PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1907.09669

EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification

This paper describes our approach to the EmotionX-2019, the shared task of SocialNLP 2019. To detect emotion for each utterance of two datasets from the TV show Friends and Facebook chat log EmotionPush, we propose two-step deep learning based methodology: (i) encode each of the utterance into a sequence of vectors that represent its meaning; and (ii) use a simply softmax classifier to predict one of the emotions amongst four candidates that an utterance may carry. Notice that the source of labeled utterances is not rich, we utilise a well-trained model, known as BERT, to transfer part of the knowledge learned from a large amount of corpus to our model. We then focus on fine-tuning our model until it well fits to the in-domain data. The performance of the proposed model is evaluated by micro-F1 scores, i.e., 79.1% and 86.2% for the testsets of Friends and EmotionPush, respectively. Our model ranks 3rd among 11 submissions.

arXiv:1907.09647

Few-shot Learning for Domain-specific Fine-grained Image Classification

Learning to recognize novel visual categories from a few examples is a challenging task for machines in real-world industrial applications. In contrast, humans have the ability to discriminate even similar objects with little supervision. This paper attempts to address the few shot fine-grained image classification problem. We propose a feature fusion model to explore discriminative features by focusing on key regions. The model utilizes the focus area location mechanism to discover the perceptually similar regions among objects. High-order integration is employed to capture the interaction information among intra-parts. We also design a Center Neighbor Loss to form robust embedding space distributions. Furthermore, we build a typical fine-grained and few-shot learning dataset miniPPlankton from the real-world application in the area of marine ecological environments. Extensive experiments are carried out to validate the performance of our method. The results demonstrate that our model achieves competitive performance compared with state-of-the-art models. Our work is a valuable complement to the model domain-specific industrial applications.

arXiv:1907.09613공식 코드 · Papers with Code

Incremental and Decremental Fuzzy Bounded Twin Support Vector Machine

In this paper we present an incremental variant of the Twin Support Vector Machine (TWSVM) called Fuzzy Bounded Twin Support Vector Machine (FBTWSVM) to deal with large datasets and learning from data streams. We combine the TWSVM with a fuzzy membership function, so that each input has a different contribution to each hyperplane in a binary classifier. To solve the pair of quadratic programming problems (QPPs) we use a dual coordinate descent algorithm with a shrinking strategy, and to obtain a robust classification with a fast training we propose the use of a Fourier Gaussian approximation function with our linear FBTWSVM. Inspired by the shrinking technique, the incremental algorithm re-utilizes part of the training method with some heuristics, while the decremental procedure is based on a scored window. The FBTWSVM is also extended for multi-class problems by combining binary classifiers using a Directed Acyclic Graph (DAG) approach. Moreover, we analyzed the theoretical foundations properties of the proposed approach and its extension, and the experimental results on benchmark datasets indicate that the FBTWSVM has a fast training and retraining process while maintaining a robust classification performance.

arXiv:1907.09567

The Effect of Visual Design in Image Classification

Financial companies continuously analyze the state of the markets to rethink and adjust their investment strategies. While the analysis is done on the digital form of data, decisions are often made based on graphical representations in white papers or presentation slides. In this study, we examine whether binary decisions are better to be decided based on the numeric or the visual representation of the same data. Using two data sets, a matrix of numerical data with spatial dependencies and financial data describing the state of the S&P index, we compare the results of supervised classification based on the original numerical representation and the visual transformation of the same data. We show that, for these data sets, the visual transformation results in higher predictability skill compared to the original form of the data. We suggest thinking of the visual representation of numeric data, effectively, as a combination of dimensional reduction and feature engineering techniques. In particular, if the visual layout encapsulates the full complexity of the data. In this view, thoughtful visual design can guard against overfitting, or introduce new features -- all of which benefit the learning process, and effectively lead to better recognition of meaningful patterns.

arXiv:1907.09565

Classification with the matrix-variate-$t$ distribution

Matrix-variate distributions can intuitively model the dependence structure of matrix-valued observations that arise in applications with multivariate time series, spatio-temporal or repeated measures. This paper develops an Expectation-Maximization algorithm for discriminant analysis and classification with matrix-variate $t$-distributions. The methodology shows promise on simulated datasets or when applied to the forensic matching of fractured surfaces or the classification of functional Magnetic Resonance, satellite or hand gestures images.

