January 25, 2020

3247 words 16 mins read

Paper Group ANR 1674

Clinically Accurate Chest X-Ray Report Generation. Zero-Shot Action Recognition in Videos: A Survey. Fast Dimensional Analysis for Root Cause Investigation in a Large-Scale Service Environment. Combining No-regret and Q-learning. Bayesian Model Selection for Change Point Detection and Clustering. An Unethical Optimization Principle. Fine-Grained An …

Clinically Accurate Chest X-Ray Report Generation


Title	Clinically Accurate Chest X-Ray Report Generation
Authors	Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew McDermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, Marzyeh Ghassemi
Abstract	The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMIC-CXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.
Tasks	Text Generation
Published	2019-04-04
URL	https://arxiv.org/abs/1904.02633v2
PDF	https://arxiv.org/pdf/1904.02633v2.pdf
PWC	https://paperswithcode.com/paper/clinically-accurate-chest-x-ray-report
Repo
Framework

Zero-Shot Action Recognition in Videos: A Survey


Title	Zero-Shot Action Recognition in Videos: A Survey
Authors	Valter Luís Estevam Junior, Helio Pedrini, David Menotti
Abstract	Zero-Shot Action Recognition has attracted attention in the last years, and many approaches have been proposed for recognition of objects, events, and actions in images and videos. There is a demand for methods that can classify instances from classes that are not present in the training of models, especially in the complex task of automatic video understanding, since collecting, annotating, and labeling videos are difficult and laborious tasks. We identify that there are many methods available in the literature, however, it is difficult to categorize which techniques can be considered state of the art. Despite the existence of some surveys about zero-shot action recognition in still images and experimental protocol, there is no work focusing on videos. Hence, in this paper, we present a survey of the methods comprising techniques to perform visual feature extraction and semantic feature extraction as well to learn the mapping between these features considering specifically zero-shot action recognition in videos. We also provide a complete description of datasets, experiments, and protocols, presenting open issues and directions for future work essential for the development of the computer vision research field.
Tasks	Action Recognition In Still Images, Action Recognition In Videos, Temporal Action Localization, Video Understanding
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06423v1
PDF	https://arxiv.org/pdf/1909.06423v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-action-recognition-in-videos-a
Repo
Framework

Fast Dimensional Analysis for Root Cause Investigation in a Large-Scale Service Environment


Title	Fast Dimensional Analysis for Root Cause Investigation in a Large-Scale Service Environment
Authors	Fred Lin, Keyur Muzumdar, Nikolay Pavlovich Laptev, Mihai-Valentin Curelea, Seunghak Lee, Sriram Sankar
Abstract	Root cause analysis in a large-scale production environment is challenging due to the complexity of services running across global data centers. Due to the distributed nature of a large-scale system, the various hardware, software, and tooling logs are often maintained separately, making it difficult to review the logs jointly for understanding production issues. Another challenge in reviewing the logs for identifying issues is the scale - there could easily be millions of entities, each described by hundreds of features. In this paper we present a fast dimensional analysis framework that automates the root cause analysis on structured logs with improved scalability. We first explore item-sets, i.e. combinations of feature values, that could identify groups of samples with sufficient support for the target failures using the Apriori algorithm and a subsequent improvement, FP-Growth. These algorithms were designed for frequent item-set mining and association rule learning over transactional databases. After applying them on structured logs, we select the item-sets that are most unique to the target failures based on lift. We propose pre-processing steps with the use of a large-scale real-time database and post-processing techniques and parallelism to further speed up the analysis and improve interpretability, and demonstrate that such optimization is necessary for handling large-scale production datasets. We have successfully rolled out this approach for root cause investigation purposes in a large-scale infrastructure. We also present the setup and results from multiple production use cases in this paper.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.01225v2
PDF	https://arxiv.org/pdf/1911.01225v2.pdf
PWC	https://paperswithcode.com/paper/fast-dimensional-analysis-for-root-cause
Repo
Framework

Combining No-regret and Q-learning


Title	Combining No-regret and Q-learning
Authors	Ian A. Kash, Michael Sullins, Katja Hofmann
Abstract	Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall. We seek to understand how to relax these requirements. As a first step, we introduce a simple algorithm, local no-regret learning (LONR), which uses a Q-learning-like update rule to allow learning without terminal states or perfect recall. We prove its convergence for the basic case of MDPs (and limited extensions of them) and present empirical results showing that it achieves last iterate convergence in a number of settings, most notably NoSDE games, a class of Markov games specifically designed to be challenging to learn where no prior algorithm is known to achieve convergence to a stationary equilibrium even on average.
Tasks	Q-Learning
Published	2019-10-07
URL	https://arxiv.org/abs/1910.03094v2
PDF	https://arxiv.org/pdf/1910.03094v2.pdf
PWC	https://paperswithcode.com/paper/combining-no-regret-and-q-learning
Repo
Framework

