January 31, 2020

3151 words 15 mins read

Paper Group ANR 160

Sentiment analysis model for Twitter data in Polish language. Hierarchical Semantic Correspondence Learning for Post-Discharge Patient Mortality Prediction. Performance Evaluation of Supervised Machine Learning Techniques for Efficient Detection of Emotions from Online Content. Online Multi-target regression trees with stacked leaf models. Learning …

Sentiment analysis model for Twitter data in Polish language


Title	Sentiment analysis model for Twitter data in Polish language
Authors	Karol Chlasta
Abstract	Text mining analysis of tweets gathered during Polish presidential election on May 10th, 2015. The project included implementation of engine to retrieve information from Twitter, building document corpora, corpora cleaning, and creating Term-Document Matrix. Each tweet from the text corpora was assigned a category based on its sentiment score. The score was calculated using the number of positive and/or negative emoticons and Polish words in each document. The result data set was used to train and test four machine learning classifiers, to select these providing most accurate automatic tweet classification results. The Naive Bayes and Maximum Entropy algorithms achieved the best accuracy of respectively 71.76% and 77.32%. All implementation tasks were completed using R programming language.
Tasks	Sentiment Analysis
Published	2019-11-03
URL	https://arxiv.org/abs/1911.00985v1
PDF	https://arxiv.org/pdf/1911.00985v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-model-for-twitter-data-in
Repo
Framework

Hierarchical Semantic Correspondence Learning for Post-Discharge Patient Mortality Prediction


Title	Hierarchical Semantic Correspondence Learning for Post-Discharge Patient Mortality Prediction
Authors	Shaika Chowdhury, Chenwei Zhang, Philip S. Yu, Yuan Luo
Abstract	Predicting patient mortality is an important and challenging problem in the healthcare domain, especially for intensive care unit (ICU) patients. Electronic health notes serve as a rich source for learning patient representations, that can facilitate effective risk assessment. However, a large portion of clinical notes are unstructured and also contain domain specific terminologies, from which we need to extract structured information. In this paper, we introduce an embedding framework to learn semantically-plausible distributed representations of clinical notes that exploits the semantic correspondence between the unstructured texts and their corresponding structured knowledge, known as semantic frame, in a hierarchical fashion. Our approach integrates text modeling and semantic correspondence learning into a single model that comprises 1) an unstructured embedding module that makes use of self-similarity matrix representations in order to inject structural regularities of different segments inherent in clinical texts to promote local coherence, 2) a structured embedding module to embed the semantic frames (e.g., UMLS semantic types) with deep ConvNet and 3) a hierarchical semantic correspondence module that embeds by enhancing the interactions between text-semantic frame embedding pairs at multiple levels (i.e., words, sentence, note). Evaluations on multiple embedding benchmarks on post discharge intensive care patient mortality prediction tasks demonstrate its effectiveness compared to approaches that do not exploit the semantic interactions between structured and unstructured information present in clinical notes.
Tasks	Mortality Prediction
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06492v1
PDF	https://arxiv.org/pdf/1910.06492v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-semantic-correspondence-learning
Repo
Framework

Performance Evaluation of Supervised Machine Learning Techniques for Efficient Detection of Emotions from Online Content


Title	Performance Evaluation of Supervised Machine Learning Techniques for Efficient Detection of Emotions from Online Content
Authors	Muhammad Zubair Asghar, Fazli Subhan, Muhammad Imran, Fazal Masud Kundi, Shahboddin Shamshirband, Amir Mosavi, Peter Csiba, Annamaria R. Varkonyi-Koczy
Abstract	Emotion detection from the text is an important and challenging problem in text analytics. The opinion-mining experts are focusing on the development of emotion detection applications as they have received considerable attention of online community including users and business organization for collecting and interpreting public emotions. However, most of the existing works on emotion detection used less efficient machine learning classifiers with limited datasets, resulting in performance degradation. To overcome this issue, this work aims at the evaluation of the performance of different machine learning classifiers on a benchmark emotion dataset. The experimental results show the performance of different machine learning classifiers in terms of different evaluation metrics like precision, recall ad f-measure. Finally, a classifier with the best performance is recommended for the emotion classification.
Tasks	Emotion Classification, Opinion Mining
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01587v1
PDF	https://arxiv.org/pdf/1908.01587v1.pdf
PWC	https://paperswithcode.com/paper/performance-evaluation-of-supervised-machine
Repo
Framework