arXiv:1907.09495

IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the 'node-orderless' property. Normally, adjacency matrices will cast an artificial and random node-order on the graphs, which renders the performance of deep models on graph classification tasks extremely erratic, and the representations learned by such models lack clear interpretability. To eliminate the unnecessary node-order constraint, we propose a novel model named Isomorphic Neural Network (IsoNN), which learns the graph representation by extracting its isomorphic features via the graph matching between input graph and templates. IsoNN has two main components: graph isomorphic feature extraction component and classification component. The graph isomorphic feature extraction component utilizes a set of subgraph templates as the kernel variables to learn the possible subgraph patterns existing in the input graph and then computes the isomorphic features. A set of permutation matrices is used in the component to break the node-order brought by the matrix representation. Three fully-connected layers are used as the classification component in IsoNN. Extensive experiments are conducted on benchmark datasets, the experimental results can demonstrate the effectiveness of ISONN, especially compared with both classic and state-of-the-art graph classification methods.

arXiv:1907.10046

Trading via Image Classification

The art of systematic financial trading evolved with an array of approaches, ranging from simple strategies to complex algorithms all relying, primary, on aspects of time-series analysis. Recently, after visiting the trading floor of a leading financial institution, we noticed that traders always execute their trade orders while observing images of financial time-series on their screens. In this work, we built upon the success in image recognition and examine the value in transforming the traditional time-series analysis to that of image classification. We create a large sample of financial time-series images encoded as candlestick (Box and Whisker) charts and label the samples following three algebraically-defined binary trade strategies. Using the images, we train over a dozen machine-learning classification models and find that the algorithms are very efficient in recovering the complicated, multiscale label-generating rules when the data is represented visually. We suggest that the transformation of continuous numeric time-series classification problem to a vision problem is useful for recovering signals typical of technical analysis.

arXiv:1907.09729

Invertible Network for Classification and Biomarker Selection for ASD

Determining biomarkers for autism spectrum disorder (ASD) is crucial to understanding its mechanisms. Recently deep learning methods have achieved success in the classification task of ASD using fMRI data. However, due to the black-box nature of most deep learning models, it's hard to perform biomarker selection and interpret model decisions. The recently proposed invertible networks can accurately reconstruct the input from its output, and have the potential to unravel the black-box representation. Therefore, we propose a novel method to classify ASD and identify biomarkers for ASD using the connectivity matrix calculated from fMRI as the input. Specifically, with invertible networks, we explicitly determine the decision boundary and the projection of data points onto the boundary. Like linear classifiers, the difference between a point and its projection onto the decision boundary can be viewed as the explanation. We then define the importance as the explanation weighted by the gradient of prediction $w.r.t$ the input, and identify biomarkers based on this importance measure. We perform a regression task to further validate our biomarker selection: compared to using all edges in the connectivity matrix, using the top 10\% important edges we generate a lower regression error on 6 different severity scores. Our experiments show that the invertible network is both effective at ASD classification and interpretable, allowing for discovery of reliable biomarkers.

arXiv:1907.09708

Node Attribute Generation on Graphs

Graph structured data provide two-fold information: graph structures and node attributes. Numerous graph-based algorithms rely on both information to achieve success in supervised tasks, such as node classification and link prediction. However, node attributes could be missing or incomplete, which significantly deteriorates the performance. The task of node attribute generation aims to generate attributes for those nodes whose attributes are completely unobserved. This task benefits many real-world problems like profiling, node classification and graph data augmentation. To tackle this task, we propose a deep adversarial learning based method to generate node attributes; called node attribute neural generator (NANG). NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities. We thus use this latent representation as a bridge to convert information from one modality to another. We further introduce practical applications to quantify the performance of node attribute generation. Extensive experiments are conducted on four real-world datasets and the empirical results show that node attributes generated by the proposed method are high-qualitative and beneficial to other applications. The datasets and codes are available online.

arXiv:1907.08696

Multi-modal Sentiment Analysis using Deep Canonical Correlation Analysis

This paper learns multi-modal embeddings from text, audio, and video views/modes of data in order to improve upon down-stream sentiment classification. The experimental framework also allows investigation of the relative contributions of the individual views in the final multi-modal embedding. Individual features derived from the three views are combined into a multi-modal embedding using Deep Canonical Correlation Analysis (DCCA) in two ways i) One-Step DCCA and ii) Two-Step DCCA. This paper learns text embeddings using BERT, the current state-of-the-art in text encoders. We posit that this highly optimized algorithm dominates over the contribution of other views, though each view does contribute to the final result. Classification tasks are carried out on two benchmark datasets and on a new Debate Emotion data set, and together these demonstrate that the one-Step DCCA outperforms the current state-of-the-art in learning multi-modal embeddings.

