Paper Group ANR 463
Compressive Embedding and Visualization using Graphs. Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons. On the letter frequencies and entropy of written Marathi. Context Attentive Bandits: Contextual Bandit with Restricted Context. Adversarial Neural Machine Translation. Delayed acceptance ABC-SMC. The Social Bow Tie. Adaptive coordina …
Compressive Embedding and Visualization using Graphs
| Title | Compressive Embedding and Visualization using Graphs |
| Authors | Johan Paratte, Nathanaël Perraudin, Pierre Vandergheynst |
| Abstract | Visualizing high-dimensional data has been a focus in data analysis communities for decades, which has led to the design of many algorithms, some of which are now considered references (such as t-SNE for example). In our era of overwhelming data volumes, the scalability of such methods have become more and more important. In this work, we present a method which allows to apply any visualization or embedding algorithm on very large datasets by considering only a fraction of the data as input and then extending the information to all data points using a graph encoding its global similarity. We show that in most cases, using only $\mathcal{O}(\log(N))$ samples is sufficient to diffuse the information to all $N$ data points. In addition, we propose quantitative methods to measure the quality of embeddings and demonstrate the validity of our technique on both synthetic and real-world datasets. |
| Tasks | |
| Published | 2017-02-19 |
| URL | http://arxiv.org/abs/1702.05815v1 |
| http://arxiv.org/pdf/1702.05815v1.pdf | |
| PWC | https://paperswithcode.com/paper/compressive-embedding-and-visualization-using |
| Repo | |
| Framework | |
Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons
| Title | Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons |
| Authors | Tom Hope, Dafna Shahaf |
| Abstract | Crowdsourcing has become a popular method for collecting labeled training data. However, in many practical scenarios traditional labeling can be difficult for crowdworkers (for example, if the data is high-dimensional or unintuitive, or the labels are continuous). In this work, we develop a novel model for crowdsourcing that can complement standard practices by exploiting people’s intuitions about groups and relations between them. We employ a recent machine learning setting, called Ballpark Learning, that can estimate individual labels given only coarse, aggregated signal over groups of data points. To address the important case of continuous labels, we extend the Ballpark setting (which focused on classification) to regression problems. We formulate the problem as a convex optimization problem and propose fast, simple methods with an innate robustness to outliers. We evaluate our methods on real-world datasets, demonstrating how useful constraints about groups can be harnessed from a crowd of non-experts. Our methods can rival supervised models trained on many true labels, and can obtain considerably better results from the crowd than a standard label-collection process (for a lower price). By collecting rough guesses on groups of instances and using machine learning to infer the individual labels, our lightweight framework is able to address core crowdsourcing challenges and train machine learning models in a cost-effective way. |
| Tasks | |
| Published | 2017-12-13 |
| URL | http://arxiv.org/abs/1712.04828v1 |
| http://arxiv.org/pdf/1712.04828v1.pdf | |
| PWC | https://paperswithcode.com/paper/ballpark-crowdsourcing-the-wisdom-of-rough |
| Repo | |
| Framework | |
On the letter frequencies and entropy of written Marathi
| Title | On the letter frequencies and entropy of written Marathi |
| Authors | Jaydeep Chipalkatti, Mihir Kulkarni |
| Abstract | We carry out a comprehensive analysis of letter frequencies in contemporary written Marathi. We determine sets of letters which statistically predominate any large generic Marathi text, and use these sets to estimate the entropy of Marathi. |
| Tasks | |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.08209v1 |
| http://arxiv.org/pdf/1707.08209v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-letter-frequencies-and-entropy-of |
| Repo | |
| Framework | |
Context Attentive Bandits: Contextual Bandit with Restricted Context
| Title | Context Attentive Bandits: Contextual Bandit with Restricted Context |
| Authors | Djallel Bouneffouf, Irina Rish, Guillermo A. Cecchi, Raphael Feraud |
| Abstract | We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommender systems and attention modeling. Herein, we adapt the standard multi-armed bandit algorithm known as Thompson Sampling to take advantage of our restricted context setting, and propose two novel algorithms, called the Thompson Sampling with Restricted Context(TSRC) and the Windows Thompson Sampling with Restricted Context(WTSRC), for handling stationary and nonstationary environments, respectively. Our empirical results demonstrate advantages of the proposed approaches on several real-life datasets |
| Tasks | Recommendation Systems |
| Published | 2017-05-10 |
| URL | http://arxiv.org/abs/1705.03821v2 |
| http://arxiv.org/pdf/1705.03821v2.pdf | |
| PWC | https://paperswithcode.com/paper/context-attentive-bandits-contextual-bandit |
| Repo | |
| Framework | |
Adversarial Neural Machine Translation
| Title | Adversarial Neural Machine Translation |
| Authors | Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu |
