January 30, 2020

3134 words 15 mins read

Paper Group ANR 257

Characterizing the Social Interactions in the Artificial Bee Colony Algorithm. A comparison of Deep Learning performances with other machine learning algorithms on credit scoring unbalanced data. What You See May Not Be What You Get: UCB Bandit Algorithms Robust to ε-Contamination. Distributed SGD Generalizes Well Under Asynchrony. Superposition as …


Title	Characterizing the Social Interactions in the Artificial Bee Colony Algorithm
Authors	Lydia Taw, Nishant Gurrapadi, Mariana Macedo, Marcos Oliveira, Diego Pinheiro, Carmelo Bastos-Filho, Ronaldo Menezes
Abstract	Computational swarm intelligence consists of multiple artificial simple agents exchanging information while exploring a search space. Despite a rich literature in the field, with works improving old approaches and proposing new ones, the mechanism by which complex behavior emerges in these systems is still not well understood. This literature gap hinders the researchers’ ability to deal with known problems in swarms intelligence such as premature convergence, and the balance of coordination and diversity among agents. Recent advances in the literature, however, have proposed to study these systems via the network that emerges from the social interactions within the swarm (i.e., the interaction network). In our work, we propose a definition of the interaction network for the Artificial Bee Colony (ABC) algorithm. With our approach, we captured striking idiosyncrasies of the algorithm. We uncovered the different patterns of social interactions that emerge from each type of bee, revealing the importance of the bees variations throughout the iterations of the algorithm. We found that ABC exhibits a dynamic information flow through the use of different bees but lacks continuous coordination between the agents.
Tasks
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04203v1
PDF	http://arxiv.org/pdf/1904.04203v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-the-social-interactions-in-the
Repo
Framework

A comparison of Deep Learning performances with other machine learning algorithms on credit scoring unbalanced data


Title	A comparison of Deep Learning performances with other machine learning algorithms on credit scoring unbalanced data
Authors	Louis Marceau, Lingling Qiu, Nick Vandewiele, Eric Charton
Abstract	Training models on highly unbalanced data is admitted to be a challenging task for machine learning algorithms. Current studies on deep learning mainly focus on data sets with balanced class labels or unbalanced data, but with massive amount of samples available, like in speech recognition. However, the capacities of deep learning on imbalanced data with little samples is not deeply investigated in literature, while it is a very common application context in numerous industries. To contribute to fill this gap, this paper compares the performances of several popular machine learning algorithms previously applied with success to unbalanced data set with deep learning algorithms. We conduct those experiments on a highly unbalanced data set, used for credit scoring. We evaluate various configuration including neural network optimization techniques and try to determine their capacities when they operate with imbalanced corpora.
Tasks	Speech Recognition
Published	2019-07-25
URL	https://arxiv.org/abs/1907.12363v2
PDF	https://arxiv.org/pdf/1907.12363v2.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-deep-learning-performances
Repo
Framework

What You See May Not Be What You Get: UCB Bandit Algorithms Robust to ε-Contamination


Title	What You See May Not Be What You Get: UCB Bandit Algorithms Robust to ε-Contamination
Authors	Laura Niss, Ambuj Tewari
Abstract	Motivated by applications of bandit algorithms in education, we consider a stochastic multi-armed bandit problem with $\varepsilon$-contaminated rewards. We allow an adversary to give arbitrary unbounded contaminated rewards with full knowledge of the past and future. We impose the constraint that for each time $t$ the proportion of contaminated rewards for any action is less than or equal to $\varepsilon$. We derive concentration inequalities for two robust mean estimators for sub-Gaussian distributions in the $\varepsilon$-contamination context. We define the $\varepsilon$-contaminated stochastic bandit problem and use our robust mean estimators to give two variants of a robust Upper Confidence Bound (UCB) algorithm, crUCB. Using regret derived from only the underlying stochastic rewards, both variants of crUCB achieve $\mathcal{O} (\sqrt{KT\log T})$. Our simulations are designed to reflect reasonable settings a teacher would experience when implementing a bandit algorithm. We show that in certain adversarial regimes crUCB not only outperforms algorithms designed for stochastic (UCB1) and adversarial bandits (EXP3) but also those that have “best of both worlds” guarantees (EXP3++ and TsallisInf) even when our constraint on the proportion of contaminated rewards is broken.
Tasks
Published	2019-10-12
URL	https://arxiv.org/abs/1910.05625v2
PDF	https://arxiv.org/pdf/1910.05625v2.pdf
PWC	https://paperswithcode.com/paper/what-you-see-may-not-be-what-you-get-ucb
Repo
Framework

