January 26, 2020

3073 words 15 mins read

Paper Group ANR 1420

Reservoir Computing Models for Patient-Adaptable ECG Monitoring in Wearable Devices. Joint Detection and Location of English Puns. MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. On the Transferability of Spectral Graph Filters. Towards Understanding Chinese Checkers with Heuristics, Monte Carlo Tree Search, and Dee …

Reservoir Computing Models for Patient-Adaptable ECG Monitoring in Wearable Devices


Title	Reservoir Computing Models for Patient-Adaptable ECG Monitoring in Wearable Devices
Authors	Fatemeh Hadaeghi
Abstract	The reservoir computing paradigm is employed to classify heartbeat anomalies online based on electrocardiogram signals. Inspired by the principles of information processing in the brain, reservoir computing provides a framework to design, train, and analyze recurrent neural networks (RNNs) for processing time-dependent information. Due to its computational efficiency and the fact that training amounts to a simple linear regression, this supervised learning algorithm has been variously considered as a strategy to implement useful computations not only on digital computers but also on emerging unconventional hardware platforms such as neuromorphic microchips. Here, this biological-inspired learning framework is exploited to devise an accurate patient-adaptive model that has the potential to be integrated into wearable cardiac events monitoring devices. The proposed patient-customized model was trained and tested on ECG recordings selected from the MIT-BIH arrhythmia database. Restrictive inclusion criteria were used to conduct the study only on ECGs including, at least, two classes of heartbeats with highly unequal number of instances. The results of extensive simulations showed this model not only provides accurate, cheap and fast patient-customized heartbeat classifier but also circumvents the problem of “imbalanced classes” when the readout weights are trained using weighted ridge-regression.
Tasks	Arrhythmia Detection, ECG Classification, Electrocardiography (ECG)
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09504v1
PDF	https://arxiv.org/pdf/1907.09504v1.pdf
PWC	https://paperswithcode.com/paper/reservoir-computing-models-for-patient
Repo
Framework

Joint Detection and Location of English Puns


Title	Joint Detection and Location of English Puns
Authors	Yanyan Zou, Wei Lu
Abstract	A pun is a form of wordplay for an intended humorous or rhetorical effect, where a word suggests two or more meanings by exploiting polysemy (homographic pun) or phonological similarity to another word (heterographic pun). This paper presents an approach that addresses pun detection and pun location jointly from a sequence labeling perspective. We employ a new tagging scheme such that the model is capable of performing such a joint task, where useful structural information can be properly captured. We show that our proposed model is effective in handling both homographic and heterographic puns. Empirical results on the benchmark datasets demonstrate that our approach can achieve new state-of-the-art results.
Tasks
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00175v1
PDF	https://arxiv.org/pdf/1909.00175v1.pdf
PWC	https://paperswithcode.com/paper/joint-detection-and-location-of-english-puns-1
Repo
Framework

MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs


Title	MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs
Authors	Alistair E. W. Johnson, Tom J. Pollard, Nathaniel R. Greenbaum, Matthew P. Lungren, Chih-ying Deng, Yifan Peng, Zhiyong Lu, Roger G. Mark, Seth J. Berkowitz, Steven Horng
Abstract	Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient’s thorax, but requiring specialized training for proper interpretation. With the advent of high performance general purpose computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. However, a key challenge in the development of these techniques is the lack of sufficient data. Here we describe MIMIC-CXR-JPG v2.0.0, a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies sourced from the Beth Israel Deaconess Medical Center between 2011 - 2016. Images are provided with 14 labels derived from two natural language processing tools applied to the corresponding free-text radiology reports. MIMIC-CXR-JPG is derived entirely from the MIMIC-CXR database, and aims to provide a convenient processed version of MIMIC-CXR, as well as to provide a standard reference for data splits and image labels. All images have been de-identified to protect patient privacy. The dataset is made freely available to facilitate and encourage a wide range of research in medical computer vision.
Tasks
Published	2019-01-21
URL	https://arxiv.org/abs/1901.07042v5
PDF	https://arxiv.org/pdf/1901.07042v5.pdf
PWC	https://paperswithcode.com/paper/mimic-cxr-a-large-publicly-available-database
Repo
Framework

