstract In this work, we investigate the application of deep learning methods for computed tomography in the context of having a low-data regime. As motivation, we review some of the existing approaches and obtain quantitative results after training them with different amounts of data. We find that the learned primal-dual has an outstanding performance in terms of reconstruction quality and data efficiency. However, in general, end-to-end learned methods have two issues: a) lack of classical guarantees in inverse problems and b) lack of generalization when not trained with enough data. To overcome these issues, we bring in the deep image prior approach in combination with classical regularization. The proposed methods improve the state-of-the-art results in the low data-regime.
Published 2020-03-10
URL https://arxiv.org/abs/2003.04989v2
PDF https://arxiv.org/pdf/2003.04989v2.pdf
PWC https://paperswithcode.com/paper/computed-tomography-reconstruction-using-deep
Repo https://github.com/oterobaguer/dip-ct-benchmark
Framework none

Artificial Benchmark for Community Detection (ABCD): Fast Random Graph Model with Community Structure

Title Artificial Benchmark for Community Detection (ABCD): Fast Random Graph Model with Community Structure
Authors Bogumił Kamiński, Paweł Prałat, François Théberge
Abstract Most of the current complex networks that are of interest to practitioners possess a certain community structure that plays an important role in understanding the properties of these networks. Moreover, many machine learning algorithms and tools that are developed for complex networks try to take advantage of the existence of communities to improve their performance or speed. As a result, there are many competing algorithms for detecting communities in large networks. Unfortunately, these algorithms are often quite sensitive and so they cannot be fine-tuned for a given, but a constantly changing, real-world network at hand. It is therefore important to test these algorithms for various scenarios that can only be done using synthetic graphs that have built-in community structure, power-law degree distribution, and other typical properties observed in complex networks. The standard and extensively used method for generating artificial networks is the LFR graph generator. Unfortunately, this model has some scalability limitations and it is challenging to analyze it theoretically. Finally, the mixing parameter $\mu$, the main parameter of the model guiding the strength of the communities, has a non-obvious interpretation and so can lead to unnaturally-defined networks. In this paper, we provide an alternative random graph model with community structure and power-law distribution for both degrees and community sizes, the Artificial Benchmark for Community Detection (ABCD). We show that the new model solves the three issues identified above and more. The conclusion is that these models produce comparable graphs but ABCD is fast, simple, and can be easily tuned to allow the user to make a smooth transition between the two extremes: pure (independent) communities and random graph with no community structure.
Tasks Community Detection
Published 2020-01-14
URL https://arxiv.org/abs/2002.00843v1
PDF https://arxiv.org/pdf/2002.00843v1.pdf
PWC https://paperswithcode.com/paper/artificial-benchmark-for-community-detection
Repo https://github.com/bkamins/ABCDGraphGenerator.jl
Framework none

Hierarchical Generation of Molecular Graphs using Structural Motifs

Title Hierarchical Generation of Molecular Graphs using Structural Motifs
Authors Wengong Jin, Regina Barzilay, Tommi Jaakkola
Abstract Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.
Tasks Drug Discovery, Graph Generation
Published 2020-02-08
URL https://arxiv.org/abs/2002.03230v1
PDF https://arxiv.org/pdf/2002.03230v1.pdf
PWC https://paperswithcode.com/paper/hierarchical-generation-of-molecular-graphs
Repo https://github.com/wengong-jin/hgraph2graph
Framework pytorch

Automating App Review Response Generation

Title Automating App Review Response Generation
Authors Cuiyun Gao, Jichuan Zeng, Xin Xia, David Lo, Michael R. Lyu, Irwin King
Abstract Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app. For example, Hassan et al. found that responding to a review increases the chances of a user updating their given rating by up to six times compared to not responding. To alleviate the labor burden in replying to the bulk of user reviews, developers usually adopt a template-based strategy where the templates can express appreciation for using the app or mention the company email address for users to follow up. However, reading a large number of user reviews every day is not an easy task for developers. Thus, there is a need for more automation to help developers respond to user reviews. Addressing the aforementioned need, in this work we propose a novel approach RRGen that automatically generates review responses by learning knowledge relations between reviews and their responses. RRGen explicitly incorporates review attributes, such as user rating and review length, and learns the relations between reviews and corresponding responses in a supervised way from the available training data. Experiments on 58 apps and 309,246 review-response pairs highlight that RRGen outperforms the baselines by at least 67.4% in terms of BLEU-4 (an accuracy measure that is widely used to evaluate dialogue response generation systems). Qualitative analysis also confirms the effectiveness of RRGen in generating relevant and accurate responses.
Published 2020-02-10
URL https://arxiv.org/abs/2002.03552v1
PDF https://arxiv.org/pdf/2002.03552v1.pdf
PWC https://paperswithcode.com/paper/automating-app-review-response-generation
Repo https://github.com/ReMine-Lab/RRGen
Framework none

Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition

Title Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
Authors Xiaolei Huang, Linzi Xing, Franck Dernoncourt, Michael J. Paul
Abstract Existing research on fairness evaluation of document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes. In this work, we assemble and publish a multilingual Twitter corpus for the task of hate speech detection with inferred four author demographic factors: age, country, gender and race/ethnicity. The corpus covers five languages: English, Italian, Polish, Portuguese and Spanish. We evaluate the inferred demographic labels with a crowdsourcing platform, Figure Eight. To examine factors that can cause biases, we take an empirical analysis of demographic predictability on the English corpus. We measure the performance of four popular document classifiers and evaluate the fairness and bias of the baseline classifiers on the author-level demographic attributes.
Tasks Document Classification, Hate Speech Detection, Speech Recognition
Published 2020-02-24
URL https://arxiv.org/abs/2002.10361v2
PDF https://arxiv.org/pdf/2002.10361v2.pdf
PWC https://paperswithcode.com/paper/multilingual-twitter-corpus-and-baselines-for
Repo https://github.com/xiaoleihuang/Multilingual_Fairness_LREC
Framework pytorch

MLography: An Automated Quantitative Metallography Model for Impurities Anomaly Detection using Novel Data Mining and Deep Learning Approach

Title MLography: An Automated Quantitative Metallography Model for Impurities Anomaly Detection using Novel Data Mining and Deep Learning Approach
Authors Matan Rusanovsky, Gal Oren, Sigalit Ifergane, Ofer Beeri
Abstract The micro-structure of most of the engineering alloys contains some inclusions and precipitates, which may affect their properties, therefore it is crucial to characterize them. In this work we focus on the development of a state-of-the-art artificial intelligence model for Anomaly Detection named MLography to automatically quantify the degree of anomaly of impurities in alloys. For this purpose, we introduce several anomaly detection measures: Spatial, Shape and Area anomaly, that successfully detect the most anomalous objects based on their objective, given that the impurities were already labeled. The first two measures quantify the degree of anomaly of each object by how each object is distant and big compared to its neighborhood, and by the abnormally of its own shape respectively. The last measure, combines the former two and highlights the most anomalous regions among all input images, for later (physical) examination. The performance of the model is presented and analyzed based on few representative cases. We stress that although the models presented here were developed for metallography analysis, most of them can be generalized to a wider set of problems in which anomaly detection of geometrical objects is desired. All models as well as the data-set that was created for this work, are publicly available at: https://github.com/matanr/MLography.
Tasks Anomaly Detection
Published 2020-02-27
URL https://arxiv.org/abs/2003.04226v1
PDF https://arxiv.org/pdf/2003.04226v1.pdf
PWC https://paperswithcode.com/paper/mlography-an-automated-quantitative
Repo https://github.com/matanr/MLography
Framework none