Distributed SGD Generalizes Well Under Asynchrony


Title	Distributed SGD Generalizes Well Under Asynchrony
Authors	Jayanth Regatti, Gaurav Tendolkar, Yi Zhou, Abhishek Gupta, Yingbin Liang
Abstract	The performance of fully synchronized distributed systems has faced a bottleneck due to the big data trend, under which asynchronous distributed systems are becoming a major popularity due to their powerful scalability. In this paper, we study the generalization performance of stochastic gradient descent (SGD) on a distributed asynchronous system. The system consists of multiple worker machines that compute stochastic gradients which are further sent to and aggregated on a common parameter server to update the variables, and the communication in the system suffers from possible delays. Under the algorithm stability framework, we prove that distributed asynchronous SGD generalizes well given enough data samples in the training optimization. In particular, our results suggest to reduce the learning rate as we allow more asynchrony in the distributed system. Such adaptive learning rate strategy improves the stability of the distributed algorithm and reduces the corresponding generalization error. Then, we confirm our theoretical findings via numerical experiments.
Tasks
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13391v1
PDF	https://arxiv.org/pdf/1909.13391v1.pdf
PWC	https://paperswithcode.com/paper/distributed-sgd-generalizes-well-under
Repo
Framework

Superposition as Data Augmentation using LSTM and HMM in Small Training Sets


Title	Superposition as Data Augmentation using LSTM and HMM in Small Training Sets
Authors	Akilesh Sivaswamy, Evgeny Pavlovskiy
Abstract	Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition augmentation and compared with plain default training and mix-up augmentation. This augmentation technique originates from the mix-up approach but provides more solid theoretical reasoning based on quantum properties. We achieved 3% improvement (from 68% to 71%) by using 38% lesser number of training samples in Russian audio-digits recognition task and 7,16% better accuracy than mix-up augmentation by training only 500 samples using HMM on the same task. Also, we achieved 1.1% better accuracy than mix-up on first 900 samples in MNIST using 3-layer stacked LSTM.
Tasks	Data Augmentation
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10881v1
PDF	https://arxiv.org/pdf/1910.10881v1.pdf
PWC	https://paperswithcode.com/paper/superposition-as-data-augmentation-using-lstm
Repo
Framework

Explaining intuitive difficulty judgments by modeling physical effort and risk


Title	Explaining intuitive difficulty judgments by modeling physical effort and risk
Authors	Ilker Yildirim, Basil Saeed, Grace Bennett-Pierre, Tobias Gerstenberg, Joshua Tenenbaum, Hyowon Gweon
Abstract	The ability to estimate task difficulty is critical for many real-world decisions such as setting appropriate goals for ourselves or appreciating others’ accomplishments. Here we give a computational account of how humans judge the difficulty of a range of physical construction tasks (e.g., moving 10 loose blocks from their initial configuration to their target configuration, such as a vertical tower) by quantifying two key factors that influence construction difficulty: physical effort and physical risk. Physical effort captures the minimal work needed to transport all objects to their final positions, and is computed using a hybrid task-and-motion planner. Physical risk corresponds to stability of the structure, and is computed using noisy physics simulations to capture the costs for precision (e.g., attention, coordination, fine motor movements) required for success. We show that the full effort-risk model captures human estimates of difficulty and construction time better than either component alone.
Tasks
Published	2019-05-11
URL	https://arxiv.org/abs/1905.04445v2
PDF	https://arxiv.org/pdf/1905.04445v2.pdf
PWC	https://paperswithcode.com/paper/explaining-intuitive-difficulty-judgments-by
Repo
Framework

Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World


Title	Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World
Authors	Julianna D. Ianni, Rajath E. Soans, Sivaramakrishnan Sankarapandian, Ramachandra Vikas Chamarthi, Devi Ayyagari, Thomas G. Olsen, Michael J. Bonham, Coleman C. Stavish, Kiran Motaparthi, Clay J. Cockerell, Theresa A. Feeser, Jason B. Lee
Abstract	Standard of care diagnostic procedure for suspected skin cancer is microscopic examination of hematoxylin & eosin stained tissue by a pathologist. Areas of high inter-pathologist discordance and rising biopsy rates necessitate higher efficiency and diagnostic reproducibility. We present and validate a deep learning system which classifies digitized dermatopathology slides into 4 categories. The system is developed using 5,070 images from a single lab, and tested on an uncurated set of 13,537 images from 3 test labs, using whole slide scanners manufactured by 3 different vendors. The system’s use of deep-learning-based confidence scoring as a criterion to consider the result as accurate yields an accuracy of up to 98%, and makes it adoptable in a real-world setting. Without confidence scoring, the system achieved an accuracy of 78%. We anticipate that our deep learning system will serve as a foundation enabling faster diagnosis of skin cancer, identification of cases for specialist review, and targeted diagnostic classifications.
Tasks	Image Classification
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11212v1
PDF	https://arxiv.org/pdf/1909.11212v1.pdf
PWC	https://paperswithcode.com/paper/augmenting-the-pathology-lab-an-intelligent
Repo
Framework

Recovery of a mixture of Gaussians by sum-of-norms clustering


Title	Recovery of a mixture of Gaussians by sum-of-norms clustering
Authors	Tao Jiang, Stephen Vavasis, Chen Wen Zhai
Abstract	Sum-of-norms clustering is a method for assigning $n$ points in $\mathbb{R}^d$ to $K$ clusters, $1\le K\le n$, using convex optimization. Recently, Panahi et al.\ proved that sum-of-norms clustering is guaranteed to recover a mixture of Gaussians under the restriction that the number of samples is not too large. The purpose of this note is to lift this restriction, i.e., show that sum-of-norms clustering with equal weights can recover a mixture of Gaussians even as the number of samples tends to infinity. Our proof relies on an interesting characterization of clusters computed by sum-of-norms clustering that was developed inside a proof of the agglomeration conjecture by Chiquet et al. Because we believe this theorem has independent interest, we restate and reprove the Chiquet et al.\ result herein.
Tasks
Published	2019-02-19
URL	http://arxiv.org/abs/1902.07137v1
PDF	http://arxiv.org/pdf/1902.07137v1.pdf
PWC	https://paperswithcode.com/paper/recovery-of-a-mixture-of-gaussians-by-sum-of
Repo
Framework

This Car is Mine!: Automobile Theft Countermeasure Leveraging Driver Identification with Generative Adversarial Networks


Title	This Car is Mine!: Automobile Theft Countermeasure Leveraging Driver Identification with Generative Adversarial Networks
Authors	Kyung Ho Park, Huy Kang Kim
Abstract	As a car becomes more connected, a countermeasure against automobile theft has become a significant task in the real world. To respond to automobile theft, data mining, biometrics, and additional authentication methods are proposed. Among current countermeasures, data mining method is one of the efficient ways to capture the owner driver’s unique characteristics. To identify the owner driver from thieves, previous works applied various algorithms toward driving data. Such data mining methods utilized supervised learning, thus required labeled data set. However, it is unrealistic to gather and apply the thief’s driving pattern. To overcome this problem, we propose driver identification method with GAN. GAN has merit to build identification model by learning the owner driver’s data only. We trained GAN only with owner driver’s data and used trained discriminator to identify the owner driver. From actual driving data, we evaluated our identification model recognizes the owner driver well. By ensembling various driver authentication methods with the proposed model, we expect industry can develop automobile theft countermeasures available in the real world.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09870v1
PDF	https://arxiv.org/pdf/1911.09870v1.pdf
PWC	https://paperswithcode.com/paper/this-car-is-mine-automobile-theft
Repo
Framework

