Paper Group ANR 447
CNNPred: CNN-based stock market prediction using several data sources. JU_KS@SAIL_CodeMixed-2017: Sentiment Analysis for Indian Code Mixed Social Media Texts. Attention Driven Person Re-identification. Usage of analytic hierarchy process for steganographic inserts detection in images. Randomized Prior Functions for Deep Reinforcement Learning. View …
CNNPred: CNN-based stock market prediction using several data sources
| Title | CNNPred: CNN-based stock market prediction using several data sources |
| Authors | Ehsan Hoseinzade, Saman Haratizadeh |
| Abstract | Feature extraction from financial data is one of the most important problems in market prediction domain for which many approaches have been suggested. Among other modern tools, convolutional neural networks (CNN) have recently been applied for automatic feature selection and market prediction. However, in experiments reported so far, less attention has been paid to the correlation among different markets as a possible source of information for extracting features. In this paper, we suggest a CNN-based framework with specially designed CNNs, that can be applied on a collection of data from a variety of sources, including different markets, in order to extract features for predicting the future of those markets. The suggested framework has been applied for predicting the next day’s direction of movement for the indices of S&P 500, NASDAQ, DJI, NYSE, and RUSSELL markets based on various sets of initial features. The evaluations show a significant improvement in prediction’s performance compared to the state of the art baseline algorithms. |
| Tasks | Feature Selection, Stock Market Prediction |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.08923v1 |
| http://arxiv.org/pdf/1810.08923v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnnpred-cnn-based-stock-market-prediction |
| Repo | |
| Framework | |
JU_KS@SAIL_CodeMixed-2017: Sentiment Analysis for Indian Code Mixed Social Media Texts
| Title | JU_KS@SAIL_CodeMixed-2017: Sentiment Analysis for Indian Code Mixed Social Media Texts |
| Authors | Kamal Sarkar |
| Abstract | This paper reports about our work in the NLP Tool Contest @ICON-2017, shared task on Sentiment Analysis for Indian Languages (SAIL) (code mixed). To implement our system, we have used a machine learning algo-rithm called Multinomial Na"ive Bayes trained using n-gram and SentiWordnet features. We have also used a small SentiWordnet for English and a small SentiWordnet for Bengali. But we have not used any SentiWordnet for Hindi language. We have tested our system on Hindi-English and Bengali-English code mixed social media data sets released for the contest. The performance of our system is very close to the best system participated in the contest. For both Bengali-English and Hindi-English runs, our system was ranked at the 3rd position out of all submitted runs and awarded the 3rd prize in the contest. |
| Tasks | Sentiment Analysis |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05737v1 |
| http://arxiv.org/pdf/1802.05737v1.pdf | |
| PWC | https://paperswithcode.com/paper/ju_kssail_codemixed-2017-sentiment-analysis |
| Repo | |
| Framework | |
Attention Driven Person Re-identification
| Title | Attention Driven Person Re-identification |
| Authors | Fan Yang, Ke Yan, Shijian Lu, Huizhu Jia, Xiaodong Xie, Wen Gao |
| Abstract | Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc. It has been studied extensively in recent years, but the multifarious local and global features are still not fully exploited by either ignoring the interplay between whole-body images and body-part images or missing in-depth examination of specific body-part images. In this paper, we propose a novel attention-driven multi-branch network that learns robust and discriminative human representation from global whole-body images and local body-part images simultaneously. Within each branch, an intra-attention network is designed to search for informative and discriminative regions within the whole-body or body-part images, where attention is elegantly decomposed into spatial-wise attention and channel-wise attention for effective and efficient learning. In addition, a novel inter-attention module is designed which fuses the output of intra-attention networks adaptively for optimal person ReID. The proposed technique has been evaluated over three widely used datasets CUHK03, Market-1501 and DukeMTMC-ReID, and experiments demonstrate its superior robustness and effectiveness as compared with the state of the arts. |
| Tasks | Person Re-Identification |
| Published | 2018-10-13 |
| URL | http://arxiv.org/abs/1810.05866v1 |
| http://arxiv.org/pdf/1810.05866v1.pdf | |
| PWC | https://paperswithcode.com/paper/attention-driven-person-re-identification |
| Repo | |
| Framework | |
Usage of analytic hierarchy process for steganographic inserts detection in images
| Title | Usage of analytic hierarchy process for steganographic inserts detection in images |
| Authors | S. V. Belim, D. E. Vilkhovskiy |
| Abstract | This article presents the method of steganography detection, which is formed by replacing the least significant bit (LSB). Detection is performed by dividing the image into layers and making an analysis of zero-layer of adjacent bits for every bit. First-layer and second-layer are analyzed too. Hierarchies analysis method is used for making decision if current bit is changed. Weighting coefficients as part of the analytic hierarchy process are formed on the values of bits. Then a matrix of corrupted pixels is generated. Visualization of matrix with corrupted pixels allows to determine size, location and presence of the embedded message. Computer experiment was performed. Message was embedded in a bounded rectangular area of the image. This method demonstrated efficiency even at low filling container, less than 10%. Widespread statistical methods are unable to detect this steganographic insert. The location and size of the embedded message can be determined with an error which is not exceeding to five pixels. |