| Abstract | In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success of generative adversarial networks (GANs), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elaborately designed Convolutional Neural Network (CNN). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English$\rightarrow$French and German$\rightarrow$English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines. |
| Tasks | Machine Translation |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1704.06933v4 |
| http://arxiv.org/pdf/1704.06933v4.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-neural-machine-translation |
| Repo | |
| Framework | |
Delayed acceptance ABC-SMC
| Title | Delayed acceptance ABC-SMC |
| Authors | Richard G. Everitt, Paulina A. Rowińska |
| Abstract | Approximate Bayesian computation (ABC) is now an established technique for statistical inference used in cases where the likelihood function is computationally expensive or not available. It relies on the use of a model that is specified in the form of a simulator, and approximates the likelihood at a parameter $\theta$ by simulating auxiliary data sets $x$ and evaluating the distance of $x$ from the true data $y$. However, ABC is not computationally feasible in cases where using the simulator for each $\theta$ is very expensive. This paper investigates this situation in cases where a cheap, but approximate, simulator is available. The approach is to employ delayed acceptance Markov chain Monte Carlo (MCMC) within an ABC sequential Monte Carlo (SMC) sampler in order to, in a first stage of the kernel, use the cheap simulator to rule out parts of the parameter space that are not worth exploring, so that the “true” simulator is only run (in the second stage of the kernel) where there is a reasonable chance of accepting proposed values of $\theta$. We show that this approach can be used quite automatically, with the only tuning parameter choice additional to ABC-SMC being the number of particles we wish to carry through to the second stage of the kernel. Applications to stochastic differential equation models and latent doubly intractable distributions are presented. |
| Tasks | |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02230v1 |
| http://arxiv.org/pdf/1708.02230v1.pdf | |
| PWC | https://paperswithcode.com/paper/delayed-acceptance-abc-smc |
| Repo | |
| Framework | |
The Social Bow Tie
| Title | The Social Bow Tie |
| Authors | Heather Mattie, Kenth Engø-Monsen, Rich Ling, Jukka-Pekka Onnela |
| Abstract | Understanding tie strength in social networks, and the factors that influence it, have received much attention in a myriad of disciplines for decades. Several models incorporating indicators of tie strength have been proposed and used to quantify relationships in social networks, and a standard set of structural network metrics have been applied to predominantly online social media sites to predict tie strength. Here, we introduce the concept of the “social bow tie” framework, a small subgraph of the network that consists of a collection of nodes and ties that surround a tie of interest, forming a topological structure that resembles a bow tie. We also define several intuitive and interpretable metrics that quantify properties of the bow tie. We use random forests and regression models to predict categorical and continuous measures of tie strength from different properties of the bow tie, including nodal attributes. We also investigate what aspects of the bow tie are most predictive of tie strength in two distinct social networks: a collection of 75 rural villages in India and a nationwide call network of European mobile phone users. Our results indicate several of the bow tie metrics are highly predictive of tie strength, and we find the more the social circles of two individuals overlap, the stronger their tie, consistent with previous findings. However, we also find that the more tightly-knit their non-overlapping social circles, the weaker the tie. This new finding complements our current understanding of what drives the strength of ties in social networks. |
| Tasks | |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.04177v2 |
| http://arxiv.org/pdf/1710.04177v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-social-bow-tie |
| Repo | |
| Framework | |
Adaptive coordination of working-memory and reinforcement learning in non-human primates performing a trial-and-error problem solving task
| Title | Adaptive coordination of working-memory and reinforcement learning in non-human primates performing a trial-and-error problem solving task |
| Authors | Guillaume Viejo, Benoît Girard, Emmanuel Procyk, Mehdi Khamassi |
| Abstract | Accumulating evidence suggest that human behavior in trial-and-error learning tasks based on decisions between discrete actions may involve a combination of reinforcement learning (RL) and working-memory (WM). While the understanding of brain activity at stake in this type of tasks often involve the comparison with non-human primate neurophysiological results, it is not clear whether monkeys use similar combined RL and WM processes to solve these tasks. Here we analyzed the behavior of five monkeys with computational models combining RL and WM. Our model-based analysis approach enables to not only fit trial-by-trial choices but also transient slowdowns in reaction times, indicative of WM use. We found that the behavior of the five monkeys was better explained in terms of a combination of RL and WM despite inter-individual differences. The same coordination dynamics we used in a previous study in humans best explained the behavior of some monkeys while the behavior of others showed the opposite pattern, revealing a possible different dynamics of WM process. We further analyzed different variants of the tested models to open a discussion on how the long pretraining in these tasks may have favored particular coordination dynamics between RL and WM. This points towards either inter-species differences or protocol differences which could be further tested in humans. |
