Paper Group ANR 992
Exploring sentence informativeness. DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems. secml: A Python Library for Secure and Explainable Machine Learning. Extraction and Analysis of Clinically Important Follow-up Recommendations in a Large Radiology Dataset. Real-time Claim Detection from News Articles an …
Exploring sentence informativeness
| Title | Exploring sentence informativeness |
| Authors | Syrielle Montariol, Aina Garí Soler, Alexandre Allauzen |
| Abstract | This study is a preliminary exploration of the concept of informativeness -how much information a sentence gives about a word it contains- and its potential benefits to building quality word representations from scarce data. We propose several sentence-level classifiers to predict informativeness, and we perform a manual annotation on a set of sentences. We conclude that these two measures correspond to different notions of informativeness. However, our experiments show that using the classifiers’ predictions to train word embeddings has an impact on embedding quality. |
| Tasks | Word Embeddings |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08469v2 |
| https://arxiv.org/pdf/1907.08469v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-sentence-informativeness |
| Repo | |
| Framework | |
DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems
| Title | DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems |
| Authors | Adam Rupe, Nalini Kumar, Vladislav Epifanov, Karthik Kashinath, Oleksandr Pavlyk, Frank Schlimbach, Mostofa Patwary, Sergey Maidanov, Victor Lee, Prabhat, James P. Crutchfield |
| Abstract | Extracting actionable insight from complex unlabeled scientific data is an open challenge and key to unlocking data-driven discovery in science. Complementary and alternative to supervised machine learning approaches, unsupervised physics-based methods based on behavior-driven theories hold great promise. Due to computational limitations, practical application on real-world domain science problems has lagged far behind theoretical development. We present our first step towards bridging this divide - DisCo - a high-performance distributed workflow for the behavior-driven local causal state theory. DisCo provides a scalable unsupervised physics-based representation learning method that decomposes spatiotemporal systems into their structurally relevant components, which are captured by the latent local causal state variables. Complex spatiotemporal systems are generally highly structured and organize around a lower-dimensional skeleton of coherent structures, and in several firsts we demonstrate the efficacy of DisCo in capturing such structures from observational and simulated scientific data. To the best of our knowledge, DisCo is also the first application software developed entirely in Python to scale to over 1000 machine nodes, providing good performance along with ensuring domain scientists’ productivity. We developed scalable, performant methods optimized for Intel many-core processors that will be upstreamed to open-source Python library packages. Our capstone experiment, using newly developed DisCo workflow and libraries, performs unsupervised spacetime segmentation analysis of CAM5.1 climate simulation data, processing an unprecedented 89.5 TB in 6.6 minutes end-to-end using 1024 Intel Haswell nodes on the Cori supercomputer obtaining 91% weak-scaling and 64% strong-scaling efficiency. |
| Tasks | Representation Learning |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11822v1 |
| https://arxiv.org/pdf/1909.11822v1.pdf | |
| PWC | https://paperswithcode.com/paper/disco-physics-based-unsupervised-discovery-of |
| Repo | |
| Framework | |
secml: A Python Library for Secure and Explainable Machine Learning
| Title | secml: A Python Library for Secure and Explainable Machine Learning |
| Authors | Marco Melis, Ambra Demontis, Maura Pintor, Angelo Sotgiu, Battista Biggio |
| Abstract | We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including not only test-time evasion attacks to generate adversarial examples against deep neural networks, but also training-time poisoning attacks against support vector machines and many other algorithms. These attacks enable evaluating the security of learning algorithms and of the corresponding defenses under both white-box and black-box threat models. To this end, secml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. secml also includes explainability methods to help understand why adversarial attacks succeed against a given model, by visualizing the most influential features and training prototypes contributing to each decision. It is distributed under the Apache License 2.0, and hosted at https://gitlab.com/secml/secml. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.10013v1 |
| https://arxiv.org/pdf/1912.10013v1.pdf | |
| PWC | https://paperswithcode.com/paper/secml-a-python-library-for-secure-and |
| Repo | |
| Framework | |
Extraction and Analysis of Clinically Important Follow-up Recommendations in a Large Radiology Dataset
| Title | Extraction and Analysis of Clinically Important Follow-up Recommendations in a Large Radiology Dataset |
| Authors | Wilson Lau, Thomas H Payne, Ozlem Uzuner, Meliha Yetisgen |