On the Transferability of Spectral Graph Filters


Title	On the Transferability of Spectral Graph Filters
Authors	Ron Levie, Elvin Isufi, Gitta Kutyniok
Abstract	This paper focuses on spectral filters on graphs, namely filters defined as elementwise multiplication in the frequency domain of a graph. In many graph signal processing settings, it is important to transfer a filter from one graph to another. One example is in graph convolutional neural networks (ConvNets), where the dataset consists of signals defined on many different graphs, and the learned filters should generalize to signals on new graphs, not present in the training set. A necessary condition for transferability (the ability to transfer filters) is stability. Namely, given a graph filter, if we add a small perturbation to the graph, then the filter on the perturbed graph is a small perturbation of the original filter. It is a common misconception that spectral filters are not stable, and this paper aims at debunking this mistake. We introduce a space of filters, called the Cayley smoothness space, that contains the filters of state-of-the-art spectral filtering methods, and whose filters can approximate any generic spectral filter. For filters in this space, the perturbation in the filter is bounded by a constant times the perturbation in the graph, and filters in the Cayley smoothness space are thus termed linearly stable. By combining stability with the known property of equivariance, we prove that graph spectral filters are transferable.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10524v1
PDF	http://arxiv.org/pdf/1901.10524v1.pdf
PWC	https://paperswithcode.com/paper/on-the-transferability-of-spectral-graph
Repo
Framework

Towards Understanding Chinese Checkers with Heuristics, Monte Carlo Tree Search, and Deep Reinforcement Learning


Title	Towards Understanding Chinese Checkers with Heuristics, Monte Carlo Tree Search, and Deep Reinforcement Learning
Authors	Ziyu Liu, Meng Zhou, Weiqing Cao, Qiang Qu, Henry Wing Fung Yeung, Vera Yuk Ying Chung
Abstract	The game of Chinese Checkers is a challenging traditional board game of perfect information that differs from other traditional games in two main aspects: first, unlike Chess, all checkers remain indefinitely in the game and hence the branching factor of the search tree does not decrease as the game progresses; second, unlike Go, there are also no upper bounds on the depth of the search tree since repetitions and backward movements are allowed. Therefore, even in a restricted game instance, the state-space of the game can still be unbounded, making it challenging for a computer program to excel. In this work, we present an approach that effectively combines the use of heuristics, Monte Carlo tree search, and deep reinforcement learning for building a Chinese Checkers agent without the use of any human game-play data. Experiment results show that our agent is competent under different scenarios and reaches the level of experienced human players.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01747v2
PDF	http://arxiv.org/pdf/1903.01747v2.pdf
PWC	https://paperswithcode.com/paper/towards-understanding-chinese-checkers-with
Repo
Framework

Advances and Open Problems in Federated Learning


Title	Advances and Open Problems in Federated Learning
Authors	Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D’Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
Abstract	Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.
Tasks
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04977v1
PDF	https://arxiv.org/pdf/1912.04977v1.pdf
PWC	https://paperswithcode.com/paper/advances-and-open-problems-in-federated
Repo
Framework

How Relevant is the Turing Test in the Age of Sophisbots?


Title	How Relevant is the Turing Test in the Age of Sophisbots?
Authors	Dan Boneh, Andrew J. Grotto, Patrick McDaniel, Nicolas Papernot
Abstract	Popular culture has contemplated societies of thinking machines for generations, envisioning futures from utopian to dystopian. These futures are, arguably, here now-we find ourselves at the doorstep of technology that can at least simulate the appearance of thinking, acting, and feeling. The real question is: now what?
Tasks
Published	2019-08-30
URL	https://arxiv.org/abs/1909.00056v1
PDF	https://arxiv.org/pdf/1909.00056v1.pdf
PWC	https://paperswithcode.com/paper/how-relevant-is-the-turing-test-in-the-age-of
Repo
Framework

Subspace Methods That Are Resistant to a Limited Number of Features Corrupted by an Adversary


Title	Subspace Methods That Are Resistant to a Limited Number of Features Corrupted by an Adversary
Authors	Chris Mesterharm, Rauf Izmailov, Scott Alexander, Simon Tsang
Abstract	In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any $l$ features in each instance and the adversary can change their values in any way. This noise is introduced on test instances and the algorithm receives no label feedback for these instances. We provide several subspace voting techniques that can be used to transform existing algorithms and prove data-dependent performance bounds in this setting. The key insight to our results is that we set our parameters so that a significant fraction of the voting hypotheses do not contain corrupt features and, for many real world problems, these uncorrupt hypotheses are sufficient to achieve high accuracy. We empirically validate our approach on several datasets including three new datasets that deal with side channel electromagnetic information.
Tasks
Published	2019-02-19
URL	https://arxiv.org/abs/1902.07280v2
PDF	https://arxiv.org/pdf/1902.07280v2.pdf
PWC	https://paperswithcode.com/paper/a-random-subspace-technique-that-is-resistant
Repo
Framework

Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm


Title	Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm
Authors	Andreas Stolcke
Abstract	Speaker diarization based on bottom-up clustering of speech segments by acoustic similarity is often highly sensitive to the choice of hyperparameters, such as the initial number of clusters and feature weighting. Optimizing these hyperparameters is difficult and often not robust across different data sets. We recently proposed the DOVER algorithm for combining multiple diarization hypotheses by voting. Here we propose to mitigate the robustness problem in diarization by using DOVER to average across different parameter choices. We also investigate the combination of diverse outputs obtained by following different merge choices pseudo-randomly in the course of clustering, thereby mitigating the greediness of best-first clustering. We show on two conference meeting data sets drawn from NIST evaluations that the proposed methods indeed yield more robust, and in several cases overall improved, results.
Tasks	Speaker Diarization
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11691v1
PDF	https://arxiv.org/pdf/1910.11691v1.pdf
PWC	https://paperswithcode.com/paper/improving-diarization-robustness-using
Repo
Framework


Title	Recommendation Systems for Tourism Based on Social Networks: A Survey
Authors	Alan Menk, Laura Sebastia, Rebeca Ferreira
Abstract	Nowadays, recommender systems are present in many daily activities such as online shopping, browsing social networks, etc. Given the rising demand for reinvigoration of the tourist industry through information technology, recommenders have been included into tourism websites such as Expedia, Booking or Tripadvisor, among others. Furthermore, the amount of scientific papers related to recommender systems for tourism is on solid and continuous growth since 2004. Much of this growth is due to social networks that, besides to offer researchers the possibility of using a great mass of available and constantly updated data, they also enable the recommendation systems to become more personalised, effective and natural. This paper reviews and analyses many research publications focusing on tourism recommender systems that use social networks in their projects. We detail their main characteristics, like which social networks are exploited, which data is extracted, the applied recommendation techniques, the methods of evaluation, etc. Through a comprehensive literature review, we aim to collaborate with the future recommender systems, by giving some clear classifications and descriptions of the current tourism recommender systems.
Tasks	Recommendation Systems
Published	2019-03-28
URL	http://arxiv.org/abs/1903.12099v1
PDF	http://arxiv.org/pdf/1903.12099v1.pdf
PWC	https://paperswithcode.com/paper/recommendation-systems-for-tourism-based-on
Repo
Framework

Pose-variant 3D Facial Attribute Generation


Title	Pose-variant 3D Facial Attribute Generation
Authors	Feng-Ju Chang, Xiang Yu, Ram Nevatia, Manmohan Chandraker
Abstract	We address the challenging problem of generating facial attributes using a single image in an unconstrained pose. In contrast to prior works that largely consider generation on 2D near-frontal images, we propose a GAN-based framework to generate attributes directly on a dense 3D representation given by UV texture and position maps, resulting in photorealistic, geometrically-consistent and identity-preserving outputs. Starting from a self-occluded UV texture map obtained by applying an off-the-shelf 3D reconstruction method, we propose two novel components. First, a texture completion generative adversarial network (TC-GAN) completes the partial UV texture map. Second, a 3D attribute generation GAN (3DA-GAN) synthesizes the target attribute while obtaining an appearance consistent with 3D face geometry and preserving identity. Extensive experiments on CelebA, LFW and IJB-A show that our method achieves consistently better attribute generation accuracy than prior methods, a higher degree of qualitative photorealism and preserves face identity information.
Tasks	3D Reconstruction
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10202v1
PDF	https://arxiv.org/pdf/1907.10202v1.pdf
PWC	https://paperswithcode.com/paper/pose-variant-3d-facial-attribute-generation
Repo
Framework

