January 26, 2020

3129 words 15 mins read

Paper Group ANR 1450

A new method for quantifying network cyclic structure to improve community detection. Direct training based spiking convolutional neural networks for object recognition. Federated Forest. Automated Segmentation of Lesions in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets. Disentangled Relational Representations for Explaining an …

A new method for quantifying network cyclic structure to improve community detection


Title	A new method for quantifying network cyclic structure to improve community detection
Authors	Behnaz Moradi-Jamei, Heman Shakeri, Pietro Poggi-Corradini, Michael J. Higgins
Abstract	A distinguishing property of communities in networks is that cycles are more prevalent within communities than across communities. Thus, the detection of these communities may be aided through the incorporation of measures of the local “richness” of the cyclic structure. In this paper, we introduce renewal non-backtracking random walks (RNBRW) as a way of quantifying this structure. RNBRW gives a weight to each edge equal to the probability that a non-backtracking random walk completes a cycle with that edge. Hence, edges with larger weights may be thought of as more important to the formation of cycles. Of note, since separate random walks can be performed in parallel, RNBRW weights can be estimated very quickly, even for large graphs. We give simulation results showing that pre-weighting edges through RNBRW may substantially improve the performance of common community detection algorithms. Our results suggest that RNBRW is especially efficient for the challenging case of detecting communities in sparse graphs.
Tasks	Community Detection
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01921v2
PDF	https://arxiv.org/pdf/1910.01921v2.pdf
PWC	https://paperswithcode.com/paper/a-new-method-for-quantifying-network-cyclic
Repo
Framework

Direct training based spiking convolutional neural networks for object recognition


Title	Direct training based spiking convolutional neural networks for object recognition
Authors	Shibo Zhou, Ying Chen, Qiang Ye, Jingxi Li
Abstract	Direct training based spiking neural networks (SNNs) have been paid a lot of attention recently because of its high energy efficiency on emerging neuromorphic hardware. However, due to the non-differentiability of the spiking activity, most of the related SNNs still cannot achieve high object recognition accuracy for the complicated dataset, such as CIFAR-10. Even though some of them can reach the accuracy of 90%, the energy consumption in those networks is very high. Considering this, we propose a direct supervised learning based spiking convolutional neural networks (SCNNs) using temporal coding scheme in this study, aiming to exploit minimum trainable parameters to recognize the object in the image with high accuracy. The MNIST and CIFAR-10 datasets are used to evaluate the performance of the proposed networks. For the MNIST dataset, the proposed networks with noise input are able to reach the high recognition accuracy (99.13%) as the other state-of-art models but use the much less trainable parameters than them. For CIFAR-10 dataset, the proposed networks with data augmentation step can reach the recognition accuracy of 80.49%., which is the state-of-art high accuracy in the field of direct training based SNNs using temporal coding manner. In addition, the number of trainable parameters used in such networks is much less than that in the conversion based SCNNs reported in the literature.
Tasks	Data Augmentation, Object Recognition
Published	2019-09-24
URL	https://arxiv.org/abs/1909.10837v2
PDF	https://arxiv.org/pdf/1909.10837v2.pdf
PWC	https://paperswithcode.com/paper/direct-training-based-spiking-convolutional
Repo
Framework

Federated Forest


Title	Federated Forest
Authors	Yang Liu, Yingting Liu, Zhijie Liu, Junbo Zhang, Chuishi Meng, Yu Zheng
Abstract	Most real-world data are scattered across different companies or government organizations, and cannot be easily integrated under data privacy and related regulations such as the European Union’s General Data Protection Regulation (GDPR) and China’ Cyber Security Law. Such data islands situation and data privacy & security are two major challenges for applications of artificial intelligence. In this paper, we tackle these challenges and propose a privacy-preserving machine learning model, called Federated Forest, which is a lossless learning model of the traditional random forest method, i.e., achieving the same level of accuracy as the non-privacy-preserving approach. Based on it, we developed a secure cross-regional machine learning system that allows a learning process to be jointly trained over different regions’ clients with the same user samples but different attribute sets, processing the data stored in each of them without exchanging their raw data. A novel prediction algorithm was also proposed which could largely reduce the communication overhead. Experiments on both real-world and UCI data sets demonstrate the performance of the Federated Forest is as accurate as the non-federated version. The efficiency and robustness of our proposed system had been verified. Overall, our model is practical, scalable and extensible for real-life tasks.
Tasks
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10053v1
PDF	https://arxiv.org/pdf/1905.10053v1.pdf
PWC	https://paperswithcode.com/paper/federated-forest
Repo
Framework

Automated Segmentation of Lesions in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets


Title	Automated Segmentation of Lesions in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets
Authors	Jie Xing, Zheren Li, Biyuan Wang, Bingbin Yu, Farhad G. Zanjani, Aiwen Zheng, Remco Duits, Tao Tan
Abstract	Breast cancer is the most common invasive cancer with the highest cancer occurrence in females. Handheld ultrasound is one of the most efficient ways to identify and diagnose the breast cancer. The area and the shape information of a lesion is very helpful for clinicians to make diagnostic decisions. In this study we propose a new deep-learning scheme, semi-pixel-wise cycle generative adversarial net (SPCGAN) for segmenting the lesion in 2D ultrasound. The method takes the advantage of a fully connected convolutional neural network (FCN) and a generative adversarial net to segment a lesion by using prior knowledge. We compared the proposed method to a fully connected neural network and the level set segmentation method on a test dataset consisting of 32 malignant lesions and 109 benign lesions. Our proposed method achieved a Dice similarity coefficient (DSC) of 0.92 while FCN and the level set achieved 0.90 and 0.79 respectively. Particularly, for malignant lesions, our method increases the DSC (0.90) of the fully connected neural network to 0.93 significantly (p$<$0.001). The results show that our SPCGAN can obtain robust segmentation results and may be used to relieve the radiologists’ burden for annotation.
Tasks
Published	2019-05-06
URL	https://arxiv.org/abs/1905.01902v3
PDF	https://arxiv.org/pdf/1905.01902v3.pdf
PWC	https://paperswithcode.com/paper/automated-segmentation-of-lesions-in
Repo
Framework

Disentangled Relational Representations for Explaining and Learning from Demonstration


Title	Disentangled Relational Representations for Explaining and Learning from Demonstration
Authors	Yordan Hristov, Daniel Angelov, Michael Burke, Alex Lascarides, Subramanian Ramamoorthy
Abstract	Learning from demonstration is an effective method for human users to instruct desired robot behaviour. However, for most non-trivial tasks of practical interest, efficient learning from demonstration depends crucially on inductive bias in the chosen structure for rewards/costs and policies. We address the case where this inductive bias comes from an exchange with a human user. We propose a method in which a learning agent utilizes the information bottleneck layer of a high-parameter variational neural model, with auxiliary loss terms, in order to ground abstract concepts such as spatial relations. The concepts are referred to in natural language instructions and are manifested in the high-dimensional sensory input stream the agent receives from the world. We evaluate the properties of the latent space of the learned model in a photorealistic synthetic environment and particularly focus on examining its usability for downstream tasks. Additionally, through a series of controlled table-top manipulation experiments, we demonstrate that the learned manifold can be used to ground demonstrations as symbolic plans, which can then be executed on a PR2 robot.
Tasks
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13627v2
PDF	https://arxiv.org/pdf/1907.13627v2.pdf
PWC	https://paperswithcode.com/paper/disentangled-relational-representations-for
Repo
Framework

Error Lower Bounds of Constant Step-size Stochastic Gradient Descent


Title	Error Lower Bounds of Constant Step-size Stochastic Gradient Descent
Authors	Zhiyan Ding, Yiding Chen, Qin Li, Xiaojin Zhu
Abstract	Stochastic Gradient Descent (SGD) plays a central role in modern machine learning. While there is extensive work on providing error upper bound for SGD, not much is known about SGD error lower bound. In this paper, we study the convergence of constant step-size SGD. We provide error lower bound of SGD for potentially non-convex objective functions with Lipschitz gradients. To our knowledge, this is the first analysis for SGD error lower bound without the strong convexity assumption. We use experiments to illustrate our theoretical results.
Tasks
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08212v1
PDF	https://arxiv.org/pdf/1910.08212v1.pdf
PWC	https://paperswithcode.com/paper/error-lower-bounds-of-constant-step-size
Repo
Framework

Tag-less Back-Translation


Title	Tag-less Back-Translation
Authors	Idris Abdulmumin, Bashir Shehu Galadanci, Aliyu Garba
Abstract	An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Tagging, or using gates, has been used to enable translation models to distinguish between synthetic and natural data. This improves standard back-translation and also enables the use of iterative back-translation on language pairs that underperformed using standard back-translation. This work presents a simplified approach of differentiating between the two data using pretraining and finetuning. The approach - tag-less back-translation - trains the model on the synthetic data and finetunes it on the natural data. Preliminary experiments have shown the approach to continuously outperform the tagging approach on low resource English-Vietnamese neural machine translation. While the need for tagging (noising) the dataset has been removed, the approach outperformed the tagged back-translation approach by an average of 0.4 BLEU.
Tasks	Machine Translation
Published	2019-12-22
URL	https://arxiv.org/abs/1912.10514v1
PDF	https://arxiv.org/pdf/1912.10514v1.pdf
PWC	https://paperswithcode.com/paper/tag-less-back-translation
Repo
Framework