| Tasks | |
| Published | 2018-12-25 |
| URL | http://arxiv.org/abs/1902.11100v1 |
| http://arxiv.org/pdf/1902.11100v1.pdf | |
| PWC | https://paperswithcode.com/paper/usage-of-analytic-hierarchy-process-for |
| Repo | |
| Framework | |
Randomized Prior Functions for Deep Reinforcement Learning
| Title | Randomized Prior Functions for Deep Reinforcement Learning |
| Authors | Ian Osband, John Aslanides, Albin Cassirer |
| Abstract | Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior’ network to each ensemble member. We prove that this approach is efficient with linear representations, provide simple illustrations of its efficacy with nonlinear representations and show that this approach scales to large-scale problems far better than previous attempts. | |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03335v2 |
| http://arxiv.org/pdf/1806.03335v2.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-prior-functions-for-deep |
| Repo | |
| Framework | |
View Extrapolation of Human Body from a Single Image
| Title | View Extrapolation of Human Body from a Single Image |
| Authors | Hao Zhu, Hao Su, Peng Wang, Xun Cao, Ruigang Yang |
| Abstract | We study how to synthesize novel views of human body from a single image. Though recent deep learning based methods work well for rigid objects, they often fail on objects with large articulation, like human bodies. The core step of existing methods is to fit a map from the observable views to novel views by CNNs; however, the rich articulation modes of human body make it rather challenging for CNNs to memorize and interpolate the data well. To address the problem, we propose a novel deep learning based pipeline that explicitly estimates and leverages the geometry of the underlying human body. Our new pipeline is a composition of a shape estimation network and an image generation network, and at the interface a perspective transformation is applied to generate a forward flow for pixel value transportation. Our design is able to factor out the space of data variation and makes learning at each step much easier. Empirically, we show that the performance for pose-varying objects can be improved dramatically. Our method can also be applied on real data captured by 3D sensors, and the flow generated by our methods can be used for generating high quality results in higher resolution. |
| Tasks | Image Generation |
| Published | 2018-04-11 |
| URL | http://arxiv.org/abs/1804.04213v1 |
| http://arxiv.org/pdf/1804.04213v1.pdf | |
| PWC | https://paperswithcode.com/paper/view-extrapolation-of-human-body-from-a |
| Repo | |
| Framework | |
On the Supermodularity of Active Graph-based Semi-supervised Learning with Stieltjes Matrix Regularization
| Title | On the Supermodularity of Active Graph-based Semi-supervised Learning with Stieltjes Matrix Regularization |
| Authors | Pin-Yu Chen, Dennis Wei |
| Abstract | Active graph-based semi-supervised learning (AG-SSL) aims to select a small set of labeled examples and utilize their graph-based relation to other unlabeled examples to aid in machine learning tasks. It is also closely related to the sampling theory in graph signal processing. In this paper, we revisit the original formulation of graph-based SSL and prove the supermodularity of an AG-SSL objective function under a broad class of regularization functions parameterized by Stieltjes matrices. Under this setting, supermodularity yields a novel greedy label sampling algorithm with guaranteed performance relative to the optimal sampling set. Compared to three state-of-the-art graph signal sampling and recovery methods on two real-life community detection datasets, the proposed AG-SSL method attains superior classification accuracy given limited sample budgets. |
| Tasks | Community Detection |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.03273v1 |
| http://arxiv.org/pdf/1804.03273v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-supermodularity-of-active-graph-based |
| Repo | |
| Framework | |
Unsupervised Features Extraction for Binary Similarity Using Graph Embedding Neural Networks
| Title | Unsupervised Features Extraction for Binary Similarity Using Graph Embedding Neural Networks |
| Authors | Roberto Baldoni, Giuseppe Antonio Di Luna, Luca Massarelli, Fabio Petroni, Leonardo Querzoni |
| Abstract | In this paper we consider the binary similarity problem that consists in determining if two binary functions are similar only considering their compiled form. This problem is know to be crucial in several application scenarios, such as copyright disputes, malware analysis, vulnerability detection, etc. The current state-of-the-art solutions in this field work by creating an embedding model that maps binary functions into vectors in $\mathbb{R}^{n}$. Such embedding model captures syntactic and semantic similarity between binaries, i.e., similar binary functions are mapped to points that are close in the vector space. This strategy has many advantages, one of them is the possibility to precompute embeddings of several binary functions, and then compare them with simple geometric operations (e.g., dot product). In [32] functions are first transformed in Annotated Control Flow Graphs (ACFGs) constituted by manually engineered features and then graphs are embedded into vectors using a deep neural network architecture. In this paper we propose and test several ways to compute annotated control flow graphs that use unsupervised approaches for feature learning, without incurring a human bias. Our methods are inspired after techniques used in the natural language processing community (e.g., we use word2vec to encode assembly instructions). We show that our approach is indeed successful, and it leads to better performance than previous state-of-the-art solutions. Furthermore, we report on a qualitative analysis of functions embeddings. We found interesting cases in which embeddings are clustered according to the semantic of the original binary function. |