| Abstract | Communication of follow-up recommendations when abnormalities are identified on imaging studies is prone to error. In this paper, we present a natural language processing approach based on deep learning to automatically identify clinically important recommendations in radiology reports. Our approach first identifies the recommendation sentences and then extracts reason, test, and time frame of the identified recommendations. To train our extraction models, we created a corpus of 567 radiology reports annotated for recommendation information. Our extraction models achieved 0.92 f-score for recommendation sentence, 0.65 f-score for reason, 0.73 f-score for test, and 0.84 f-score for time frame. We applied the extraction models to a set of over 3.3 million radiology reports and analyzed the adherence of follow-up recommendations. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05877v1 |
| https://arxiv.org/pdf/1905.05877v1.pdf | |
| PWC | https://paperswithcode.com/paper/extraction-and-analysis-of-clinically |
| Repo | |
| Framework | |
Real-time Claim Detection from News Articles and Retrieval of Semantically-Similar Factchecks
| Title | Real-time Claim Detection from News Articles and Retrieval of Semantically-Similar Factchecks |
| Authors | Ben Adler, Giacomo Bosciani-Gilroy |
| Abstract | Factchecking has always been a part of the journalistic process. However with newsroom budgets shrinking it is coming under increasing pressure just as the amount of false information circulating is on the rise. We therefore propose a method to increase the efficiency of the factchecking process, using the latest developments in Natural Language Processing (NLP). This method allows us to compare incoming claims to an existing corpus and return similar, factchecked, claims in a live system-allowing factcheckers to work simultaneously without duplicating their work. |
| Tasks | |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.02030v1 |
| https://arxiv.org/pdf/1907.02030v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-claim-detection-from-news-articles |
| Repo | |
| Framework | |
Latent Translation: Crossing Modalities by Bridging Generative Models
| Title | Latent Translation: Crossing Modalities by Bridging Generative Models |
| Authors | Yingtao Tian, Jesse Engel |
| Abstract | End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc interface between two existing models to solve a new task. Specifically, we take inspiration from neural machine translation, and cast the challenging problem of cross-modal domain transfer as unsupervised translation between the latent spaces of pretrained deep generative models. By abstracting away the data representation, we demonstrate that it is possible to transfer across different modalities (e.g., image-to-audio) and even different types of generative models (e.g., VAE-to-GAN). We compare to state-of-the-art techniques and find that a straight-forward variational autoencoder is able to best bridge the two generative models through learning a shared latent space. We can further impose supervised alignment of attributes in both domains with a classifier in the shared latent space. Through qualitative and quantitative evaluations, we demonstrate that locality and semantic alignment are preserved through the transfer process, as indicated by high transfer accuracies and smooth interpolations within a class. Finally, we show this modular structure speeds up training of new interface models by several orders of magnitude by decoupling it from expensive retraining of base generative models. |
| Tasks | Machine Translation |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08261v1 |
| http://arxiv.org/pdf/1902.08261v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-translation-crossing-modalities-by |
| Repo | |
| Framework | |
Membership Model Inversion Attacks for Deep Networks
| Title | Membership Model Inversion Attacks for Deep Networks |
| Authors | Samyadeep Basu, Rauf Izmailov, Chris Mesterharm |
| Abstract | With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of instancesused to train the targeted machine learning model. This so-called model inversionattack is based on sequential leveraging of classification scores towards obtaininghigh confidence representations for various classes. However, for deep networks,such procedures usually lead to unrecognizable representations that are uselessfor the adversary. In this paper, we introduce a more realistic definition of modelinversion, where the adversary is aware of the general purpose of the attackedmodel (for instance, whether it is an OCR system or a facial recognition system),and the goal is to find realistic class representations within the corresponding lower-dimensional manifold (of, respectively, general symbols or general faces). To thatend, we leverage properties of generative adversarial networks for constructinga connected lower-dimensional manifold, and demonstrate the efficiency of ourmodel inversion attack that is carried out within that manifold. |
| Tasks | Optical Character Recognition |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04257v1 |
| https://arxiv.org/pdf/1910.04257v1.pdf | |
| PWC | https://paperswithcode.com/paper/membership-model-inversion-attacks-for-deep |
| Repo | |
| Framework | |
Who said that?: Audio-visual speaker diarisation of real-world meetings
| Title | Who said that?: Audio-visual speaker diarisation of real-world meetings |
| Authors | Joon Son Chung, Bong-Jin Lee, Icksang Han |