Unsupervised Anomaly Detection for X-Ray Images

Title Unsupervised Anomaly Detection for X-Ray Images
Authors Diana Davletshina, Valentyn Melnychuk, Viet Tran, Hitansh Singla, Max Berrendorf, Evgeniy Faerman, Michael Fromm, Matthias Schubert
Abstract Obtaining labels for medical (image) data requires scarce and expensive experts. Moreover, due to ambiguous symptoms, single images rarely suffice to correctly diagnose a medical condition. Instead, it often requires to take additional background information such as the patient’s medical history or test results into account. Hence, instead of focusing on uninterpretable black-box systems delivering an uncertain final diagnosis in an end-to-end-fashion, we investigate how unsupervised methods trained on images without anomalies can be used to assist doctors in evaluating X-ray images of hands. Our method increases the efficiency of making a diagnosis and reduces the risk of missing important regions. Therefore, we adopt state-of-the-art approaches for unsupervised learning to detect anomalies and show how the outputs of these methods can be explained. To reduce the effect of noise, which often can be mistaken for an anomaly, we introduce a powerful preprocessing pipeline. We provide an extensive evaluation of different approaches and demonstrate empirically that even without labels it is possible to achieve satisfying results on a real-world dataset of X-ray images of hands. We also evaluate the importance of preprocessing and one of our main findings is that without it, most of our approaches perform not better than random. To foster reproducibility and accelerate research we make our code publicly available at https://github.com/Valentyn1997/xray
Tasks Anomaly Detection, Unsupervised Anomaly Detection
Published 2020-01-29
URL https://arxiv.org/abs/2001.10883v1
PDF https://arxiv.org/pdf/2001.10883v1.pdf
PWC https://paperswithcode.com/paper/unsupervised-anomaly-detection-for-x-ray
Repo https://github.com/Valentyn1997/xray
Framework pytorch

Deep learning achieves perfect anomaly detection on 108,308 retinal images including unlearned diseases

Title Deep learning achieves perfect anomaly detection on 108,308 retinal images including unlearned diseases
Authors Ayaka Suzuki, Yoshiro Suzuki
Abstract Optical coherence tomography (OCT) scanning is useful in detecting various retinal diseases. However, there are not enough ophthalmologists who can diagnose retinal OCT images in much of the world. To provide OCT screening inexpensively and extensively, an automated diagnosis system is indispensable. Although many machine learning techniques have been presented for assisting ophthalmologists in diagnosing retinal OCT images, there is no technique that can diagnose independently without relying on an ophthalmologist, i.e., there is no technique that does not overlook any anomaly, including unlearned diseases. As long as there is a risk of overlooking a disease with a technique, ophthalmologists must double-check even those images that the technique classifies as normal. Here, we show that our deep-learning-based binary classifier (normal or abnormal) achieved a perfect classification on 108,308 two-dimensional retinal OCT images, i.e., true positive rate = 1.000000 and true negative rate = 1.000000; hence, the area under the ROC curve = 1.0000000. Although the test set included three types of diseases, two of these were not used for training. However, all test images were correctly classified. Furthermore, we demonstrated that our scheme was able to cope with differences in patient race. No conventional approach has achieved the above performances. Our work has a sufficient possibility of raising automated diagnosis techniques for retinal OCT images from “assistant for ophthalmologists” to “independent diagnosis system without ophthalmologists”.
Tasks Anomaly Detection
Published 2020-01-13
URL https://arxiv.org/abs/2001.05859v3
PDF https://arxiv.org/pdf/2001.05859v3.pdf
PWC https://paperswithcode.com/paper/deep-learning-achieves-perfect-anomaly
Repo https://github.com/SAyaka0122/Deep-learning-based-binary-classifier
Framework tf

Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning

Title Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning
Authors Qian Long, Zihan Zhou, Abhibav Gupta, Fei Fang, Yi Wu, Xiaolong Wang
Abstract In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large. In this paper, we introduce Evolutionary Population Curriculum (EPC), a curriculum learning paradigm that scales up Multi-Agent Reinforcement Learning (MARL) by progressively increasing the population of training agents in a stage-wise manner. Furthermore, EPC uses an evolutionary approach to fix an objective misalignment issue throughout the curriculum: agents successfully trained in an early stage with a small population are not necessarily the best candidates for adapting to later stages with scaled populations. Concretely, EPC maintains multiple sets of agents in each stage, performs mix-and-match and fine-tuning over these sets and promotes the sets of agents with the best adaptability to the next stage. We implement EPC on a popular MARL algorithm, MADDPG, and empirically show that our approach consistently outperforms baselines by a large margin as the number of agents grows exponentially.
Tasks Multi-agent Reinforcement Learning
Published 2020-03-23
URL https://arxiv.org/abs/2003.10423v1
PDF https://arxiv.org/pdf/2003.10423v1.pdf
PWC https://paperswithcode.com/paper/evolutionary-population-curriculum-for-1
Repo https://github.com/qian18long/epciclr2020
Framework tf

