Paper Group ANR 315
Bayesian Modeling via Goodness-of-fit. Teaching Syntax by Adversarial Distraction. Sentiment analysis for Arabic language: A brief survey of approaches and techniques. Complex Network Classification with Convolutional Neural Network. Reconstructing probabilistic trees of cellular differentiation from single-cell RNA-seq data. Embedding Push and Pul …
Bayesian Modeling via Goodness-of-fit
| Title | Bayesian Modeling via Goodness-of-fit |
| Authors | Subhadeep, Mukhopadhyay, Douglas Fletcher |
| Abstract | The two key issues of modern Bayesian statistics are: (i) establishing principled approach for distilling statistical prior that is consistent with the given data from an initial believable scientific prior; and (ii) development of a Bayes-frequentist consolidated data analysis workflow that is more effective than either of the two separately. In this paper, we propose the idea of “Bayes via goodness of fit” as a framework for exploring these fundamental questions, in a way that is general enough to embrace almost all of the familiar probability models. Several illustrative examples show the benefit of this new point of view as a practical data analysis tool. Relationship with other Bayesian cultures is also discussed. |
| Tasks | |
| Published | 2018-02-01 |
| URL | http://arxiv.org/abs/1802.00474v3 |
| http://arxiv.org/pdf/1802.00474v3.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-modeling-via-goodness-of-fit |
| Repo | |
| Framework | |
Teaching Syntax by Adversarial Distraction
| Title | Teaching Syntax by Adversarial Distraction |
| Authors | Juho Kim, Christopher Malon, Asim Kadav |
| Abstract | Existing entailment datasets mainly pose problems which can be answered without attention to grammar or word order. Learning syntax requires comparing examples where different grammar and word order change the desired classification. We introduce several datasets based on synthetic transformations of natural entailment examples in SNLI or FEVER, to teach aspects of grammar and word order. We show that without retraining, popular entailment models are unaware that these syntactic differences change meaning. With retraining, some but not all popular entailment models can learn to compare the syntax properly. |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.11067v1 |
| http://arxiv.org/pdf/1810.11067v1.pdf | |
| PWC | https://paperswithcode.com/paper/teaching-syntax-by-adversarial-distraction |
| Repo | |
| Framework | |
Sentiment analysis for Arabic language: A brief survey of approaches and techniques
| Title | Sentiment analysis for Arabic language: A brief survey of approaches and techniques |
| Authors | Mo’ath Alrefai, Hossam Faris, Ibrahim Aljarah |
| Abstract | With the emergence of Web 2.0 technology and the expansion of on-line social networks, current Internet users have the ability to add their reviews, ratings and opinions on social media and on commercial and news web sites. Sentiment analysis aims to classify these reviews reviews in an automatic way. In the literature, there are numerous approaches proposed for automatic sentiment analysis for different language contexts. Each language has its own properties that makes the sentiment analysis more challenging. In this regard, this work presents a comprehensive survey of existing Arabic sentiment analysis studies, and covers the various approaches and techniques proposed in the literature. Moreover, we highlight the main difficulties and challenges of Arabic sentiment analysis, and the proposed techniques in literature to overcome these barriers. |
| Tasks | Arabic Sentiment Analysis, Sentiment Analysis |
| Published | 2018-09-08 |
| URL | http://arxiv.org/abs/1809.02782v2 |
| http://arxiv.org/pdf/1809.02782v2.pdf | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-for-arabic-language-a |
| Repo | |
| Framework | |
Complex Network Classification with Convolutional Neural Network
| Title | Complex Network Classification with Convolutional Neural Network |
| Authors | Ruyue Xin, Jiang Zhang, Yitong Shao |
| Abstract | Classifying large scale networks into several categories and distinguishing them according to their fine structures is of great importance with several applications in real life. However, most studies of complex networks focus on properties of a single network but seldom on classification, clustering, and comparison between different networks, in which the network is treated as a whole. Due to the non-Euclidean properties of the data, conventional methods can hardly be applied on networks directly. In this paper, we propose a novel framework of complex network classifier (CNC) by integrating network embedding and convolutional neural network to tackle the problem of network classification. By training the classifiers on synthetic complex network data and real international trade network data, we show CNC can not only classify networks in a high accuracy and robustness, it can also extract the features of the networks automatically. |