| Tasks | |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00698v1 |
| http://arxiv.org/pdf/1711.00698v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-coordination-of-working-memory-and |
| Repo | |
| Framework | |
Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification
| Title | Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification |
| Authors | Yanis Bahroun, Andrea Soltoggio |
| Abstract | Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different data sets using the same underlying rules thanks to the autonomous discovery of discriminating features during training. Recently, a new class of Hebbian-like and local unsupervised learning rules for neural networks have been developed that minimise a similarity matching cost-function. These have been shown to perform sparse representation learning. This study tests the effectiveness of one such learning rule for learning features from images. The rule implemented is derived from a nonnegative classical multidimensional scaling cost-function, and is applied to both single and multi-layer architectures. The features learned by the algorithm are then used as input to an SVM to test their effectiveness in classification on the established CIFAR-10 image dataset. The algorithm performs well in comparison to other unsupervised learning algorithms and multi-layer networks, thus suggesting its validity in the design of a new class of compact, online learning networks. |
| Tasks | Image Classification, Representation Learning |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06456v3 |
| http://arxiv.org/pdf/1702.06456v3.pdf | |
| PWC | https://paperswithcode.com/paper/online-representation-learning-with-single |
| Repo | |
| Framework | |
All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification
| Title | All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification |
| Authors | Yoshihide Sawada, Yoshikuni Sato, Toru Nakada, Kei Ujimoto, Nobuhiro Hayashi |
| Abstract | In this article, we propose a transfer learning method for deep neural networks (DNNs). Deep learning has been widely used in many applications. However, applying deep learning is problematic when a large amount of training data are not available. One of the conventional methods for solving this problem is transfer learning for DNNs. In the field of image recognition, state-of-the-art transfer learning methods for DNNs re-use parameters trained on source domain data except for the output layer. However, this method may result in poor classification performance when the amount of target domain data is significantly small. To address this problem, we propose a method called All-Transfer Deep Learning, which enables the transfer of all parameters of a DNN. With this method, we can compute the relationship between the source and target labels by the source domain knowledge. We applied our method to actual two-dimensional electrophoresis image~(2-DE image) classification for determining if an individual suffers from sepsis; the first attempt to apply a classification approach to 2-DE images for proteomics, which has attracted considerable attention as an extension beyond genomics. The results suggest that our proposed method outperforms conventional transfer learning methods for DNNs. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04450v1 |
| http://arxiv.org/pdf/1711.04450v1.pdf | |
| PWC | https://paperswithcode.com/paper/all-transfer-learning-for-deep-neural |
| Repo | |
| Framework | |
MotifMark: Finding Regulatory Motifs in DNA Sequences
| Title | MotifMark: Finding Regulatory Motifs in DNA Sequences |
| Authors | Hamid Reza Hassanzadeh, Pushkar Kolhe, Charles L. Isbell, May D. Wang |
| Abstract | The interaction between proteins and DNA is a key driving force in a significant number of biological processes such as transcriptional regulation, repair, recombination, splicing, and DNA modification. The identification of DNA-binding sites and the specificity of target proteins in binding to these regions are two important steps in understanding the mechanisms of these biological activities. A number of high-throughput technologies have recently emerged that try to quantify the affinity between proteins and DNA motifs. Despite their success, these technologies have their own limitations and fall short in precise characterization of motifs, and as a result, require further downstream analysis to extract useful and interpretable information from a haystack of noisy and inaccurate data. Here we propose MotifMark, a new algorithm based on graph theory and machine learning, that can find binding sites on candidate probes and rank their specificity in regard to the underlying transcription factor. We developed a pipeline to analyze experimental data derived from compact universal protein binding microarrays and benchmarked it against two of the most accurate motif search methods. Our results indicate that MotifMark can be a viable alternative technique for prediction of motif from protein binding microarrays and possibly other related high-throughput techniques. |
| Tasks | |
| Published | 2017-05-04 |
| URL | http://arxiv.org/abs/1705.03321v1 |
| http://arxiv.org/pdf/1705.03321v1.pdf | |
