Paper Group ANR 163
Proceedings of the 4th Workshop on Formal Reasoning about Causation, Responsibility, and Explanations in Science and Technology. Fast Neural Network Verification via Shadow Prices. Face Recognition System. Component Mismatches Are a Critical Bottleneck to Fielding AI-Enabled Systems in the Public Sector. Adversarial Examples for Electrocardiograms. …
Proceedings of the 4th Workshop on Formal Reasoning about Causation, Responsibility, and Explanations in Science and Technology
| Title | Proceedings of the 4th Workshop on Formal Reasoning about Causation, Responsibility, and Explanations in Science and Technology |
| Authors | Georgiana Caltais, Jean Krivine |
| Abstract | The fourth edition of the international workshop on Causation, Responsibility and Explanation took place in Prague (Czech Republic) as part of ETAPS 2019. The program consisted in 5 invited speakers and 4 regular papers, whose selection was based on a careful reviewing process and that are included in these proceedings. |
| Tasks | |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.13641v1 |
| https://arxiv.org/pdf/1910.13641v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-4th-workshop-on-formal |
| Repo | |
| Framework | |
Fast Neural Network Verification via Shadow Prices
| Title | Fast Neural Network Verification via Shadow Prices |
| Authors | Vicenc Rubies Royo, Roberto Calandra, Dusan M. Stipanovic, Claire Tomlin |
| Abstract | To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation. Recent work on ReLU networks has sought to verify whether inputs belonging to a bounded box can ever yield some undesirable output. Input-splitting procedures, a particular type of verification mechanism, do so by recursively partitioning the input set into smaller sets. The efficiency of these methods is largely determined by the number of splits the box must undergo before the property can be verified. In this work, we propose a new technique based on shadow prices that fully exploits the information of the problem yielding a more efficient generation of splits than the state-of-the-art. Results on the Airborne Collision Avoidance System (ACAS) benchmark verification tasks show a considerable reduction in the partitions generated which substantially reduces computation times. These results open the door to improved verification methods for a wide variety of machine learning applications including vision and control. |
| Tasks | |
| Published | 2019-02-19 |
| URL | http://arxiv.org/abs/1902.07247v2 |
| http://arxiv.org/pdf/1902.07247v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-neural-network-verification-via-shadow |
| Repo | |
| Framework | |
Face Recognition System
| Title | Face Recognition System |
| Authors | Yang Li, Sangwhan Cha |
| Abstract | Deep learning is one of the new and important branches in machine learning. Deep learning refers to a set of algorithms that solve various problems such as images and texts by using various machine learning algorithms in multi-layer neural networks. Deep learning can be classified as a neural network from the general category, but there are many changes in the concrete realization. At the core of deep learning is feature learning, which is designed to obtain hierarchical information through hierarchical networks, so as to solve the important problems that previously required artificial design features. Deep Learning is a framework that contains several important algorithms. For different applications (images, voice, text), you need to use different network models to achieve better results. With the development of deep learning and the introduction of deep convolutional neural networks, the accuracy and speed of face recognition have made great strides. However, as we said above, the results from different networks and models are very different. In this paper, facial features are extracted by merging and comparing multiple models, and then a deep neural network is constructed to train and construct the combined features. In this way, the advantages of multiple models can be combined to mention the recognition accuracy. After getting a model with high accuracy, we build a product model. This article compares the pure-client model with the server-client model, analyzes the pros and cons of the two models, and analyzes the various commercial products that are required for the server-client model. |
| Tasks | Face Recognition |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02452v1 |
| http://arxiv.org/pdf/1901.02452v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-recognition-system |
| Repo | |
| Framework | |
Component Mismatches Are a Critical Bottleneck to Fielding AI-Enabled Systems in the Public Sector
| Title | Component Mismatches Are a Critical Bottleneck to Fielding AI-Enabled Systems in the Public Sector |
| Authors | Grace A. Lewis, Stephany Bellomo, April Galyardt |
| Abstract | The use of machine learning or artificial intelligence (ML/AI) holds substantial potential toward improving many functions and needs of the public sector. In practice however, integrating ML/AI components into public sector applications is severely limited not only by the fragility of these components and their algorithms, but also because of mismatches between components of ML-enabled systems. For example, if an ML model is trained on data that is different from data in the operational environment, field performance of the ML component will be dramatically reduced. Separate from software engineering considerations, the expertise needed to field an ML/AI component within a system frequently comes from outside software engineering. As a result, assumptions and even descriptive language used by practitioners from these different disciplines can exacerbate other challenges to integrating ML/AI components into larger systems. We are investigating classes of mismatches in ML/AI systems integration, to identify the implicit assumptions made by practitioners in different fields (data scientists, software engineers, operations staff) and find ways to communicate the appropriate information explicitly. We will discuss a few categories of mismatch, and provide examples from each class. To enable ML/AI components to be fielded in a meaningful way, we will need to understand the mismatches that exist and develop practices to mitigate the impacts of these mismatches. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06136v1 |