| Abstract | The goal of this work is to determine ‘who spoke when’ in real-world meetings. The method takes surround-view video and single or multi-channel audio as inputs, and generates robust diarisation outputs. To achieve this, we propose a novel iterative approach that first enrolls speaker models using audio-visual correspondence, then uses the enrolled models together with the visual information to determine the active speaker. We show strong quantitative and qualitative performance on a dataset of real-world meetings. The method is also evaluated on the public AMI meeting corpus, on which we demonstrate results that exceed all comparable methods. We also show that beamforming can be used together with the video to further improve the performance when multi-channel audio is available. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10042v1 |
| https://arxiv.org/pdf/1906.10042v1.pdf | |
| PWC | https://paperswithcode.com/paper/who-said-that-audio-visual-speaker |
| Repo | |
| Framework | |
Fairness-enhancing interventions in stream classification
| Title | Fairness-enhancing interventions in stream classification |
| Authors | Vasileios Iosifidis, Thi Ngoc Han Tran, Eirini Ntoutsi |
| Abstract | The wide spread usage of automated data-driven decision support systems has raised a lot of concerns regarding accountability and fairness of the employed models in the absence of human supervision. Existing fairness-aware approaches tackle fairness as a batch learning problem and aim at learning a fair model which can then be applied to future instances of the problem. In many applications, however, the data comes sequentially and its characteristics might evolve with time. In such a setting, it is counter-intuitive to “fix” a (fair) model over the data stream as changes in the data might incur changes in the underlying model therefore, affecting its fairness. In this work, we propose fairness-enhancing interventions that modify the input data so that the outcome of any stream classifier applied to that data will be fair. Experiments on real and synthetic data show that our approach achieves good predictive performance and low discrimination scores over the course of the stream. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07223v1 |
| https://arxiv.org/pdf/1907.07223v1.pdf | |
| PWC | https://paperswithcode.com/paper/fairness-enhancing-interventions-in-stream |
| Repo | |
| Framework | |
Enabling real-time multi-messenger astrophysics discoveries with deep learning
| Title | Enabling real-time multi-messenger astrophysics discoveries with deep learning |
| Authors | E. A. Huerta, Gabrielle Allen, Igor Andreoni, Javier M. Antelis, Etienne Bachelet, Bruce Berriman, Federica Bianco, Rahul Biswas, Matias Carrasco, Kyle Chard, Minsik Cho, Philip S. Cowperthwaite, Zachariah B. Etienne, Maya Fishbach, Francisco Förster, Daniel George, Tom Gibbs, Matthew Graham, William Gropp, Robert Gruendl, Anushri Gupta, Roland Haas, Sarah Habib, Elise Jennings, Margaret W. G. Johnson, Erik Katsavounidis, Daniel S. Katz, Asad Khan, Volodymyr Kindratenko, William T. C. Kramer, Xin Liu, Ashish Mahabal, Zsuzsa Marka, Kenton McHenry, Jonah Miller, Claudia Moreno, Mark Neubauer, Steve Oberlin, Alexander R. Olivas, Donald Petravick, Adam Rebei, Shawn Rosofsky, Milton Ruiz, Aaron Saxton, Bernard F. Schutz, Alex Schwing, Ed Seidel, Stuart L. Shapiro, Hongyu Shen, Yue Shen, Leo Singer, Brigitta M. Sipőcz, Lunan Sun, John Towns, Antonios Tsokaros, Wei Wei, Jack Wells, Timothy J. Williams, Jinjun Xiong, Zhizhen Zhao |
| Abstract | Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and the need to build a community of experts to realize the goals of multi-messenger astrophysics. |
| Tasks | |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11779v1 |
| https://arxiv.org/pdf/1911.11779v1.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-real-time-multi-messenger |
| Repo | |
| Framework | |
Practical Bayesian Optimization with Threshold-Guided Marginal Likelihood Maximization
| Title | Practical Bayesian Optimization with Threshold-Guided Marginal Likelihood Maximization |
| Authors | Jungtaek Kim, Seungjin Choi |
| Abstract | We propose a practical Bayesian optimization method, of which the surrogate function is Gaussian process regression with threshold-guided marginal likelihood maximization. Because Bayesian optimization consumes much time in finding optimal free parameters of Gaussian process regression, mitigating a time complexity of this step is critical to speed up Bayesian optimization. For this reason, we propose a simple, but straightforward Bayesian optimization method, assuming a reasonable condition, which is observed in many practical examples. Our experimental results confirm that our method is effective to reduce the execution time. All implementations are available in our repository. |
| Tasks | |
| Published | 2019-05-18 |
| URL | https://arxiv.org/abs/1905.07540v1 |
| https://arxiv.org/pdf/1905.07540v1.pdf | |
| PWC | https://paperswithcode.com/paper/practical-bayesian-optimization-with |
| Repo | |
| Framework | |
Adabot: Fault-Tolerant Java Decompiler
| Title | Adabot: Fault-Tolerant Java Decompiler |
| Authors | Zhiming Li, Qing Wu, Kun Qian |
| Abstract | Reverse Engineering(RE) has been a fundamental task in software engineering. However, most of the traditional Java reverse engineering tools are strictly rule defined, thus are not fault-tolerant, which pose serious problem when noise and interference were introduced into the system. In this paper, we view reverse engineering as a statistical machine translation task instead of rule-based task, and propose a fault-tolerant Java decompiler based on machine translation models. Our model is based on attention-based Neural Machine Translation (NMT) and Transformer architectures. First, we measure the translation quality on both the redundant and purified datasets. Next, we evaluate the fault-tolerance(anti-noise ability) of our framework on test sets with different unit error probability (UEP). In addition, we compare the suitability of different word segmentation algorithms for decompilation task. Experimental results demonstrate that our model is more robust and fault-tolerant compared to traditional Abstract Syntax Tree (AST) based decompilers. Specifically, in terms of BLEU-4 and Word Error Rate (WER), our performance has reached 94.50% and 2.65% on the redundant test set; 92.30% and 3.48% on the purified test set. |