| PWC | https://paperswithcode.com/paper/motifmark-finding-regulatory-motifs-in-dna |
| Repo | |
| Framework | |
Learning across scales - A multiscale method for Convolution Neural Networks
| Title | Learning across scales - A multiscale method for Convolution Neural Networks |
| Authors | Eldad Haber, Lars Ruthotto, Elliot Holtham, Seong-Hwan Jun |
| Abstract | In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs). We show that the forward propagation in CNNs can be interpreted as a time-dependent nonlinear differential equation and learning as controlling the parameters of the differential equation such that the network approximates the data-label relation for given training data. Using this continuous interpretation we derive two new methods to scale CNNs with respect to two different dimensions. The first class of multiscale methods connects low-resolution and high-resolution data through prolongation and restriction of CNN parameters. We demonstrate that this enables classifying high-resolution images using CNNs trained with low-resolution images and vice versa and warm-starting the learning process. The second class of multiscale methods connects shallow and deep networks and leads to new training strategies that gradually increase the depths of the CNN while re-using parameters for initializations. |
| Tasks | |
| Published | 2017-03-06 |
| URL | http://arxiv.org/abs/1703.02009v2 |
| http://arxiv.org/pdf/1703.02009v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-across-scales-a-multiscale-method |
| Repo | |
| Framework | |
Epistemic Logic with Functional Dependency Operator
| Title | Epistemic Logic with Functional Dependency Operator |
| Authors | Yifeng Ding |
| Abstract | Epistemic logic with non-standard knowledge operators, especially the “knowing-value” operator, has recently gathered much attention. With the “knowing-value” operator, we can express knowledge of individual variables, but not of the relations between them in general. In this paper, we propose a new operator Kf to express knowledge of the functional dependencies between variables. The semantics of this Kf operator uses a function domain which imposes a constraint on what counts as a functional dependency relation. By adjusting this function domain, different interesting logics arise, and in this paper we axiomatize three such logics in a single agent setting. Then we show how these three logics can be unified by allowing the function domain to vary relative to different agents and possible worlds. A multiagent axiomatization is given in this case. |
| Tasks | |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02048v1 |
| http://arxiv.org/pdf/1706.02048v1.pdf | |
| PWC | https://paperswithcode.com/paper/epistemic-logic-with-functional-dependency |
| Repo | |
| Framework | |
Classification Driven Dynamic Image Enhancement
| Title | Classification Driven Dynamic Image Enhancement |
| Authors | Vivek Sharma, Ali Diba, Davy Neven, Michael S. Brown, Luc Van Gool, Rainer Stiefelhagen |
| Abstract | Convolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality and in turn improve the overall effectiveness of a CNN. Existing image enhancement methods, however, are designed to improve the perceptual quality of an image for a human observer. In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception. To this end, we present a unified CNN architecture that uses a range of enhancement filters that can enhance image-specific details via end-to-end dynamic filter learning. We demonstrate the effectiveness of this strategy on four challenging benchmark datasets for fine-grained, object, scene, and texture classification: CUB-200-2011, PASCAL-VOC2007, MIT-Indoor, and DTD. Experiments using our proposed enhancement show promising results on all the datasets. In addition, our approach is capable of improving the performance of all generic CNN architectures. |
| Tasks | Image Classification, Image Enhancement, Texture Classification |
| Published | 2017-10-20 |
| URL | http://arxiv.org/abs/1710.07558v3 |
| http://arxiv.org/pdf/1710.07558v3.pdf | |
| PWC | https://paperswithcode.com/paper/classification-driven-dynamic-image |
| Repo | |
| Framework | |
An Optimal Dimensionality Multi-shell Sampling Scheme with Accurate and Efficient Transforms for Diffusion MRI
| Title | An Optimal Dimensionality Multi-shell Sampling Scheme with Accurate and Efficient Transforms for Diffusion MRI |
| Authors | Alice P. Bates, Zubair Khalid, Jason D. McEwen, Rodney A. Kennedy |
| Abstract | This paper proposes a multi-shell sampling scheme and corresponding transforms for the accurate reconstruction of the diffusion signal in diffusion MRI by expansion in the spherical polar Fourier (SPF) basis. The sampling scheme uses an optimal number of samples, equal to the degrees of freedom of the band-limited diffusion signal in the SPF domain, and allows for computationally efficient reconstruction. We use synthetic data sets to demonstrate that the proposed scheme allows for greater reconstruction accuracy of the diffusion signal than the multi-shell sampling schemes obtained using the generalised electrostatic energy minimisation (gEEM) method used in the Human Connectome Project. We also demonstrate that the proposed sampling scheme allows for increased angular discrimination and improved rotational invariance of reconstruction accuracy than the gEEM schemes. |
| Tasks | |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1705.04336v1 |
| http://arxiv.org/pdf/1705.04336v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimal-dimensionality-multi-shell |
| Repo | |
| Framework | |