Continuous Graph Neural Networks


Title	Continuous Graph Neural Networks
Authors	Louis-Pascal A. C. Xhonneux, Meng Qu, Jian Tang
Abstract	This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current node representations, the representations of neighbors, and the initial values of the nodes. We propose and analyse two possible dynamics on graphs—including each dimension of node representations (a.k.a. the feature channel) change independently or interact with each other—both with theoretical justification. The proposed continuous graph neural networks are robust to over-smoothing and hence allow us to build deeper networks, which in turn are able to capture the long-range dependencies between nodes. Experimental results on the task of node classification demonstrate the effectiveness of our proposed approach over competitive baselines.
Tasks	Node Classification
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00967v2
PDF	https://arxiv.org/pdf/1912.00967v2.pdf
PWC	https://paperswithcode.com/paper/continuous-graph-neural-networks
Repo
Framework

Performance Evaluation Methodology for Long-Term Visual Object Tracking


Title	Performance Evaluation Methodology for Long-Term Visual Object Tracking
Authors	Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan
Abstract	A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures outperform existing ones in interpretation potential and in better distinguishing between different tracking behaviors. We show that these measures generalize the short-term performance measures, thus linking the two tracking problems. Furthermore, the new measures are highly robust to temporal annotation sparsity and allow annotation of sequences hundreds of times longer than in the current datasets without increasing manual annotation labor. A new challenging dataset of carefully selected sequences with many target disappearances is proposed. A new tracking taxonomy is proposed to position trackers on the short-term/long-term spectrum. The benchmark contains an extensive evaluation of the largest number of long-term tackers and comparison to state-of-the-art short-term trackers. We analyze the influence of tracking architecture implementations to long-term performance and explore various re-detection strategies as well as influence of visual model update strategies to long-term tracking drift. The methodology is integrated in the VOT toolkit to automate experimental analysis and benchmarking and to facilitate future development of long-term trackers.
Tasks	Object Tracking, Visual Object Tracking
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08675v1
PDF	https://arxiv.org/pdf/1906.08675v1.pdf
PWC	https://paperswithcode.com/paper/performance-evaluation-methodology-for-long
Repo
Framework

Robust and Fast Automatic Modulation Classification with CNN under Multipath Fading Channels


Title	Robust and Fast Automatic Modulation Classification with CNN under Multipath Fading Channels
Authors	Kürşat Tekbıyık, Ali Rıza Ekti, Ali Görçin, Güneş Karabulut Kurt, Cihat Keçeci
Abstract	Automatic modulation classification (AMC) has been studied for more than a quarter of a century; however, it has been difficult to design a classifier that operates successfully under changing multipath fading conditions and other impairments. Recently, deep learning (DL)-based methods are adopted by AMC systems and major improvements are reported. In this paper, a novel convolutional neural network (CNN) classifier model is proposed to classify modulation classes in terms of their families, i.e., types. The proposed classifier is robust against realistic wireless channel impairments and in relation to that when the data sets that are utilized for testing and evaluating the proposed methods are considered, it is seen that RadioML2016.10a is the main dataset utilized for testing and evaluation of the proposed methods. However, the channel effects incorporated in this dataset and some others may lack the appropriate modeling of the real-world conditions since it only considers two distributions for channel models for a single tap configuration. Therefore, in this paper, a more comprehensive dataset, named as HisarMod2019.1, is also introduced, considering real-life applicability. HisarMod2019.1 includes 26 modulation classes passing through the channels with 5 different fading types and several numbers of taps for classification. It is shown that the proposed model performs better than the existing models in terms of both accuracy and training time under more realistic conditions. Even more, surpassed their performance when the RadioML2016.10a dataset is utilized.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04970v2
PDF	https://arxiv.org/pdf/1911.04970v2.pdf
PWC	https://paperswithcode.com/paper/robust-and-fast-automatic-modulation
Repo
Framework