| https://arxiv.org/pdf/1910.06136v1.pdf | |
| PWC | https://paperswithcode.com/paper/component-mismatches-are-a-critical |
| Repo | |
| Framework | |
Adversarial Examples for Electrocardiograms
| Title | Adversarial Examples for Electrocardiograms |
| Authors | Xintian Han, Yuxuan Hu, Luca Foschini, Larry Chinitz, Lior Jankelson, Rajesh Ranganath |
| Abstract | In recent years, the electrocardiogram (ECG) has seen a large diffusion in both medical and commercial applications, fueled by the rise of single-lead versions. Single-lead ECG can be embedded in medical devices and wearable products such as the injectable Medtronic Linq monitor, the iRhythm Ziopatch wearable monitor, and the Apple Watch Series 4. Recently, deep neural networks have been used to automatically analyze ECG tracings, outperforming even physicians specialized in cardiac electrophysiology in detecting certain rhythm irregularities. However, deep learning classifiers have been shown to be brittle to adversarial examples, which are examples created to look incontrovertibly belonging to a certain class to a human eye but contain subtle features that fool the classifier into misclassifying them into the wrong class. Very recently, adversarial examples have also been created for medical-related tasks. Yet, traditional attack methods to create adversarial examples, such as projected gradient descent (PGD) do not extend directly to ECG signals, as they generate examples that introduce square wave artifacts that are not physiologically plausible. Here, we developed a method to construct smoothed adversarial examples for single-lead ECG. First, we implemented a neural network model achieving state-of-the-art performance on the data from the 2017 PhysioNet/Computing-in-Cardiology Challenge for arrhythmia detection from single lead ECG classification. For this model, we utilized a new technique to generate smoothed examples to produce signals that are 1) indistinguishable to cardiologists from the original examples and 2) incorrectly classified by the neural network. Finally, we show that adversarial examples are not unique and provide a general technique to collate and perturb known adversarial examples to create new ones. |
| Tasks | Adversarial Defense, Arrhythmia Detection, ECG Classification, Electrocardiography (ECG) |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05163v2 |
| https://arxiv.org/pdf/1905.05163v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-examples-for-electrocardiograms |
| Repo | |
| Framework | |
ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation
| Title | ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation |
| Authors | Juraj Juraska, Kevin K. Bowden, Marilyn Walker |
| Abstract | The uptake of deep learning in natural language generation (NLG) led to the release of both small and relatively large parallel corpora for training neural models. The existing data-to-text datasets are, however, aimed at task-oriented dialogue systems, and often thus limited in diversity and versatility. They are typically crowdsourced, with much of the noise left in them. Moreover, current neural NLG models do not take full advantage of large training data, and due to their strong generalizing properties produce sentences that look template-like regardless. We therefore present a new corpus of 7K samples, which (1) is clean despite being crowdsourced, (2) has utterances of 9 generalizable and conversational dialogue act types, making it more suitable for open-domain dialogue systems, and (3) explores the domain of video games, which is new to dialogue systems despite having excellent potential for supporting rich conversations. |
| Tasks | Data-to-Text Generation, Task-Oriented Dialogue Systems, Text Generation |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12129v1 |
| https://arxiv.org/pdf/1910.12129v1.pdf | |
| PWC | https://paperswithcode.com/paper/viggo-a-video-game-corpus-for-data-to-text |
| Repo | |
| Framework | |
Ultra Low-Power and Real-time ECG Classification Based on STDP and R-STDP Neural Networks for Wearable Devices
| Title | Ultra Low-Power and Real-time ECG Classification Based on STDP and R-STDP Neural Networks for Wearable Devices |
| Authors | Alireza Amirshahi, Matin Hashemi |
| Abstract | This paper presents a novel ECG classification algorithm for real-time cardiac monitoring on ultra low-power wearable devices. The proposed solution is based on spiking neural networks which are the third generation of neural networks. In specific, we employ spike-timing dependent plasticity (STDP), and reward-modulated STDP (R-STDP), in which the model weights are trained according to the timings of spike signals, and reward or punishment signals. Experiments show that the proposed solution is suitable for real-time operation, achieves comparable accuracy with respect to previous methods, and more importantly, its energy consumption is significantly smaller than previous neural network based solutions. |
| Tasks | ECG Classification |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.02954v4 |
| https://arxiv.org/pdf/1905.02954v4.pdf | |