arXiv:1907.09204

Domain Adaptation for One-Class Classification: Monitoring the Health of Critical Systems Under Limited Information

The failure of a complex and safety critical industrial asset can have extremely high consequences. Close monitoring for early detection of abnormal system conditions is therefore required. Data-driven solutions to this problem have been limited for two reasons: First, safety critical assets are designed and maintained to be highly reliable and faults are rare. Fault detection can thus not be solved with supervised learning. Second, complex industrial systems usually have long lifetime during which they face very different operating conditions. In the early life of the system, the collected data is probably not representative of future operating conditions, making it challenging to train a robust model. In this paper, we propose a methodology to monitor the systems in their early life. To do so, we enhance the training dataset with other units from a fleet, for which longer observations are available. Since each unit has its own specificity, we propose to extract features made independent of their origin by three unsupervised feature alignment techniques. First, using a variational encoder, we impose a shared probabilistic encoder/decoder for both units. Second, we introduce a new loss designed to conserve inter-point spacial relationships between the input and the learned features. Last, we propose to train in an adversarial manner a discriminator on the origin of the features. Once aligned, the features are fed to a one-class classifier to monitor the health of the system. By exploring the different combinations of the proposed alignment strategies, and by testing them on a real case study, a fleet composed of 112 power plants operated in different geographical locations and under very different operating regimes, we demonstrate that this alignment is necessary and beneficial.

arXiv:1907.09013

Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classification

Recent research has helped to cultivate growing awareness that machine learning systems fueled by big data can create or exacerbate troubling disparities in society. Much of this research comes from outside of the practicing data science community, leaving its members with little concrete guidance to proactively address these concerns. This article introduces issues of discrimination to the data science community on its own terms. In it, we tour the familiar data mining process while providing a taxonomy of common practices that have the potential to produce unintended discrimination. We also survey how discrimination is commonly measured, and suggest how familiar development processes can be augmented to mitigate systems' discriminatory potential. We advocate that data scientists should be intentional about modeling and reducing discriminatory outcomes. Without doing so, their efforts will result in perpetuating any systemic discrimination that may exist, but under a misleading veil of data-driven objectivity.

arXiv:1907.09000

Image Classification with Hierarchical Multigraph Networks

Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data. Despite being general, GCNs are admittedly inferior to convolutional neural networks (CNNs) when applied to vision tasks, mainly due to the lack of domain knowledge that is hardcoded into CNNs, such as spatially oriented translation invariant filters. However, a great advantage of GCNs is the ability to work on irregular inputs, such as superpixels of images. This could significantly reduce the computational cost of image reasoning tasks. Another key advantage inherent to GCNs is the natural ability to model multirelational data. Building upon these two promising properties, in this work, we show best practices for designing GCNs for image classification; in some cases even outperforming CNNs on the MNIST, CIFAR-10 and PASCAL image datasets.

arXiv:1907.08968

Infant Mortality Prediction using Birth Certificate Data

The Infant Mortality Rate (IMR) is the number of infants per 1000 that do not survive until their first birthday. It is an important metric providing information about infant health but it also measures the society's general health status. Despite the high level of prosperity in the U.S.A., the country's IMR is higher than that of many other developed countries. Additionally, the U.S.A. exhibits persistent inequalities in the IMR across different racial and ethnic groups. In this paper, we study the infant mortality prediction using features extracted from birth certificates. We are interested in training classification models to decide whether an infant will survive or not. We focus on exploring and understanding the importance of features in subsets of the population; we compare models trained for individual races to general models. Our evaluation shows that our methodology outperforms standard classification methods used by epidemiology researchers.

arXiv:1907.08962

Logical Classification of Partially Ordered Data

Issues concerning intelligent data analysis occurring in machine learning are investigated. A scheme for synthesizing correct supervised classification procedures is proposed. These procedures are focused on specifying partial order relations on sets of feature values; they are based on a generalization of the classical concepts of logical classification. It is shown that learning the correct logical classifier requires an intractable discrete problem to be solved. This is the dualization problem over products of partially ordered sets. The matrix formulation of this problem is given. The effectiveness of the proposed approach to the supervised classification problem is illustrated on model and real-life data.