Active preference learning based on radial basis functions


Title	Active preference learning based on radial basis functions
Authors	Alberto Bemporad, Dario Piga
Abstract	This paper proposes a method for solving optimization problems in which the decision-maker cannot evaluate the objective function, but rather can only express a preference such as “this is better than that” between two candidate decision vectors. The algorithm described in this paper aims at reaching the global optimizer by iteratively proposing the decision maker a new comparison to make, based on actively learning a surrogate of the latent (unknown and perhaps unquantifiable) objective function from past sampled decision vectors and pairwise preferences. The surrogate is fit by means of radial basis functions, under the constraint of satisfying, if possible, the preferences expressed by the decision maker on existing samples. The surrogate is used to propose a new sample of the decision vector for comparison with the current best candidate based on two possible criteria: minimize a combination of the surrogate and an inverse weighting distance function to balance between exploitation of the surrogate and exploration of the decision space, or maximize a function related to the probability that the new candidate will be preferred. Compared to active preference learning based on Bayesian optimization, we show that our approach is superior in that, within the same number of comparisons, it approaches the global optimum more closely and is computationally lighter. MATLAB and a Python implementations of the algorithms described in the paper are available at http://cse.lab.imtlucca.it/~bemporad/idwgopt.
Tasks
Published	2019-09-28
URL	https://arxiv.org/abs/1909.13049v1
PDF	https://arxiv.org/pdf/1909.13049v1.pdf
PWC	https://paperswithcode.com/paper/active-preference-learning-based-on-radial
Repo
Framework

Differential Equation Units: Learning Functional Forms of Activation Functions from Data


Title	Differential Equation Units: Learning Functional Forms of Activation Functions from Data
Authors	MohamadAli Torkamani, Shiv Shankar, Amirmohammad Rooshenas, Phillip Wallis
Abstract	Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact network capable of achieving comparable, if not superior, performance when is compared to much larger networks.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03069v1
PDF	https://arxiv.org/pdf/1909.03069v1.pdf
PWC	https://paperswithcode.com/paper/differential-equation-units-learning
Repo
Framework

Why Can’t I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition


Title	Why Can’t I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
Authors	Jinwoo Choi, Chen Gao, Joseph C. E. Messou, Jia-Bin Huang
Abstract	Human activities often occur in specific scene contexts, e.g., playing basketball on a basketball court. Training a model using existing video datasets thus inevitably captures and leverages such bias (instead of using the actual discriminative cues). The learned representation may not generalize well to new action classes or different tasks. In this paper, we propose to mitigate scene bias for video representation learning. Specifically, we augment the standard cross-entropy loss for action classification with 1) an adversarial loss for scene types and 2) a human mask confusion loss for videos where the human actors are masked out. These two losses encourage learning representations that are unable to predict the scene types and the correct actions when there is no evidence. We validate the effectiveness of our method by transferring our pre-trained model to three different tasks, including action classification, temporal localization, and spatio-temporal action detection. Our results show consistent improvement over the baseline model without debiasing.
Tasks	Action Classification, Action Detection, Representation Learning, Temporal Localization
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05534v1
PDF	https://arxiv.org/pdf/1912.05534v1.pdf
PWC	https://paperswithcode.com/paper/why-cant-i-dance-in-the-mall-learning-to-1
Repo
Framework

QXplore: Q-learning Exploration by Maximizing Temporal Difference Error


Title	QXplore: Q-learning Exploration by Maximizing Temporal Difference Error
Authors	Riley Simmons-Edler, Ben Eisner, Daniel Yang, Anthony Bisulco, Eric Mitchell, Sebastian Seung, Daniel Lee
Abstract	A major challenge in reinforcement learning is exploration, especially when reward landscapes are sparse. Several recent methods provide an intrinsic motivation to explore by directly encouraging agents to seek novel states. A potential disadvantage of pure state novelty-seeking behavior is that unknown states are treated equally regardless of their potential for future reward. In this paper, we propose an exploration objective using the temporal difference error experienced on extrinsic rewards as a secondary reward signal for exploration in deep reinforcement learning. Our objective yields novelty-seeking in the absence of extrinsic reward, while accelerating exploration of reward-relevant states in sparse (but nonzero) reward landscapes. We implement the objective with a two-policy Q-learning method in which Q and Qx are the action-value functions for extrinsic and secondary rewards, respectively. Secondary reward is given by the absolute value of the TD-error of Q. Training is off-policy, based on a replay buffer containing a mix of trajectories sampled using Q and Qx. We characterize performance on a set of continuous control benchmark tasks, and demonstrate comparable or faster convergence on all tasks when compared with other state-of-the-art exploration methods.
Tasks	Continuous Control, Q-Learning
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08189v3
PDF	https://arxiv.org/pdf/1906.08189v3.pdf
PWC	https://paperswithcode.com/paper/qxplore-q-learning-exploration-by-maximizing
Repo
Framework