| Tasks | Machine Translation |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.06748v2 |
| https://arxiv.org/pdf/1908.06748v2.pdf | |
| PWC | https://paperswithcode.com/paper/adabot-fault-tolerant-java-decompiler |
| Repo | |
| Framework | |
Delineating Knowledge Domains in the Scientific Literature Using Visual Information
| Title | Delineating Knowledge Domains in the Scientific Literature Using Visual Information |
| Authors | Sean Yang, Po-shen Lee, Jevin D. West, Bill Howe |
| Abstract | Figures are an important channel for scientific communication, used to express complex ideas, models and data in ways that words cannot. However, this visual information is mostly ignored in analyses of the scientific literature. In this paper, we demonstrate the utility of using scientific figures as markers of knowledge domains in science, which can be used for classification, recommender systems, and studies of scientific information exchange. We encode sets of images into a visual signature, then use distances between these signatures to understand how patterns of visual communication compare with patterns of jargon and citation structures. We find that figures can be as effective for differentiating communities of practice as text or citation patterns. We then consider where these metrics disagree to understand how different disciplines use visualization to express ideas. Finally, we further consider how specific figure types propagate through the literature, suggesting a new mechanism for understanding the flow of ideas apart from conventional channels of text and citations. Our ultimate aim is to better leverage these information-dense objects to improve scientific communication across disciplinary boundaries. |
| Tasks | Recommendation Systems |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.07465v1 |
| https://arxiv.org/pdf/1908.07465v1.pdf | |
| PWC | https://paperswithcode.com/paper/delineating-knowledge-domains-in-the |
| Repo | |
| Framework | |
Generative Hybrid Representations for Activity Forecasting with No-Regret Learning
| Title | Generative Hybrid Representations for Activity Forecasting with No-Regret Learning |
| Authors | Jiaqi Guan, Ye Yuan, Kris M. Kitani, Nicholas Rhinehart |
| Abstract | Automatically reasoning about future human behaviors is a difficult problem with significant practical applications to assistive systems. Part of this difficulty stems from learning systems’ inability to represent all kinds of behaviors. Some behaviors, such as motion, are best described with continuous representations, whereas others, such as picking up a cup, are best described with discrete representations. Furthermore, human behavior is generally not fixed: people can change their habits and routines. This suggests these systems must be able to learn and adapt continuously. In this work, we develop an efficient deep generative model to jointly forecast a person’s future discrete actions and continuous motions. On a large-scale egocentric dataset, EPIC-KITCHENS, we observe our method generates high-quality and diverse samples while exhibiting better generalization than related generative models. Finally, we propose a variant to continually learn our model from streaming data, observe its practical effectiveness, and theoretically justify its learning efficiency. |
| Tasks | |
| Published | 2019-04-12 |
| URL | http://arxiv.org/abs/1904.06250v1 |
| http://arxiv.org/pdf/1904.06250v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-hybrid-representations-for |
| Repo | |
| Framework | |
Balancing Specialization, Generalization, and Compression for Detection and Tracking
| Title | Balancing Specialization, Generalization, and Compression for Detection and Tracking |
| Authors | Dotan Kaufman, Koby Bibas, Eran Borenstein, Michael Chertok, Tal Hassner |
| Abstract | We propose a method for specializing deep detectors and trackers to restricted settings. Our approach is designed with the following goals in mind: (a) Improving accuracy in restricted domains; (b) preventing overfitting to new domains and forgetting of generalized capabilities; (c) aggressive model compression and acceleration. To this end, we propose a novel loss that balances compression and acceleration of a deep learning model vs. loss of generalization capabilities. We apply our method to the existing tracker and detector models. We report detection results on the VIRAT and CAVIAR data sets. These results show our method to offer unprecedented compression rates along with improved detection. We apply our loss for tracker compression at test time, as it processes each video. Our tests on the OTB2015 benchmark show that applying compression during test time actually improves tracking performance. |
| Tasks | Model Compression |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11348v1 |
| https://arxiv.org/pdf/1909.11348v1.pdf | |
| PWC | https://paperswithcode.com/paper/balancing-specialization-generalization-and |
| Repo | |
| Framework | |