| Tasks | Network Embedding |
| Published | 2018-02-02 |
| URL | http://arxiv.org/abs/1802.00539v2 |
| http://arxiv.org/pdf/1802.00539v2.pdf | |
| PWC | https://paperswithcode.com/paper/complex-network-classification-with |
| Repo | |
| Framework | |
Reconstructing probabilistic trees of cellular differentiation from single-cell RNA-seq data
| Title | Reconstructing probabilistic trees of cellular differentiation from single-cell RNA-seq data |
| Authors | Miriam Shiffman, William T. Stephenson, Geoffrey Schiebinger, Jonathan Huggins, Trevor Campbell, Aviv Regev, Tamara Broderick |
| Abstract | Until recently, transcriptomics was limited to bulk RNA sequencing, obscuring the underlying expression patterns of individual cells in favor of a global average. Thanks to technological advances, we can now profile gene expression across thousands or millions of individual cells in parallel. This new type of data has led to the intriguing discovery that individual cell profiles can reflect the imprint of time or dynamic processes. However, synthesizing this information to reconstruct dynamic biological phenomena from data that are noisy, heterogenous, and sparse—and from processes that may unfold asynchronously—poses a complex computational and statistical challenge. Here, we develop a full generative model for probabilistically reconstructing trees of cellular differentiation from single-cell RNA-seq data. Specifically, we extend the framework of the classical Dirichlet diffusion tree to simultaneously infer branch topology and latent cell states along continuous trajectories over the full tree. In tandem, we construct a novel Markov chain Monte Carlo sampler that interleaves Metropolis-Hastings and message passing to leverage model structure for efficient inference. Finally, we demonstrate that these techniques can recover latent trajectories from simulated single-cell transcriptomes. While this work is motivated by cellular differentiation, we derive a tractable model that provides flexible densities for any data (coupled with an appropriate noise model) that arise from continuous evolution along a latent nonparametric tree. |
| Tasks | |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11790v1 |
| http://arxiv.org/pdf/1811.11790v1.pdf | |
| PWC | https://paperswithcode.com/paper/reconstructing-probabilistic-trees-of |
| Repo | |
| Framework | |
Embedding Push and Pull Search in the Framework of Differential Evolution for Solving Constrained Single-objective Optimization Problems
| Title | Embedding Push and Pull Search in the Framework of Differential Evolution for Solving Constrained Single-objective Optimization Problems |
| Authors | Zhun Fan, Wenji Li, Zhaojun Wang, Yutong Yuan, Fuzan Sun, Zhi Yang, Jie Ruan, Zhaocheng Li, Erik Goodman |
| Abstract | This paper proposes a push and pull search method in the framework of differential evolution (PPS-DE) to solve constrained single-objective optimization problems (CSOPs). More specifically, two sub-populations, including the top and bottom sub-populations, are collaborated with each other to search global optimal solutions efficiently. The top sub-population adopts the pull and pull search (PPS) mechanism to deal with constraints, while the bottom sub-population use the superiority of feasible solutions (SF) technique to deal with constraints. In the top sub-population, the search process is divided into two different stages — push and pull stages.An adaptive DE variant with three trial vector generation strategies is employed in the proposed PPS-DE. In the top sub-population, all the three trial vector generation strategies are used to generate offsprings, just like in CoDE. In the bottom sub-population, a strategy adaptation, in which the trial vector generation strategies are periodically self-adapted by learning from their experiences in generating promising solutions in the top sub-population, is used to choose a suitable trial vector generation strategy to generate one offspring. Furthermore, a parameter adaptation strategy from LSHADE44 is employed in both sup-populations to generate scale factor $F$ and crossover rate $CR$ for each trial vector generation strategy. Twenty-eight CSOPs with 10-, 30-, and 50-dimensional decision variables provided in the CEC2018 competition on real parameter single objective optimization are optimized by the proposed PPS-DE. The experimental results demonstrate that the proposed PPS-DE has the best performance compared with the other seven state-of-the-art algorithms, including AGA-PPS, LSHADE44, LSHADE44+IDE, UDE, IUDE, $\epsilon$MAg-ES and C$^2$oDE. |