| Tasks | Graph Embedding, Semantic Similarity, Semantic Textual Similarity, Vulnerability Detection |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09683v2 |
| http://arxiv.org/pdf/1810.09683v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-features-extraction-for-binary |
| Repo | |
| Framework | |
Off-the-Shelf Unsupervised NMT
| Title | Off-the-Shelf Unsupervised NMT |
| Authors | Chris Hokamp, Sebastian Ruder, John Glover |
| Abstract | We frame unsupervised machine translation (MT) in the context of multi-task learning (MTL), combining insights from both directions. We leverage off-the-shelf neural MT architectures to train unsupervised MT models with no parallel data and show that such models can achieve reasonably good performance, competitive with models purpose-built for unsupervised MT. Finally, we propose improvements that allow us to apply our models to English-Turkish, a truly low-resource language pair. |
| Tasks | Machine Translation, Multi-Task Learning, Unsupervised Machine Translation |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02278v1 |
| http://arxiv.org/pdf/1811.02278v1.pdf | |
| PWC | https://paperswithcode.com/paper/off-the-shelf-unsupervised-nmt |
| Repo | |
| Framework | |
Observer-based Adaptive Optimal Output Containment Control problem of Linear Heterogeneous Multi-agent Systems with Relative Output Measurements
| Title | Observer-based Adaptive Optimal Output Containment Control problem of Linear Heterogeneous Multi-agent Systems with Relative Output Measurements |
| Authors | Majid Mazouchi, Mohammad Bagher Naghibi-Sistani, Seyed Kamal Hosseini Sani, Farzaneh Tatari, Hamidreza Modares |
| Abstract | This paper develops an optimal relative output-feedback based solution to the containment control problem of linear heterogeneous multi-agent systems. A distributed optimal control protocol is presented for the followers to not only assure that their outputs fall into the convex hull of the leaders’ output (i.e., the desired or safe region), but also optimizes their transient performance. The proposed optimal control solution is composed of a feedback part, depending of the followers’ state, and a feed-forward part, depending on the convex hull of the leaders’ state. To comply with most real-world applications, the feedback and feed-forward states are assumed to be unavailable and are estimated using two distributed observers. That is, since the followers cannot directly sense their absolute states, a distributed observer is designed that uses only relative output measurements with respect to their neighbors (measured for example by using range sensors in robotic) and the information which is broadcasted by their neighbors to estimate their states. Moreover, another adaptive distributed observer is designed that uses exchange of information between followers over a communication network to estimate the convex hull of the leaders’ state. The proposed observer relaxes the restrictive requirement of knowing the complete knowledge of the leaders’ dynamics by all followers. An off-policy reinforcement learning algorithm on an actor-critic structure is next developed to solve the optimal containment control problem online, using relative output measurements and without requirement of knowing the leaders’ dynamics by all followers. Finally, the theoretical results are verified by numerical simulations. |
| Tasks | |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11411v1 |
| http://arxiv.org/pdf/1803.11411v1.pdf | |
| PWC | https://paperswithcode.com/paper/observer-based-adaptive-optimal-output |
| Repo | |
| Framework | |
Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation
| Title | Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation |
| Authors | Zhong Zhou, Matthias Sperber, Alex Waibel |
| Abstract | We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems. We build a translation system that addresses these challenges using eight European language families as our test ground. Firstly, we add the source and the target family labels and study intra-family and inter-family influences for effective cross-lingual transfer. We achieve an improvement of +9.9 in BLEU score for English-Swedish translation using eight families compared to the single-family multi-source multi-target baseline. Moreover, we find that training on two neighboring families closest to the low-resource language is often enough. Secondly, we construct an ablation study and find that reasonably good results can be achieved even with considerably less target data. Thirdly, we address the variable-binding problem by building an order-preserving named entity translation model. We obtain 60.6% accuracy in qualitative evaluation where our translations are akin to human translations in a preliminary study. |