Online Multi-target regression trees with stacked leaf models


Title	Online Multi-target regression trees with stacked leaf models
Authors	Saulo Martiello Mastelini, Sylvio Barbon Jr., André Carlos Ponce de Leon Ferreira de Carvalho
Abstract	One of the current challenges in machine learning is how to deal with data coming at increasing rates in data streams. New predictive learning strategies are needed to cope with the high throughput data and concept drift. One of the data stream mining tasks where new learning strategies are needed is multi-target regression, due to its applicability in a high number of real world problems. While reliable and effective learning strategies have been proposed for batch multi-target regression, few have been proposed for multi-target online learning in data streams. Besides, most of the existing solutions do not consider the occurrence of inter-target correlations when making predictions. In this work, we propose a novel online learning strategy for multi-target regression in data streams. The proposed strategy extends existing online decision tree learning algorithm to explore inter-target dependencies while making predictions. For such, the proposed strategy, called Stacked Single-target Hoeffding Tree (SST-HT), uses the inter-target dependencies as an additional information source to enhance predictive accuracy. Throughout an extensive experimental setup, we evaluate our proposal against state-of-the-art decision tree-based algorithms for online multi-target regression. According to the experimental results, SST-HT presents superior predictive accuracy, with a small increase in the processing time and memory requirements.
Tasks
Published	2019-03-29
URL	https://arxiv.org/abs/1903.12483v4
PDF	https://arxiv.org/pdf/1903.12483v4.pdf
PWC	https://paperswithcode.com/paper/online-multi-target-regression-trees-with
Repo
Framework

Learning mappings onto regularized latent spaces for biometric authentication


Title	Learning mappings onto regularized latent spaces for biometric authentication
Authors	Matteo Testa, Arslan Ali, Tiziano Bianchi, Enrico Magli
Abstract	We propose a novel architecture for generic biometric authentication based on deep neural networks: RegNet. Differently from other methods, RegNet learns a mapping of the input biometric traits onto a target distribution in a well-behaved space in which users can be separated by means of simple and tunable boundaries. More specifically, authorized and unauthorized users are mapped onto two different and well behaved Gaussian distributions. The novel approach of learning the mapping instead of the boundaries further avoids the problem encountered in typical classifiers for which the learnt boundaries may be complex and difficult to analyze. RegNet achieves high performance in terms of security metrics such as Equal Error Rate (EER), False Acceptance Rate (FAR) and Genuine Acceptance Rate (GAR). The experiments we conducted on publicly available datasets of face and fingerprint confirm the effectiveness of the proposed system.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08764v1
PDF	https://arxiv.org/pdf/1911.08764v1.pdf
PWC	https://paperswithcode.com/paper/learning-mappings-onto-regularized-latent
Repo
Framework

Private Protocols for U-Statistics in the Local Model and Beyond


Title	Private Protocols for U-Statistics in the Local Model and Beyond
Authors	James Bell, Aurélien Bellet, Adrià Gascón, Tejas Kulkarni
Abstract	In this paper, we study the problem of computing $U$-statistics of degree $2$, i.e., quantities that come in the form of averages over pairs of data points, in the local model of differential privacy (LDP). The class of $U$-statistics covers many statistical estimates of interest, including Gini mean difference, Kendall’s tau coefficient and Area under the ROC Curve (AUC), as well as empirical risk measures for machine learning problems such as ranking, clustering and metric learning. We first introduce an LDP protocol based on quantizing the data into bins and applying randomized response, which guarantees an $\epsilon$-LDP estimate with a Mean Squared Error (MSE) of $O(1/\sqrt{n}\epsilon)$ under regularity assumptions on the $U$-statistic or the data distribution. We then propose a specialized protocol for AUC based on a novel use of hierarchical histograms that achieves MSE of $O(\alpha^3/n\epsilon^2)$ for arbitrary data distribution. We also show that 2-party secure computation allows to design a protocol with MSE of $O(1/n\epsilon^2)$, without any assumption on the kernel function or data distribution and with total communication linear in the number of users $n$. Finally, we evaluate the performance of our protocols through experiments on synthetic and real datasets.
Tasks	Metric Learning
Published	2019-10-09
URL	https://arxiv.org/abs/1910.03861v2
PDF	https://arxiv.org/pdf/1910.03861v2.pdf
PWC	https://paperswithcode.com/paper/private-protocols-for-u-statistics-in-the
Repo
Framework