| Tasks | |
| Published | 2018-12-16 |
| URL | http://arxiv.org/abs/1812.06381v1 |
| http://arxiv.org/pdf/1812.06381v1.pdf | |
| PWC | https://paperswithcode.com/paper/embedding-push-and-pull-search-in-the |
| Repo | |
| Framework | |
TextZoo, a New Benchmark for Reconsidering Text Classification
| Title | TextZoo, a New Benchmark for Reconsidering Text Classification |
| Authors | Benyou Wang, Li Wang, Qikang Wei, Lichun Liu |
| Abstract | Text representation is a fundamental concern in Natural Language Processing, especially in text classification. Recently, many neural network approaches with delicate representation model (e.g. FASTTEXT, CNN, RNN and many hybrid models with attention mechanisms) claimed that they achieved state-of-art in specific text classification datasets. However, it lacks an unified benchmark to compare these models and reveals the advantage of each sub-components for various settings. We re-implement more than 20 popular text representation models for classification in more than 10 datasets. In this paper, we reconsider the text classification task in the perspective of neural network and get serval effects with analysis of the above results. |
| Tasks | Text Classification |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03656v2 |
| http://arxiv.org/pdf/1802.03656v2.pdf | |
| PWC | https://paperswithcode.com/paper/textzoo-a-new-benchmark-for-reconsidering |
| Repo | |
| Framework | |
Gender Prediction in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System
| Title | Gender Prediction in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System |
| Authors | Ankush Khandelwal, Sahil Swami, Syed Sarfaraz Akhtar, Manish Shrivastava |
| Abstract | The rapid expansion in the usage of social media networking sites leads to a huge amount of unprocessed user generated data which can be used for text mining. Author profiling is the problem of automatically determining profiling aspects like the author’s gender and age group through a text is gaining much popularity in computational linguistics. Most of the past research in author profiling is concentrated on English texts \cite{1,2}. However many users often change the language while posting on social media which is called code-mixing, and it develops some challenges in the field of text classification and author profiling like variations in spelling, non-grammatical structure and transliteration \cite{3}. There are very few English-Hindi code-mixed annotated datasets of social media content present online \cite{4}. In this paper, we analyze the task of author’s gender prediction in code-mixed content and present a corpus of English-Hindi texts collected from Twitter which is annotated with author’s gender. We also explore language identification of every word in this corpus. We present a supervised classification baseline system which uses various machine learning algorithms to identify the gender of an author using a text, based on character and word level features. |
| Tasks | Gender Prediction, Language Identification, Text Classification, Transliteration |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05600v1 |
| http://arxiv.org/pdf/1806.05600v1.pdf | |
| PWC | https://paperswithcode.com/paper/gender-prediction-in-english-hindi-code-mixed |
| Repo | |
| Framework | |
Learning Dynamical Demand Response Model in Real-Time Pricing Program
| Title | Learning Dynamical Demand Response Model in Real-Time Pricing Program |
| Authors | Hanchen Xu, Hongbo Sun, Daniel Nikovski, Kitamura Shoichi, Kazuyuki Mori |
| Abstract | Price responsiveness is a major feature of end use customers (EUCs) that participate in demand response (DR) programs, and has been conventionally modeled with static demand functions, which take the electricity price as the input and the aggregate energy consumption as the output. This, however, neglects the inherent temporal correlation of the EUC behaviors, and may result in large errors when predicting the actual responses of EUCs in real-time pricing (RTP) programs. In this paper, we propose a dynamical DR model so as to capture the temporal behavior of the EUCs. The states in the proposed dynamical DR model can be explicitly chosen, in which case the model can be represented by a linear function or a multi-layer feedforward neural network, or implicitly chosen, in which case the model can be represented by a recurrent neural network or a long short-term memory unit network. In both cases, the dynamical DR model can be learned from historical price and energy consumption data. Numerical simulation illustrated how the states are chosen and also showed the proposed dynamical DR model significantly outperforms the static ones. |
| Tasks | |
| Published | 2018-12-22 |
| URL | http://arxiv.org/abs/1812.09567v1 |