| Tasks | Cross-Lingual Transfer |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1804.07878v2 |
| http://arxiv.org/pdf/1804.07878v2.pdf | |
| PWC | https://paperswithcode.com/paper/massively-parallel-cross-lingual-learning-in |
| Repo | |
| Framework | |
Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing
| Title | Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing |
| Authors | Somnath Basu Roy Chowdhury, K M Annervaz, Ambedkar Dukkipati |
| Abstract | Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize solely based on the data that is presented with during the training. In this work, we propose an inductive transfer learning method that can augment learning models by infusing similar instances from different learning tasks in the Natural Language Processing (NLP) domain. We propose to use instance representations from a source dataset, \textit{without inheriting anything} from the source learning model. Representations of the instances of \textit{source} & \textit{target} datasets are learned, retrieval of relevant source instances is performed using soft-attention mechanism and \textit{locality sensitive hashing}, and then, augmented into the model during training on the target dataset. Our approach simultaneously exploits the local \textit{instance level information} as well as the macro statistical viewpoint of the dataset. Using this approach we have shown significant improvements for three major news classification datasets over the baseline. Experimental evaluations also show that the proposed approach reduces dependency on labeled data by a significant margin for comparable performance. With our proposed cross dataset learning procedure we show that one can achieve competitive/better performance than learning from a single dataset. |
| Tasks | Transfer Learning |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.05934v1 |
| http://arxiv.org/pdf/1802.05934v1.pdf | |
| PWC | https://paperswithcode.com/paper/instance-based-inductive-deep-transfer |
| Repo | |
| Framework | |
A Statistical Approach to Adult Census Income Level Prediction
| Title | A Statistical Approach to Adult Census Income Level Prediction |
| Authors | Navoneel Chakrabarty, Sanket Biswas |
| Abstract | The prominent inequality of wealth and income is a huge concern especially in the United States. The likelihood of diminishing poverty is one valid reason to reduce the world’s surging level of economic inequality. The principle of universal moral equality ensures sustainable development and improve the economic stability of a nation. Governments in different countries have been trying their best to address this problem and provide an optimal solution. This study aims to show the usage of machine learning and data mining techniques in providing a solution to the income equality problem. The UCI Adult Dataset has been used for the purpose. Classification has been done to predict whether a person’s yearly income in US falls in the income category of either greater than 50K Dollars or less equal to 50K Dollars category based on a certain set of attributes. The Gradient Boosting Classifier Model was deployed which clocked the highest accuracy of 88.16%, eventually breaking the benchmark accuracy of existing works. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.10076v1 |
| http://arxiv.org/pdf/1810.10076v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-statistical-approach-to-adult-census-income |
| Repo | |
| Framework | |
A Deep Generative Model for Semi-Supervised Classification with Noisy Labels
| Title | A Deep Generative Model for Semi-Supervised Classification with Noisy Labels |
| Authors | Maxime Langevin, Edouard Mehlman, Jeffrey Regier, Romain Lopez, Michael I. Jordan, Nir Yosef |
| Abstract | Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for label noise. Additionally, the derivation of M-VAE gives new theoretical insights into the popular M1+M2 semi-supervised model. |
| Tasks | |
| Published | 2018-09-16 |
| URL | http://arxiv.org/abs/1809.05957v1 |
| http://arxiv.org/pdf/1809.05957v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-generative-model-for-semi-supervised |
| Repo | |
| Framework | |
Distributed Learning from Interactions in Social Networks
| Title | Distributed Learning from Interactions in Social Networks |
| Authors | Francesco Sasso, Angelo Coluccia, Giuseppe Notarstefano |
| Abstract | We consider a network scenario in which agents can evaluate each other according to a score graph that models some interactions. The goal is to design a distributed protocol, run by the agents, that allows them to learn their unknown state among a finite set of possible values. We propose a Bayesian framework in which scores and states are associated to probabilistic events with unknown parameters and hyperparameters, respectively. We show that each agent can learn its state by means of a local Bayesian classifier and a (centralized) Maximum-Likelihood (ML) estimator of parameter-hyperparameter that combines plain ML and Empirical Bayes approaches. By using tools from graphical models, which allow us to gain insight on conditional dependencies of scores and states, we provide a relaxed probabilistic model that ultimately leads to a parameter-hyperparameter estimator amenable to distributed computation. To highlight the appropriateness of the proposed relaxation, we demonstrate the distributed estimators on a social interaction set-up for user profiling. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01003v1 |
| http://arxiv.org/pdf/1806.01003v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-learning-from-interactions-in |
| Repo | |
| Framework | |