Addressing Time Bias in Bipartite Graph Ranking for Important Node Identification


Title	Addressing Time Bias in Bipartite Graph Ranking for Important Node Identification
Authors	Hao Liao, Jiao Wu, Mingyang Zhou, Alexandre Vidmer
Abstract	The goal of the ranking problem in networks is to rank nodes from best to worst, according to a chosen criterion. In this work, we focus on ranking the nodes according to their quality. The problem of ranking the nodes in bipartite networks is valuable for many real-world applications. For instance, high-quality products can be promoted on an online shop or highly reputed restaurants attract more people on venues review platforms. However, many classical ranking algorithms share a common drawback: they tend to rank older movies higher than newer movies, though some newer movies may have a high quality. This time bias originates from the fact that older nodes in a network tend to have more connections than newer ones. In the study, we develop a ranking method using a rebalance approach to diminish the time bias of the rankings in bipartite graphs.
Tasks	Graph Ranking
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12558v1
PDF	https://arxiv.org/pdf/1911.12558v1.pdf
PWC	https://paperswithcode.com/paper/addressing-time-bias-in-bipartite-graph
Repo
Framework

Generative Hierarchical Models for Parts, Objects, and Scenes


Title	Generative Hierarchical Models for Parts, Objects, and Scenes
Authors	Fei Deng, Zhuo Zhi, Sungjin Ahn
Abstract	Compositional structures between parts and objects are inherent in natural scenes. Modeling such compositional hierarchies via unsupervised learning can bring various benefits such as interpretability and transferability, which are important in many downstream tasks. In this paper, we propose the first deep latent variable model, called RICH, for learning Representation of Interpretable Compositional Hierarchies. At the core of RICH is a latent scene graph representation that organizes the entities of a scene into a tree structure according to their compositional relationships. During inference, taking top-down approach, RICH is able to use higher-level representation to guide lower-level decomposition. This avoids the difficult problem of routing between parts and objects that is faced by bottom-up approaches. In experiments on images containing multiple objects with different part compositions, we demonstrate that RICH is able to learn the latent compositional hierarchy and generate imaginary scenes.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09119v1
PDF	https://arxiv.org/pdf/1910.09119v1.pdf
PWC	https://paperswithcode.com/paper/generative-hierarchical-models-for-parts-1
Repo
Framework

Higher-order Count Sketch: Dimensionality Reduction That Retains Efficient Tensor Operations


Title	Higher-order Count Sketch: Dimensionality Reduction That Retains Efficient Tensor Operations
Authors	Yang Shi, Animashree Anandkumar
Abstract	Sketching is a randomized dimensionality-reduction method that aims to preserve relevant information in large-scale datasets. Count sketch is a simple popular sketch which uses a randomized hash function to achieve compression. In this paper, we propose a novel extension known as Higher-order Count Sketch (HCS). While count sketch uses a single hash function, HCS uses multiple (smaller) hash functions for sketching. HCS reshapes the input (vector) data into a higher-order tensor and employs a tensor product of the random hash functions to compute the sketch. This results in an exponential saving (with respect to the order of the tensor) in the memory requirements of the hash functions, under certain conditions on the input data. Furthermore, when the input data itself has an underlying structure in the form of various tensor representations such as the Tucker decomposition, we obtain significant advantages. We derive efficient (approximate) computation of various tensor operations such as tensor products and tensor contractions directly on the sketched data. Thus, HCS is the first sketch to fully exploit the multi-dimensional nature of higher-order tensors. We apply HCS to tensorized neural networks where we replace fully connected layers with sketched tensor operations. We achieve nearly state of the art accuracy with significant compression on the image classification benchmark.
Tasks	Dimensionality Reduction, Image Classification
Published	2019-01-31
URL	https://arxiv.org/abs/1901.11261v5
PDF	https://arxiv.org/pdf/1901.11261v5.pdf
PWC	https://paperswithcode.com/paper/multi-dimensional-tensor-sketch
Repo
Framework