Bayesian Model Selection for Change Point Detection and Clustering


Title	Bayesian Model Selection for Change Point Detection and Clustering
Authors	Othmane Mazhar, Cristian R. Rojas, Carlo Fischione, Mohammad R. Hesamzadeh
Abstract	We address the new problem of estimating a piece-wise constant signal with the purpose of detecting its change points and the levels of clusters. Our approach is to model it as a nonparametric penalized least square model selection on a family of models indexed over the collection of partitions of the design points and propose a computationally efficient algorithm to approximately solve it. Statistically, minimizing such a penalized criterion yields an approximation to the maximum a posteriori probability (MAP) estimator. The criterion is then analyzed and an oracle inequality is derived using a Gaussian concentration inequality. The oracle inequality is used to derive on one hand conditions for consistency and on the other hand an adaptive upper bound on the expected square risk of the estimator, which statistically motivates our approximation. Finally, we apply our algorithm to simulated data to experimentally validate the statistical guarantees and illustrate its behavior.
Tasks	Change Point Detection, Model Selection
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01308v1
PDF	https://arxiv.org/pdf/1912.01308v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-model-selection-for-change-point-1
Repo
Framework

An Unethical Optimization Principle


Title	An Unethical Optimization Principle
Authors	Nicholas Beale, Heather Battey, Anthony C. Davison, Robert S. MacKay
Abstract	If an artificial intelligence aims to maximise risk-adjusted return, then under mild conditions it is disproportionately likely to pick an unethical strategy unless the objective function allows sufficiently for this risk. Even if the proportion ${\eta}$ of available unethical strategies is small, the probability ${p_U}$ of picking an unethical strategy can become large; indeed unless returns are fat-tailed ${p_U}$ tends to unity as the strategy space becomes large. We define an Unethical Odds Ratio Upsilon (${\Upsilon}$) that allows us to calculate ${p_U}$ from ${\eta}$, and we derive a simple formula for the limit of ${\Upsilon}$ as the strategy space becomes large. We give an algorithm for estimating ${\Upsilon}$ and ${p_U}$ in finite cases and discuss how to deal with infinite strategy spaces. We show how this principle can be used to help detect unethical strategies and to estimate ${\eta}$. Finally we sketch some policy implications of this work.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05116v1
PDF	https://arxiv.org/pdf/1911.05116v1.pdf
PWC	https://paperswithcode.com/paper/an-unethical-optimization-principle
Repo
Framework

Fine-Grained Analysis of Propaganda in News Articles


Title	Fine-Grained Analysis of Propaganda in News Articles
Authors	Giovanni Da San Martino, Seunghak Yu, Alberto Barrón-Cedeño, Rostislav Petrov, Preslav Nakov
Abstract	Propaganda aims at influencing people’s mindset with the purpose of advancing a specific agenda. Previous work has addressed propaganda detection at the document level, typically labelling all articles from a propagandistic news outlet as propaganda. Such noisy gold labels inevitably affect the quality of any learning system trained on them. A further issue with most existing systems is the lack of explainability. To overcome these limitations, we propose a novel task: performing fine-grained analysis of texts by detecting all fragments that contain propaganda techniques as well as their type. In particular, we create a corpus of news articles manually annotated at the fragment level with eighteen propaganda techniques and we propose a suitable evaluation measure. We further design a novel multi-granularity neural network, and we show that it outperforms several strong BERT-based baselines.
Tasks
Published	2019-10-06
URL	https://arxiv.org/abs/1910.02517v1
PDF	https://arxiv.org/pdf/1910.02517v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-analysis-of-propaganda-in-news
Repo
Framework

Extracting Visual Knowledge from the Internet: Making Sense of Image Data


Title	Extracting Visual Knowledge from the Internet: Making Sense of Image Data
Authors	Yazhou Yao, Jian Zhang, Xiansheng Hua, Fumin Shen, Zhenmin Tang
Abstract	Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less attention has been paid to the third. Due to the high cost of manual labeling, the size of recent efforts such as ImageNet is still relatively small in respect to daily applications. In this work, we mainly focus on how to automatically generate identifying image data for a given visual concept on a vast scale. With the generated image data, we can train a robust recognition model for the given concept. We evaluate the proposed webly supervised approach on the benchmark Pascal VOC 2007 dataset and the results demonstrates the superiority of our proposed approach in image data collection.
Tasks	Representation Learning
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03219v1
PDF	https://arxiv.org/pdf/1906.03219v1.pdf
PWC	https://paperswithcode.com/paper/extracting-visual-knowledge-from-the-internet
Repo
Framework

What it Thinks is Important is Important: Robustness Transfers through Input Gradients