Attack Agnostic Statistical Method for Adversarial Detection


Title	Attack Agnostic Statistical Method for Adversarial Detection
Authors	Sambuddha Saha, Aashish Kumar, Pratyush Sahay, George Jose, Srinivas Kruthiventi, Harikrishna Muralidhara
Abstract	Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial attacks - a technique of adding small perturbations to the inputs which can fool a deep network into misclassifying them. Developing defenses against such adversarial attacks is an active research area, with some approaches proposing robust models that are immune to such adversaries, while other techniques attempt to detect such adversarial inputs. In this paper, we present a novel statistical approach for adversarial detection in image classification. Our approach is based on constructing a per-class feature distribution and detecting adversaries based on comparison of features of a test image with the feature distribution of its class. For this purpose, we make use of various statistical distances such as ED (Energy Distance), MMD (Maximum Mean Discrepancy) for adversarial detection, and analyze the performance of each metric. We experimentally show that our approach achieves good adversarial detection performance on MNIST and CIFAR-10 datasets irrespective of the attack method, sample size and the degree of adversarial perturbation.
Tasks	Image Classification
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10008v1
PDF	https://arxiv.org/pdf/1911.10008v1.pdf
PWC	https://paperswithcode.com/paper/attack-agnostic-statistical-method-for
Repo
Framework

Kernel-Guided Training of Implicit Generative Models with Stability Guarantees


Title	Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
Authors	Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet, Bernhard Schölkopf
Abstract	Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance. If we see these implicit models as dynamical systems, some of these issues are caused by being unable to control their behavior in a meaningful way during the course of training. In this work, we propose a theoretically grounded method to guide the training trajectories of GANs by augmenting the GAN loss function with a kernel-based regularization term that controls local and global discrepancies between the model and true distributions. This control signal allows us to inject prior knowledge into the model. We provide theoretical guarantees on the stability of the resulting dynamical system and demonstrate different aspects of it via a wide range of experiments.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.14428v2
PDF	https://arxiv.org/pdf/1910.14428v2.pdf
PWC	https://paperswithcode.com/paper/kernel-guided-training-of-implicit-generative
Repo
Framework

A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing


Title	A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing
Authors	Sidra Mehtab, Jaydip Sen
Abstract	Prediction of future movement of stock prices has been a subject matter of many research work. There is a gamut of literature of technical analysis of stock prices where the objective is to identify patterns in stock price movements and derive profit from it. Improving the prediction accuracy remains the single most challenge in this area of research. We propose a hybrid approach for stock price movement prediction using machine learning, deep learning, and natural language processing. We select the NIFTY 50 index values of the National Stock Exchange of India, and collect its daily price movement over a period of three years (2015 to 2017). Based on the data of 2015 to 2017, we build various predictive models using machine learning, and then use those models to predict the closing value of NIFTY 50 for the period January 2018 till June 2019 with a prediction horizon of one week. For predicting the price movement patterns, we use a number of classification techniques, while for predicting the actual closing price of the stock, various regression models have been used. We also build a Long and Short-Term Memory - based deep learning network for predicting the closing price of the stocks and compare the prediction accuracies of the machine learning models with the LSTM model. We further augment the predictive model by integrating a sentiment analysis module on twitter data to correlate the public sentiment of stock prices with the market sentiment. This has been done using twitter sentiment and previous week closing values to predict stock price movement for the next week. We tested our proposed scheme using a cross validation method based on Self Organizing Fuzzy Neural Networks and found extremely interesting results.
Tasks	Sentiment Analysis, Stock Price Prediction
Published	2019-12-09
URL	https://arxiv.org/abs/1912.07700v1
PDF	https://arxiv.org/pdf/1912.07700v1.pdf
PWC	https://paperswithcode.com/paper/a-robust-predictive-model-for-stock-price
Repo
Framework

Adversarially Robust Submodular Maximization under Knapsack Constraints


Title	Adversarially Robust Submodular Maximization under Knapsack Constraints
Authors	Dmitrii Avdiukhin, Slobodan Mitrović, Grigory Yaroslavtsev, Samson Zhou
Abstract	We propose the first adversarially robust algorithm for monotone submodular maximization under single and multiple knapsack constraints with scalable implementations in distributed and streaming settings. For a single knapsack constraint, our algorithm outputs a robust summary of almost optimal (up to polylogarithmic factors) size, from which a constant-factor approximation to the optimal solution can be constructed. For multiple knapsack constraints, our approximation is within a constant-factor of the best known non-robust solution. We evaluate the performance of our algorithms by comparison to natural robustifications of existing non-robust algorithms under two objectives: 1) dominating set for large social network graphs from Facebook and Twitter collected by the Stanford Network Analysis Project (SNAP), 2) movie recommendations on a dataset from MovieLens. Experimental results show that our algorithms give the best objective for a majority of the inputs and show strong performance even compared to offline algorithms that are given the set of removals in advance.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02367v1
PDF	https://arxiv.org/pdf/1905.02367v1.pdf
PWC	https://paperswithcode.com/paper/adversarially-robust-submodular-maximization
Repo
Framework

Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously


Title	Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously
Authors	Julian Zimmert, Haipeng Luo, Chen-Yu Wei
Abstract	We develop the first general semi-bandit algorithm that simultaneously achieves $\mathcal{O}(\log T)$ regret for stochastic environments and $\mathcal{O}(\sqrt{T})$ regret for adversarial environments without knowledge of the regime or the number of rounds $T$. The leading problem-dependent constants of our bounds are not only optimal in some worst-case sense studied previously, but also optimal for two concrete instances of semi-bandit problems. Our algorithm and analysis extend the recent work of (Zimmert & Seldin, 2019) for the special case of multi-armed bandit, but importantly requires a novel hybrid regularizer designed specifically for semi-bandit. Experimental results on synthetic data show that our algorithm indeed performs well uniformly over different environments. We finally provide a preliminary extension of our results to the full bandit feedback.
Tasks
Published	2019-01-25
URL	https://arxiv.org/abs/1901.08779v2
PDF	https://arxiv.org/pdf/1901.08779v2.pdf
PWC	https://paperswithcode.com/paper/beating-stochastic-and-adversarial-semi
Repo
Framework

Invariant-equivariant representation learning for multi-class data


Title	Invariant-equivariant representation learning for multi-class data
Authors	Ilya Feige
Abstract	Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two separate deep representations: an invariant representation that encodes the information of the class from which the data belongs, and an equivariant representation that encodes the symmetry transformation defining the particular data point within the class manifold (equivariant in the sense that the representation varies naturally with symmetry transformations). This approach is based primarily on the strategic routing of data through the two latent variables, and thus is conceptually transparent, easy to implement, and in-principle generally applicable to any data comprised of discrete classes of continuous distributions (e.g. objects in images, topics in language, individuals in behavioural data). We demonstrate qualitatively compelling representation learning and competitive quantitative performance, in both supervised and semi-supervised settings, versus comparable modelling approaches in the literature with little fine tuning.
Tasks	Representation Learning
Published	2019-02-08
URL	https://arxiv.org/abs/1902.03251v2
PDF	https://arxiv.org/pdf/1902.03251v2.pdf
PWC	https://paperswithcode.com/paper/invariant-equivariant-representation-learning
Repo
Framework

Efficient Wrapper Feature Selection using Autoencoder and Model Based Elimination


Title	Efficient Wrapper Feature Selection using Autoencoder and Model Based Elimination
Authors	Sharan Ramjee, Aly El Gamal
Abstract	We propose a computationally efficient wrapper feature selection method - called Autoencoder and Model Based Elimination of features using Relevance and Redundancy scores (AMBER) - that uses a single ranker model along with autoencoders to perform greedy backward elimination of features. The ranker model is used to prioritize the removal of features that are not critical to the classification task, while the autoencoders are used to prioritize the elimination of correlated features. We demonstrate the superior feature selection ability of AMBER on 4 well known datasets corresponding to different domain applications via comparing the classification accuracies with other computationally efficient state-of-the-art feature selection techniques. Interestingly, we find that the ranker model that is used for feature selection does not necessarily have to be the same as the final classifier that is trained on the selected features. Finally, we note how a smaller number of features can lead to higher accuracies on some datasets, and hypothesize that overfitting the ranker model on the training set facilitates the selection of more salient features.
Tasks	Feature Selection
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11592v2
PDF	https://arxiv.org/pdf/1905.11592v2.pdf
PWC	https://paperswithcode.com/paper/efficient-wrapper-feature-selection-using
Repo
Framework

Attraction-Repulsion clustering with applications to fairness


Title	Attraction-Repulsion clustering with applications to fairness
Authors	Eustasio del Barrio, Hristo Inouzhe, Jean-Michel Loubes
Abstract	In the framework of fair learning, we consider clustering methods that avoid or limit the influence of a set of protected attributes, $S$, (race, sex, etc) over the resulting clusters, with the goal of producing a fair clustering. For this, we introduce perturbations to the Euclidean distance that take into account $S$ in a way that resembles attraction-repulsion in charged particles in Physics and results in dissimilarities with an easy interpretation. Cluster analysis based on these dissimilarities penalizes homogeneity of the clusters in the attributes $S$, and leads to an improvement in fairness. We illustrate the use of our procedures with both synthetic and real data.
Tasks
Published	2019-04-10
URL	https://arxiv.org/abs/1904.05254v2
PDF	https://arxiv.org/pdf/1904.05254v2.pdf
PWC	https://paperswithcode.com/paper/attraction-repulsion-clustering-with
Repo
Framework