Ensembling methods for countrywide short term forecasting of gas demand


Title	Ensembling methods for countrywide short term forecasting of gas demand
Authors	Emanuele Fabbiani, Andrea Marziali, Giuseppe De Nicolao
Abstract	Gas demand is made of three components: Residential, Industrial, and Thermoelectric Gas Demand. Herein, the one-day-ahead prediction of each component is studied, using Italian data as a case study. Statistical properties and relationships with temperature are discussed, as a preliminary step for an effective feature selection. Nine “base forecasters” are implemented and compared: Ridge Regression, Gaussian Processes, Nearest Neighbours, Artificial Neural Networks, Torus Model, LASSO, Elastic Net, Random Forest, and Support Vector Regression (SVR). Based on them, four ensemble predictors are crafted: simple average, weighted average, subset average, and SVR aggregation. We found that ensemble predictors perform consistently better than base ones. Moreover, our models outperformed Transmission System Operator (TSO) predictions in a two-year out-of-sample validation. Such results suggest that combining predictors may lead to significant performance improvements in gas demand forecasting.
Tasks	Feature Selection, Gaussian Processes
Published	2019-01-31
URL	https://arxiv.org/abs/1902.00097v2
PDF	https://arxiv.org/pdf/1902.00097v2.pdf
PWC	https://paperswithcode.com/paper/short-term-forecasting-of-italian-gas-demand
Repo
Framework

Provable Gradient Variance Guarantees for Black-Box Variational Inference


Title	Provable Gradient Variance Guarantees for Black-Box Variational Inference
Authors	Justin Domke
Abstract	Recent variational inference methods use stochastic gradient estimators whose variance is not well understood. Theoretical guarantees for these estimators are important to understand when these methods will or will not work. This paper gives bounds for the common “reparameterization” estimators when the target is smooth and the variational family is a location-scale distribution. These bounds are unimprovable and thus provide the best possible guarantees under the stated assumptions.
Tasks
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08241v2
PDF	https://arxiv.org/pdf/1906.08241v2.pdf
PWC	https://paperswithcode.com/paper/provable-gradient-variance-guarantees-for
Repo
Framework

A Case Study of Deep-Learned Activations via Hand-Crafted Audio Features


Title	A Case Study of Deep-Learned Activations via Hand-Crafted Audio Features
Authors	Olga Slizovskaia, Emilia Gómez, Gloria Haro
Abstract	The explainability of Convolutional Neural Networks (CNNs) is a particularly challenging task in all areas of application, and it is notably under-researched in music and audio domain. In this paper, we approach explainability by exploiting the knowledge we have on hand-crafted audio features. Our study focuses on a well-defined MIR task, the recognition of musical instruments from user-generated music recordings. We compute the similarity between a set of traditional audio features and representations learned by CNNs. We also propose a technique for measuring the similarity between activation maps and audio features which typically presented in the form of a matrix, such as chromagrams or spectrograms. We observe that some neurons’ activations correspond to well-known classical audio features. In particular, for shallow layers, we found similarities between activations and harmonic and percussive components of the spectrum. For deeper layers, we compare chromagrams with high-level activation maps as well as loudness and onset rate with deep-learned embeddings.
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01813v1
PDF	https://arxiv.org/pdf/1907.01813v1.pdf
PWC	https://paperswithcode.com/paper/a-case-study-of-deep-learned-activations-via
Repo
Framework

Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning


Title	Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
Authors	Limeng Qiao, Yemin Shi, Jia Li, Yaowei Wang, Tiejun Huang, Yonghong Tian
Abstract	Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier with the capability of adapting to specific tasks with severely limited data still remains in this domain. To this end, we propose a Transductive Episodic-wise Adaptive Metric (TEAM) framework for few-shot learning, by integrating the meta-learning paradigm with both deep metric learning and transductive inference. With exploring the pairwise constraints and regularization prior within each task, we explicitly formulate the adaptation procedure into a standard semi-definite programming problem. By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space. Moreover, we further leverage an attention-based bi-directional similarity strategy for extracting the more robust relationship between queries and prototypes. Extensive experiments on three benchmark datasets show that our framework is superior to other existing approaches and achieves the state-of-the-art performance in the few-shot literature.
Tasks	Few-Shot Learning, Meta-Learning, Metric Learning
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02224v1
PDF	https://arxiv.org/pdf/1910.02224v1.pdf
PWC	https://paperswithcode.com/paper/transductive-episodic-wise-adaptive-metric
Repo
Framework

Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation


Title	Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation
Authors	Gopal Sharma, Evangelos Kalogerakis, Subhransu Maji
Abstract	User generated 3D shapes in online repositories contain rich information about surfaces, primitives, and their geometric relations, often arranged in a hierarchy. We present a framework for learning representations of 3D shapes that reflect the information present in this meta data and show that it leads to improved generalization for semantic segmentation tasks. Our approach is a point embedding network that generates a vectorial representation of the 3D points such that it reflects the grouping hierarchy and tag data. The main challenge is that the data is noisy and highly variable. To this end, we present a tree-aware metric-learning approach and demonstrate that such learned embeddings offer excellent transfer to semantic segmentation tasks, especially when training data is limited. Our approach reduces the relative error by $10.2%$ with $8$ training examples, by $11.72%$ with $120$ training examples on the ShapeNet semantic segmentation benchmark, in comparison to the network trained from scratch. By utilizing tag data the relative error is reduced by $12.8%$ with $8$ training examples, in comparison to the network trained from scratch. These improvements come at no additional labeling cost as the meta data is freely available.
Tasks	Metric Learning, Semantic Segmentation
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01269v1
PDF	https://arxiv.org/pdf/1910.01269v1.pdf
PWC	https://paperswithcode.com/paper/learning-point-embeddings-from-shape
Repo
Framework

Computational Attention System for Children, Adults and Elderly


Title	Computational Attention System for Children, Adults and Elderly
Authors	Onkar Krishna, Kiyoharu Aizawa, Go Irie
Abstract	The existing computational visual attention systems have focused on the objective to basically simulate and understand the concept of visual attention system in adults. Consequently, the impact of observer’s age in scene viewing behavior has rarely been considered. This study quantitatively analyzed the age-related differences in gaze landings during scene viewing for three different class of images: naturals, man-made, and fractals. Observer’s of different age-group have shown different scene viewing tendencies independent to the class of the image viewed. Several interesting observations are drawn from the results. First, gaze landings for man-made dataset showed that whereas child observers focus more on the scene foreground, i.e., locations that are near, elderly observers tend to explore the scene background, i.e., locations farther in the scene. Considering this result a framework is proposed in this paper to quantitatively measure the depth bias tendency across age groups. Second, the quantitative analysis results showed that children exhibit the lowest exploratory behavior level but the highest central bias tendency among the age groups and across the different scene categories. Third, inter-individual similarity metrics reveal that an adult had significantly lower gaze consistency with children and elderly compared to other adults for all the scene categories. Finally, these analysis results were consequently leveraged to develop a more accurate age-adapted saliency model independent to the image type. The prediction accuracy suggests that our model fits better to the collected eye-gaze data of the observers belonging to different age groups than the existing models do.
Tasks
Published	2019-04-18
URL	http://arxiv.org/abs/1904.12628v1
PDF	http://arxiv.org/pdf/1904.12628v1.pdf
PWC	https://paperswithcode.com/paper/190412628
Repo
Framework