| http://arxiv.org/pdf/1812.09567v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-dynamical-demand-response-model-in |
| Repo | |
| Framework | |
A Multi-Objective Deep Reinforcement Learning Framework
| Title | A Multi-Objective Deep Reinforcement Learning Framework |
| Authors | Thanh Thi Nguyen |
| Abstract | This paper presents a new multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We propose the use of linear and non-linear methods to develop the MODRL framework that includes both single-policy and multi-policy strategies. The experimental results on two benchmark problems including the two-objective deep sea treasure environment and the three-objective mountain car problem indicate that the proposed framework is able to converge to the optimal Pareto solutions effectively. The proposed framework is generic, which allows implementation of different deep reinforcement learning algorithms in different complex environments. This therefore overcomes many difficulties involved with standard multi-objective reinforcement learning (MORL) methods existing in the current literature. The framework creates a platform as a testbed environment to develop methods for solving various problems associated with the current MORL. Details of the framework implementation can be referred to http://www.deakin.edu.au/~thanhthi/drl.htm. |
| Tasks | |
| Published | 2018-03-08 |
| URL | http://arxiv.org/abs/1803.02965v2 |
| http://arxiv.org/pdf/1803.02965v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-objective-deep-reinforcement-learning |
| Repo | |
| Framework | |
Image-based Survival Analysis for Lung Cancer Patients using CNNs
| Title | Image-based Survival Analysis for Lung Cancer Patients using CNNs |
| Authors | Christoph Haarburger, Philippe Weitz, Oliver Rippel, Dorit Merhof |
| Abstract | Traditional survival models such as the Cox proportional hazards model are typically based on scalar or categorical clinical features. With the advent of increasingly large image datasets, it has become feasible to incorporate quantitative image features into survival prediction. So far, this kind of analysis is mostly based on radiomics features, i.e. a fixed set of features that is mathematically defined a priori. To capture highly abstract information, it is desirable to learn the feature extraction using convolutional neural networks. However, for tomographic medical images, model training is difficult because on the one hand, only few samples of 3D image data fit into one batch at once and on the other hand, survival loss functions are essentially ordering measures that require large batch sizes. In this work, we show that by simplifying survival analysis to median survival classification, convolutional neural networks can be trained with small batch sizes and learn features that predict survival equally well as end-to-end hazard prediction networks. Our approach outperforms the previous state of the art in a publicly available lung cancer dataset. |
| Tasks | Survival Analysis |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.09679v2 |
| http://arxiv.org/pdf/1808.09679v2.pdf | |
| PWC | https://paperswithcode.com/paper/image-based-survival-analysis-for-lung-cancer |
| Repo | |
| Framework | |
Learning The Invisible: A Hybrid Deep Learning-Shearlet Framework for Limited Angle Computed Tomography
| Title | Learning The Invisible: A Hybrid Deep Learning-Shearlet Framework for Limited Angle Computed Tomography |
| Authors | T. A. Bubba, G. Kutyniok, M. Lassas, M. März, W. Samek, S. Siltanen, V. Srinivasan |
| Abstract | The high complexity of various inverse problems poses a significant challenge to model-based reconstruction schemes, which in such situations often reach their limits. At the same time, we witness an exceptional success of data-based methodologies such as deep learning. However, in the context of inverse problems, deep neural networks mostly act as black box routines, used for instance for a somewhat unspecified removal of artifacts in classical image reconstructions. In this paper, we will focus on the severely ill-posed inverse problem of limited angle computed tomography, in which entire boundary sections are not captured in the measurements. We will develop a hybrid reconstruction framework that fuses model-based sparse regularization with data-driven deep learning. Our method is reliable in the sense that we only learn the part that can provably not be handled by model-based methods, while applying the theoretically controllable sparse regularization technique to the remaining parts. Such a decomposition into visible and invisible segments is achieved by means of the shearlet transform that allows to resolve wavefront sets in the phase space. Furthermore, this split enables us to assign the clear task of inferring unknown shearlet coefficients to the neural network and thereby offering an interpretation of its performance in the context of limited angle computed tomography. Our numerical experiments show that our algorithm significantly surpasses both pure model- and more data-based reconstruction methods. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04602v1 |