| PWC | https://paperswithcode.com/paper/ultra-low-power-and-real-time-ecg-1 |
| Repo | |
| Framework | |
Deep Time-Frequency Representation and Progressive Decision Fusion for ECG Classification
| Title | Deep Time-Frequency Representation and Progressive Decision Fusion for ECG Classification |
| Authors | Jing Zhang, Jing Tian, Yang Cao, Yuxiang Yang, Xiaobin Xu |
| Abstract | Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients’ cardiac conditions, increasing the success rate of the treatment. Classifying abnormal rhythms into exact categories is very challenging due to the broad taxonomy of rhythms, noises and lack of large-scale real-world annotated data. Different from previous methods that utilize hand-crafted features or learn features from the original signal domain, we propose a novel ECG classification method by learning deep time-frequency representation and progressive decision fusion at different temporal scales in an end-to-end manner. First, the ECG wave signal is transformed into the time-frequency domain by using the Short-Time Fourier Transform. Next, several scale-specific deep convolutional neural networks are trained on ECG samples of a specific length. Finally, a progressive online decision fusion method is proposed to fuse decisions from the scale-specific models into a more accurate and stable one. Extensive experiments on both synthetic and real-world ECG datasets demonstrate the effectiveness and efficiency of the proposed method. |
| Tasks | ECG Classification |
| Published | 2019-01-19 |
| URL | https://arxiv.org/abs/1901.06469v3 |
| https://arxiv.org/pdf/1901.06469v3.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-ecg-classification-based-on-deep |
| Repo | |
| Framework | |
Constant Time Graph Neural Networks
| Title | Constant Time Graph Neural Networks |
| Authors | Ryoma Sato, Makoto Yamada, Hisashi Kashima |
| Abstract | The recent advancements in graph neural networks (GNNs) have led to state-of-the-art performances in various applications, including chemo-informatics, question-answering systems, and recommender systems. However, scaling up these methods to huge graphs, such as social networks and Web graphs, remains a challenge. In particular, the existing methods for accelerating GNNs either are not theoretically guaranteed in terms of the approximation error or incur at least a linear time computation cost. In this study, we reveal the query complexity of the uniform node sampling scheme for Message Passing Neural Networks including GraphSAGE, graph attention networks (GATs), and graph convolutional networks (GCNs). Surprisingly, our analysis reveals that the complexity of the node sampling method is completely independent of the number of the nodes, edges, and neighbors of the input and depends only on the error tolerance and confidence probability while providing a theoretical guarantee for the approximation error. To the best of our knowledge, this is the first paper to provide a theoretical guarantee of approximation for GNNs within constant time. Through experiments with synthetic and real-world datasets, we investigated the speed and precision of the node sampling scheme and validated our theoretical results. |
| Tasks | Question Answering, Recommendation Systems |
| Published | 2019-01-23 |
| URL | https://arxiv.org/abs/1901.07868v3 |
| https://arxiv.org/pdf/1901.07868v3.pdf | |
| PWC | https://paperswithcode.com/paper/constant-time-graph-neural-networks |
| Repo | |
| Framework | |
Distributed representation of multi-sense words: A loss-driven approach
| Title | Distributed representation of multi-sense words: A loss-driven approach |
| Authors | Saurav Manchanda, George Karypis |
| Abstract | Word2Vec’s Skip Gram model is the current state-of-the-art approach for estimating the distributed representation of words. However, it assumes a single vector per word, which is not well-suited for representing words that have multiple senses. This work presents LDMI, a new model for estimating distributional representations of words. LDMI relies on the idea that, if a word carries multiple senses, then having a different representation for each of its senses should lead to a lower loss associated with predicting its co-occurring words, as opposed to the case when a single vector representation is used for all the senses. After identifying the multi-sense words, LDMI clusters the occurrences of these words to assign a sense to each occurrence. Experiments on the contextual word similarity task show that LDMI leads to better performance than competing approaches. |
| Tasks | |
| Published | 2019-04-14 |
| URL | http://arxiv.org/abs/1904.06725v1 |
| http://arxiv.org/pdf/1904.06725v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-representation-of-multi-sense |
| Repo | |
| Framework | |
Targeted Source Detection for Environmental Data
| Title | Targeted Source Detection for Environmental Data |
| Authors | Guanjie Zheng, Mengqi Liu, Tao Wen, Hongjian Wang, Huaxiu Yao, Susan L. Brantley, Zhenhui Li |
| Abstract | In the face of growing needs for water and energy, a fundamental understanding of the environmental impacts of human activities becomes critical for managing water and energy resources, remedying water pollution, and making regulatory policy wisely. Among activities that impact the environment, oil and gas production, wastewater transport, and urbanization are included. In addition to the occurrence of anthropogenic contamination, the presence of some contaminants (e.g., methane, salt, and sulfate) of natural origin is not uncommon. Therefore, scientists sometimes find it difficult to identify the sources of contaminants in the coupled natural and human systems. In this paper, we propose a technique to simultaneously conduct source detection and prediction, which outperforms other approaches in the interdisciplinary case study of the identification of potential groundwater contamination within a region of high-density shale gas development. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11056v1 |