arXiv:1907.08952

An Interpretable Compression and Classification System: Theory and Applications

This study proposes a low-complexity interpretable classification system. The proposed system contains three main modules including feature extraction, feature reduction, and classification. All of them are linear. Thanks to the linear property, the extracted and reduced features can be inversed to original data, like a linear transform such as Fourier transform, so that one can quantify and visualize the contribution of individual features towards the original data. Also, the reduced features and reversibility naturally endure the proposed system ability of data compression. This system can significantly compress data with a small percent deviation between the compressed and the original data. At the same time, when the compressed data is used for classification, it still achieves high testing accuracy. Furthermore, we observe that the extracted features of the proposed system can be approximated to uncorrelated Gaussian random variables. Hence, classical theory in estimation and detection can be applied for classification. This motivates us to propose using a MAP (maximum a posteriori) based classification method. As a result, the extracted features and the corresponding performance have statistical meaning and mathematically interpretable. Simulation results show that the proposed classification system not only enjoys significant reduced training and testing time but also high testing accuracy compared to the conventional schemes.

arXiv:1907.08937공식 코드 · Papers with Code

Quantifying Similarity between Relations with Fact Distribution

We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases. Specifically, our approach is based on the divergence between the conditional probability distributions over entity pairs. In this paper, these distributions are parameterized by a very simple neural network. Although computing the exact similarity is in-tractable, we provide a sampling-based method to get a good approximation. We empirically show the outputs of our approach significantly correlate with human judgments. By applying our method to various tasks, we also find that (1) our approach could effectively detect redundant relations extracted by open information extraction (Open IE) models, that (2) even the most competitive models for relational classification still make mistakes among very similar relations, and that (3) our approach could be incorporated into negative sampling and softmax classification to alleviate these mistakes. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/relation-similarity.

arXiv:1907.09423

Satellite-Net: Automatic Extraction of Land Cover Indicators from Satellite Imagery by Deep Learning

In this paper we address the challenge of land cover classification for satellite images via Deep Learning (DL). Land Cover aims to detect the physical characteristics of the territory and estimate the percentage of land occupied by a certain category of entities: vegetation, residential buildings, industrial areas, forest areas, rivers, lakes, etc. DL is a new paradigm for Big Data analytics and in particular for Computer Vision. The application of DL in images classification for land cover purposes has a great potential owing to the high degree of automation and computing performance. In particular, the invention of Convolution Neural Networks (CNNs) was a fundament for the advancements in this field. In [1], the Satellite Task Team of the UN Global Working Group describes the results achieved so far with respect to the use of earth observation for Official Statistics. However, in that study, CNNs have not yet been explored for automatic classification of imagery. This work investigates the usage of CNNs for the estimation of land cover indicators, providing evidence of the first promising results. In particular, the paper proposes a customized model, called Satellite-Net, able to reach an accuracy level up to 98% on test sets.

arXiv:1907.09382

Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition

The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We leverage independently trained local visual cues to learn representations that can be transferred from a source domain, which provides primitive action labels, to a different target domain using only a handful of examples. Visual cues we employ include object-object interactions, hand grasps and motion within regions that are a function of hand locations. We employ a framework based on meta-learning to extract the distinctive and domain invariant components of the deployed visual cues. This enables transfer of action classification models across public datasets captured with diverse scene and action configurations. We present comparative results of our transfer learning methodology and report superior results over state-of-the-art action classification approaches for both inter-class and inter-dataset transfer.

arXiv:1907.09296

A-Phase classification using convolutional neural networks

A series of short events, called A-phases, can be observed in the human electroencephalogram during NREM sleep. These events can be classified in three groups (A1, A2 and A3) according to their spectral contents, and are thought to play a role in the transitions between the different sleep stages. A-phase detection and classification is usually performed manually by a trained expert, but it is a tedious and time-consuming task. In the past two decades, various researchers have designed algorithms to automatically detect and classify the A-phases with varying degrees of success, but the problem remains open. In this paper, a different approach is proposed: instead of attempting to design a general classifier for all subjects, we propose to train ad-hoc classifiers for each subject using as little data as possible, in order to drastically reduce the amount of time required from the expert. The proposed classifiers are based on deep convolutional neural networks using the log-spectrogram of the EEG signal as input data. Results are encouraging, achieving average accuracies of 80.31% when discriminating between A-phases and non A-phases, and 71.87% when classifying among A-phase sub-types, with only 25% of the total A-phases used for training. When additional expert-validated data is considered, the sub-type classification accuracy increases to 78.92%. These results show that a semi-automatic annotation system with assistance from an expert could provide a better alternative to fully automatic classifiers.