Hierarchical Human Parsing with Typed Part-Relation Reasoning

Title Hierarchical Human Parsing with Typed Part-Relation Reasoning
Authors Wenguan Wang, Hailong Zhu, Jifeng Dai, Yanwei Pang, Jianbing Shen, Ling Shao
Abstract Human parsing is for pixel-wise human semantic understanding. As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task. Focusing on this, we seek to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures. In particular, we provide following two contributions. First, three kinds of part relations, i.e., decomposition, composition, and dependency, are, for the first time, completely and precisely described by three distinct relation networks. This is in stark contrast to previous parsers, which only focus on a portion of the relations and adopt a type-agnostic relation modeling strategy. More expressive relation information can be captured by explicitly imposing the parameters in the relation networks to satisfy the specific characteristics of different relations. Second, previous parsers largely ignore the need for an approximation algorithm over the loopy human hierarchy, while we instead address an iterative reasoning process, by assimilating generic message-passing networks with their edge-typed, convolutional counterparts. With these efforts, our parser lays the foundation for more sophisticated and flexible human relation patterns of reasoning. Comprehensive experiments on five datasets demonstrate that our parser sets a new state-of-the-art on each.
Tasks Human Parsing
Published 2020-03-10
URL https://arxiv.org/abs/2003.04845v2
PDF https://arxiv.org/pdf/2003.04845v2.pdf
PWC https://paperswithcode.com/paper/hierarchical-human-parsing-with-typed-part
Repo https://github.com/hlzhu09/Hierarchical-Human-Parsing
Framework none

Wasserstein Exponential Kernels

Title Wasserstein Exponential Kernels
Authors Henri De Plaen, Michaël Fanuel, Johan A. K. Suykens
Abstract In the context of kernel methods, the similarity between data points is encoded by the kernel function which is often defined thanks to the Euclidean distance, a common example being the squared exponential kernel. Recently, other distances relying on optimal transport theory - such as the Wasserstein distance between probability distributions - have shown their practical relevance for different machine learning techniques. In this paper, we study the use of exponential kernels defined thanks to the regularized Wasserstein distance and discuss their positive definiteness. More specifically, we define Wasserstein feature maps and illustrate their interest for supervised learning problems involving shapes and images. Empirically, Wasserstein squared exponential kernels are shown to yield smaller classification errors on small training sets of shapes, compared to analogous classifiers using Euclidean distances.
Published 2020-02-05
URL https://arxiv.org/abs/2002.01878v1
PDF https://arxiv.org/pdf/2002.01878v1.pdf
PWC https://paperswithcode.com/paper/wasserstein-exponential-kernels
Repo https://github.com/hdeplaen/Exponential_Wasserstein_Kernels
Framework none

Kalman meets Bellman: Improving Policy Evaluation through Value Tracking

Title Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
Authors Shirli Di-Castro Shashua, Shie Mannor
Abstract Policy evaluation is a key process in Reinforcement Learning (RL). It assesses a given policy by estimating the corresponding value function. When using parameterized value functions, common approaches minimize the sum of squared Bellman temporal-difference errors and receive a point-estimate for the parameters. Kalman-based and Gaussian-processes based frameworks were suggested to evaluate the policy by treating the value as a random variable. These frameworks can learn uncertainties over the value parameters and exploit them for policy exploration. When adopting these frameworks to solve deep RL tasks, several limitations are revealed: excessive computations in each optimization step, difficulty with handling batches of samples which slows training and the effect of memory in stochastic environments which prevents off-policy learning. In this work, we discuss these limitations and propose to overcome them by an alternative general framework, based on the extended Kalman filter. We devise an optimization method, called Kalman Optimization for Value Approximation (KOVA) that can be incorporated as a policy evaluation component in policy optimization algorithms. KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties. We analyze the properties of KOVA and present its performance on deep RL control tasks.
Tasks Gaussian Processes
Published 2020-02-17
URL https://arxiv.org/abs/2002.07171v1
PDF https://arxiv.org/pdf/2002.07171v1.pdf
PWC https://paperswithcode.com/paper/kalman-meets-bellman-improving-policy
Repo https://github.com/sdicastro/KOVA
Framework tf
comments powered by Disqus