| https://arxiv.org/pdf/1908.11056v1.pdf | |
| PWC | https://paperswithcode.com/paper/targeted-source-detection-for-environmental |
| Repo | |
| Framework | |
Numeric Solutions of Eigenvalue Problems for Generic Nonlinear Operators
| Title | Numeric Solutions of Eigenvalue Problems for Generic Nonlinear Operators |
| Authors | Ester Hait-Fraenkel, Guy Gilboa |
| Abstract | Numerical methods for solving linear eigenvalue problem are widely studiedand used in science and engineering. In this paper, we propose a generalizednumerical method for solving eigenproblems for generic, nonlinear opera-tors. This has potentially wide implications, since most image processingalgorithms (e.g. denoising) can be viewed as nonlinear operators, whoseeigenproblem analysis provides information on the most- and least-suitablefunctions as input. We solve the problem by a nonlinear adaptation of thepower method, a well known linear eigensolver. An analysis and valida-tion framework is proposed, as well as preliminary theory. We validate themethod using total-variation (TV) and demonstrate it on the EPLL denoiser(Zoran-Weiss). Finally, we suggest an encryption-decryption application. |
| Tasks | Denoising |
| Published | 2019-09-12 |
| URL | https://arxiv.org/abs/1909.12775v2 |
| https://arxiv.org/pdf/1909.12775v2.pdf | |
| PWC | https://paperswithcode.com/paper/numeric-solutions-of-eigenvalue-problems-for |
| Repo | |
| Framework | |
Let’s measure run time! Extending the IR replicability infrastructure to include performance aspects
| Title | Let’s measure run time! Extending the IR replicability infrastructure to include performance aspects |
| Authors | Sebastian Hofstätter, Allan Hanbury |
| Abstract | Establishing a docker-based replicability infrastructure offers the community a great opportunity: measuring the run time of information retrieval systems. The time required to present query results to a user is paramount to the users satisfaction. Recent advances in neural IR re-ranking models put the issue of query latency at the forefront. They bring a complex trade-off between performance and effectiveness based on a myriad of factors: the choice of encoding model, network architecture, hardware acceleration and many others. The best performing models (currently using the BERT transformer model) run orders of magnitude more slowly than simpler architectures. We aim to broaden the focus of the neural IR community to include performance considerations – to sustain the practical applicability of our innovations. In this position paper we supply our argument with a case study exploring the performance of different neural re-ranking models. Finally, we propose to extend the OSIRRC docker-based replicability infrastructure with two performance focused benchmark scenarios. |
| Tasks | Information Retrieval |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04614v1 |
| https://arxiv.org/pdf/1907.04614v1.pdf | |
| PWC | https://paperswithcode.com/paper/lets-measure-run-time-extending-the-ir |
| Repo | |
| Framework | |
Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays
| Title | Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays |
| Authors | N. Mert Vural, Hakan Gokcesu, Kaan Gokcesu, Suleyman S. Kozat |
| Abstract | We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching $m$-arm strategy with minimax optimal regret bounds. To construct our algorithm, we introduce a new expert advice algorithm for the multiple-play setting. By using our expert advice algorithm, we additionally improve the best-known high-probability bound for the multi-play setting by $O(\sqrt{m})$. Our results are guaranteed to hold in an individual sequence manner since we have no statistical assumption on the bandit arm gains. Through an extensive set of experiments involving synthetic and real data, we demonstrate significant performance gains achieved by the proposed algorithm with respect to the state-of-the-art algorithms. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11122v1 |
| https://arxiv.org/pdf/1911.11122v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-optimal-algorithms-for-adversarial |
| Repo | |
| Framework | |
On the Estimation and Use of Statistical Modelling in Information Retrieval
| Title | On the Estimation and Use of Statistical Modelling in Information Retrieval |
| Authors | Casper Petersen |
| Abstract | Several tasks in information retrieval (IR) rely on assumptions regarding the distribution of some property (such as term frequency) in the data being processed. This thesis argues that such distributional assumptions can lead to incorrect conclusions and proposes a statistically principled method for determining the “true” distribution. This thesis further applies this method to derive a new family of ranking models that adapt their computations to the statistics of the data being processed. Experimental evaluation shows results on par or better than multiple strong baselines on several TREC collections. Overall, this thesis concludes that distributional assumptions can be replaced with an effective, efficient and principled method for determining the “true” distribution and that using the “true” distribution can lead to improved retrieval performance. |
| Tasks | Information Retrieval |
| Published | 2019-03-30 |
| URL | http://arxiv.org/abs/1904.00289v1 |
| http://arxiv.org/pdf/1904.00289v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-estimation-and-use-of-statistical |
| Repo | |
| Framework | |