Title	What it Thinks is Important is Important: Robustness Transfers through Input Gradients
Authors	Alvin Chan, Yi Tay, Yew-Soon Ong
Abstract	Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations are previously found to be transferable across different tasks but this applies only if the model architecture for the source and target tasks is the same. Input gradients characterize how small changes at each input pixel affect the model output. Using only natural images, we show here that training a student model’s input gradients to match those of a robust teacher model can gain robustness close to a strong baseline that is robustly trained from scratch. Through experiments in MNIST, CIFAR-10, CIFAR-100 and Tiny-ImageNet, we show that our proposed method, input gradient adversarial matching, can transfer robustness across different tasks and even across different model architectures. This demonstrates that directly targeting the semantics of input gradients is a feasible way towards adversarial robustness.
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05699v2
PDF	https://arxiv.org/pdf/1912.05699v2.pdf
PWC	https://paperswithcode.com/paper/what-it-thinks-is-important-is-important
Repo
Framework

Cooperative Reasoning on Knowledge Graph and Corpus: A Multi-agentReinforcement Learning Approach


Title	Cooperative Reasoning on Knowledge Graph and Corpus: A Multi-agentReinforcement Learning Approach
Authors	Yunan Zhang, Xiang Cheng, Heting Gao, Chengxiang Zhai
Abstract	Knowledge-graph-based reasoning has drawn a lot of attention due to its interpretability. However, previous methods suffer from the incompleteness of the knowledge graph, namely the interested link or entity that can be missing in the knowledge graph(explicit missing). Also, most previous models assume the distance between the target and source entity is short, which is not true on a real-world KG like Freebase(implicit missing). The sensitivity to the incompleteness of KG and the incapability to capture the long-distance link between entities have limited the performance of these models on large KG. In this paper, we propose a model that leverages the text corpus to cure such limitations, either the explicit or implicit missing links. We model the question answering on KG as a cooperative task between two agents, a knowledge graph reasoning agent and an information extraction agent. Each agent learns its skill to complete its own task, hopping on KG or select knowledge from the corpus, via maximizing the reward for correctly answering the question. The reasoning agent decides how to find an equivalent path for the given entity and relation. The extraction agent provide shortcut for long-distance target entity or provide missing relations for explicit missing links with messages from the reasoning agent. Through such cooperative reward design, our model can augment the incomplete KG strategically while not introduce much unnecessary noise that could enlarge the search space and lower the performance.
Tasks	Question Answering
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02206v1
PDF	https://arxiv.org/pdf/1912.02206v1.pdf
PWC	https://paperswithcode.com/paper/cooperative-reasoning-on-knowledge-graph-and
Repo
Framework

INS: An Interactive Chinese News Synthesis System


Title	INS: An Interactive Chinese News Synthesis System
Authors	Hui Liu, Wentao Qin, Xiaojun Wan
Abstract	Nowadays, we are surrounded by more and more online news articles. Tens or hundreds of news articles need to be read if we wish to explore a hot news event or topic. So it is of vital importance to automatically synthesize a batch of news articles related to the event or topic into a new synthesis article (or overview article) for reader’s convenience. It is so challenging to make news synthesis fully automatic that there is no successful solution by now. In this paper, we put forward a novel Interactive News Synthesis system (i.e. INS), which can help generate news overview articles automatically or by interacting with users. More importantly, INS can serve as a tool for editors to help them finish their jobs. In our experiments, INS performs well on both topic representation and synthesis article generation. A user study also demonstrates the usefulness and users’ satisfaction with the INS tool. A demo video is available at \url{https://youtu.be/7ItteKW3GEk}.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10781v1
PDF	https://arxiv.org/pdf/1907.10781v1.pdf
PWC	https://paperswithcode.com/paper/ins-an-interactive-chinese-news-synthesis-1
Repo
Framework

Heuristic Strategies in Uncertain Approval Voting Environments


Title	Heuristic Strategies in Uncertain Approval Voting Environments
Authors	Jaelle Scheuerman, Jason L. Harman, Nicholas Mattei, K. Brent Venable
Abstract	In many collective decision making situations, agents vote to choose an alternative that best represents the preferences of the group. Agents may manipulate the vote to achieve a better outcome by voting in a way that does not reflect their true preferences. In real world voting scenarios, people often do not have complete information about other voter preferences and it can be computationally complex to identify a strategy that will maximize their expected utility. In such situations, it is often assumed that voters will vote truthfully rather than expending the effort to strategize. However, being truthful is just one possible heuristic that may be used. In this paper, we examine the effectiveness of heuristics in single winner and multi-winner approval voting scenarios with missing votes. In particular, we look at heuristics where a voter ignores information about other voting profiles and makes their decisions based solely on how much they like each candidate. In a behavioral experiment, we show that people vote truthfully in some situations and prioritize high utility candidates in others. We examine when these behaviors maximize expected utility and show how the structure of the voting environment affects both how well each heuristic performs and how humans employ these heuristics.
Tasks	Decision Making
Published	2019-11-29
URL	https://arxiv.org/abs/1912.00011v1
PDF	https://arxiv.org/pdf/1912.00011v1.pdf
PWC	https://paperswithcode.com/paper/heuristic-strategies-in-uncertain-approval
Repo
Framework