Self-imitating Feedback Generation Using GAN for Computer-Assisted Pronunciation Training


Title	Self-imitating Feedback Generation Using GAN for Computer-Assisted Pronunciation Training
Authors	Seung Hee Yang, Minhwa Chung
Abstract	Self-imitating feedback is an effective and learner-friendly method for non-native learners in Computer-Assisted Pronunciation Training. Acoustic characteristics in native utterances are extracted and transplanted onto learner’s own speech input, and given back to the learner as a corrective feedback. Previous works focused on speech conversion using prosodic transplantation techniques based on PSOLA algorithm. Motivated by the visual differences found in spectrograms of native and non-native speeches, we investigated applying GAN to generate self-imitating feedback by utilizing generator’s ability through adversarial training. Because this mapping is highly under-constrained, we also adopt cycle consistency loss to encourage the output to preserve the global structure, which is shared by native and non-native utterances. Trained on 97,200 spectrogram images of short utterances produced by native and non-native speakers of Korean, the generator is able to successfully transform the non-native spectrogram input to a spectrogram with properties of self-imitating feedback. Furthermore, the transformed spectrogram shows segmental corrections that cannot be obtained by prosodic transplantation. Perceptual test comparing the self-imitating and correcting abilities of our method with the baseline PSOLA method shows that the generative approach with cycle consistency loss is promising.
Tasks
Published	2019-04-20
URL	http://arxiv.org/abs/1904.09407v1
PDF	http://arxiv.org/pdf/1904.09407v1.pdf
PWC	https://paperswithcode.com/paper/190409407
Repo
Framework

UBC-NLP at SemEval-2019 Task 6:Ensemble Learning of Offensive Content With Enhanced Training Data


Title	UBC-NLP at SemEval-2019 Task 6:Ensemble Learning of Offensive Content With Enhanced Training Data
Authors	Arun Rajendran, Chiyu Zhang, Muhammad Abdul-Mageed
Abstract	We examine learning offensive content on Twitter with limited, imbalanced data. For the purpose, we investigate the utility of using various data enhancement methods with a host of classical ensemble classifiers. Among the 75 participating teams in SemEval-2019 sub-task B, our system ranks 6th (with 0.706 macro F1-score). For sub-task C, among the 65 participating teams, our system ranks 9th (with 0.587 macro F1-score).
Tasks
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03692v1
PDF	https://arxiv.org/pdf/1906.03692v1.pdf
PWC	https://paperswithcode.com/paper/ubc-nlp-at-semeval-2019-task-6ensemble
Repo
Framework

Refuting Strong AI: Why Consciousness Cannot Be Algorithmic


Title	Refuting Strong AI: Why Consciousness Cannot Be Algorithmic
Authors	Andrew Knight
Abstract	While physicalism requires only that a conscious state depends entirely on an underlying physical state, it is often assumed that consciousness is algorithmic and that conscious states can be copied, such as by copying or digitizing the human brain. In an effort to further elucidate the physical nature of consciousness, I challenge these assumptions and attempt to prove the Single Stream of Consciousness Theorem (SSCT): that a conscious entity cannot experience more than one stream of consciousness from a given conscious state. Assuming only that consciousness is a purely physical phenomenon, it is shown that both Special Relativity and Multiverse theory independently imply SSCT and that the Many Worlds Interpretation of quantum mechanics is inadequate to counter it. Then, SSCT is shown to be incompatible with Strong Artificial Intelligence, implying that consciousness cannot be created or simulated by a computer. Finally, SSCT is shown to imply that a conscious state cannot be physically reset to an earlier conscious state nor can it be duplicated by any physical means. The profound but counterintuitive implications of these conclusions are briefly discussed.
Tasks
Published	2019-06-11
URL	https://arxiv.org/abs/1906.10177v1
PDF	https://arxiv.org/pdf/1906.10177v1.pdf
PWC	https://paperswithcode.com/paper/refuting-strong-ai-why-consciousness-cannot
Repo
Framework