| http://arxiv.org/pdf/1811.04602v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-invisible-a-hybrid-deep-learning |
| Repo | |
| Framework | |
Recovering a Single Community with Side Information
| Title | Recovering a Single Community with Side Information |
| Authors | Hussein Saad, Aria Nosratinia |
| Abstract | We study the effect of the quality and quantity of side information on the recovery of a hidden community of size $K=o(n)$ in a graph of size $n$. Side information for each node in the graph is modeled by a random vector with the following features: either the dimension of the vector is allowed to vary with $n$, while log-likelihood ratio (LLR) of each component with respect to the node label is fixed, or the LLR is allowed to vary and the vector dimension is fixed. These two models represent the variation in quality and quantity of side information. Under maximum likelihood detection, we calculate tight necessary and sufficient conditions for exact recovery of the labels. We demonstrate how side information needs to evolve with $n$ in terms of either its quantity, or quality, to improve the exact recovery threshold. A similar set of results are obtained for weak recovery. Under belief propagation, tight necessary and sufficient conditions for weak recovery are calculated when the LLRs are constant, and sufficient conditions when the LLRs vary with $n$. Moreover, we design and analyze a local voting procedure using side information that can achieve exact recovery when applied after belief propagation. The results for belief propagation are validated via simulations on finite synthetic data-sets, showing that the asymptotic results of this paper can also shed light on the performance at finite $n$. |
| Tasks | |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01738v1 |
| http://arxiv.org/pdf/1809.01738v1.pdf | |
| PWC | https://paperswithcode.com/paper/recovering-a-single-community-with-side |
| Repo | |
| Framework | |
How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network?
| Title | How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network? |
| Authors | Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh |
| Abstract | It is widely believed that the practical success of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) owes to the fact that CNNs and RNNs use a more compact parametric representation than their Fully-Connected Neural Network (FNN) counterparts, and consequently require fewer training examples to accurately estimate their parameters. We initiate the study of rigorously characterizing the sample-complexity of estimating CNNs and RNNs. We show that the sample-complexity to learn CNNs and RNNs scales linearly with their intrinsic dimension and this sample-complexity is much smaller than for their FNN counterparts. For both CNNs and RNNs, we also present lower bounds showing our sample complexities are tight up to logarithmic factors. Our main technical tools for deriving these results are a localized empirical process analysis and a new technical lemma characterizing the convolutional and recurrent structure. We believe that these tools may inspire further developments in understanding CNNs and RNNs. |
| Tasks | |
| Published | 2018-05-21 |
| URL | https://arxiv.org/abs/1805.07883v3 |
| https://arxiv.org/pdf/1805.07883v3.pdf | |
| PWC | https://paperswithcode.com/paper/how-many-samples-are-needed-to-estimate-a |
| Repo | |
| Framework | |
Detecting Potential Local Adversarial Examples for Human-Interpretable Defense
| Title | Detecting Potential Local Adversarial Examples for Human-Interpretable Defense |
| Authors | Xavier Renard, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki |
| Abstract | Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval. Some people may be tempted to manipulate specific variables, such as the age or the salary, in order to get better chances of approval. In this ongoing work, we propose to discuss, with a first proposition, the issue of detecting a potential local adversarial example on classical tabular data by providing to a human expert the locally critical features for the classifier’s decision, in order to control the provided information and avoid a fraud. |
| Tasks | |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.02397v1 |
| http://arxiv.org/pdf/1809.02397v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-potential-local-adversarial |
| Repo | |
| Framework | |