Unsupervised Inflection Generation Using Neural Language Modeling


Title	Unsupervised Inflection Generation Using Neural Language Modeling
Authors	Octavia-Maria Sulea, Steve Young
Abstract	The use of Deep Neural Network architectures for Language Modeling has recently seen a tremendous increase in interest in the field of NLP with the advent of transfer learning and the shift in focus from rule-based and predictive models (supervised learning) to generative or unsupervised models to solve the long-standing problems in NLP like Information Extraction or Question Answering. While this shift has worked greatly for languages lacking in inflectional morphology, such as English, challenges still arise when trying to build similar systems for morphologically-rich languages, since their individual words shift forms in context more often. In this paper we investigate the extent to which these new unsupervised or generative techniques can serve to alleviate the type-token ratio disparity in morphologically rich languages. We apply an off-the-shelf neural language modeling library to the newly introduced task of unsupervised inflection generation in the nominal domain of three morphologically rich languages: Romanian, German, and Finnish. We show that this neural language model architecture can successfully generate the full inflection table of nouns without needing any pre-training on large, wikipedia-sized corpora, as long as the model is shown enough inflection examples. In fact, our experiments show that pre-training hinders the generation performance.
Tasks	Language Modelling, Question Answering, Transfer Learning
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01156v1
PDF	https://arxiv.org/pdf/1912.01156v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-inflection-generation-using
Repo
Framework

Weights Adaptation Optimization of Heterogeneous Epidemic Spreading Networks: A Constrained Cooperative Coevolution Strategy


Title	Weights Adaptation Optimization of Heterogeneous Epidemic Spreading Networks: A Constrained Cooperative Coevolution Strategy
Authors	Yun Feng, Bing-Chuan Wang
Abstract	In this paper, the dynamic constrained optimization problem of weights adaptation for heterogeneous epidemic spreading networks is investigated. Due to the powerful ability of searching global optimum, evolutionary algorithms are employed as the optimizers. One major difficulty is that the dimension of the problem is increasing exponentially with the network size and most existing evolutionary algorithms cannot achieve satisfiable performance on large-scale optimization problems. To address this issue, a novel constrained cooperative coevolution ($C^3$) strategy, which can separate the original large-scale problem into different subcomponents, is employed to achieve the trade-off between the constraint and objective function.
Tasks
Published	2019-01-03
URL	https://arxiv.org/abs/1901.00602v2
PDF	https://arxiv.org/pdf/1901.00602v2.pdf
PWC	https://paperswithcode.com/paper/a-constrained-cooperative-coevolution
Repo
Framework

They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimization


Title	They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimization
Authors	Rayan Mosli, Matthew Wright, Bo Yuan, Yin Pan
Abstract	Machine learning models have been found to be susceptible to adversarial examples that are often indistinguishable from the original inputs. These adversarial examples are created by applying adversarial perturbations to input samples, which would cause them to be misclassified by the target models. Attacks that search and apply the perturbations to create adversarial examples are performed in both white-box and black-box settings, depending on the information available to the attacker about the target. For black-box attacks, the only capability available to the attacker is the ability to query the target with specially crafted inputs and observing the labels returned by the model. Current black-box attacks either have low success rates, requires a high number of queries, or produce adversarial examples that are easily distinguishable from their sources. In this paper, we present AdversarialPSO, a black-box attack that uses fewer queries to create adversarial examples with high success rates. AdversarialPSO is based on the evolutionary search algorithm Particle Swarm Optimization, a populationbased gradient-free optimization algorithm. It is flexible in balancing the number of queries submitted to the target vs the quality of imperceptible adversarial examples. The attack has been evaluated using the image classification benchmark datasets CIFAR-10, MNIST, and Imagenet, achieving success rates of 99.6%, 96.3%, and 82.0%, respectively, while submitting substantially fewer queries than the state-of-the-art. We also present a black-box method for isolating salient features used by models when making classifications. This method, called Swarms with Individual Search Spaces or SWISS, creates adversarial examples by finding and modifying the most important features in the input.
Tasks	Image Classification
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07490v1
PDF	https://arxiv.org/pdf/1909.07490v1.pdf
PWC	https://paperswithcode.com/paper/they-might-not-be-giants-crafting-black-box
Repo
Framework