PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1909.08612

Large e-retailer image dataset for visual search and product classification

Recent results of deep convolutional networks in visual recognition challenges open the path to a whole new set of disruptive user experiences such as visual search or recommendation. The list of companies offering this type of service is growing everyday but the adoption rate and the relevancy of results may vary a lot. We believe that the availability of large and diverse datasets is a necessary condition to improve the relevancy of such recommendation systems and facilitate their adoption. For that purpose, we wish to share with the community this dataset of more than 12M images of the 7M products of our online store classified into 5K categories. This original dataset is introduced in this article and several features are described. We also present some aspects of the winning solutions of our image classification challenge that was organized on the Kaggle platform around this set of images.

arXiv:1909.08444공식 코드 · Papers with Code

Musical Instrument Classification via Low-Dimensional Feature Vectors

Music is a mysterious language that conveys feeling and thoughts via different tones and timbre. For better understanding of timbre in music, we chose music data of 6 representative instruments, analysed their timbre features and classified them. Instead of the current trend of Neural Network for black-box classification, our project is based on a combination of MFCC and LPC, and augmented with a 6-dimensional feature vector designed by ourselves from observation and attempts. In our white-box model, we observed significant patterns of sound that distinguish different timbres, and discovered some connection between objective data and subjective senses. With a totally 32-dimensional feature vector and a naive all-pairs SVM, we achieved improved classification accuracy compared to a single tool. We also attempted to analyze music pieces downloaded from the Internet, found out different performance on different instruments, explored the reasons and suggested possible ways to improve the performance.

arXiv:1909.08306공식 코드 · Papers with Code

Text Length Adaptation in Sentiment Classification

Can a text classifier generalize well for datasets where the text length is different? For example, when short reviews are sentiment-labeled, can these transfer to predict the sentiment of long reviews (i.e., short to long transfer), or vice versa? While unsupervised transfer learning has been well-studied for cross domain/lingual transfer tasks, Cross Length Transfer (CLT) has not yet been explored. One reason is the assumption that length difference is trivially transferable in classification. We show that it is not, because short/long texts differ in context richness and word intensity. We devise new benchmark datasets from diverse domains and languages, and show that existing models from similar tasks cannot deal with the unique challenge of transferring across text lengths. We introduce a strong baseline model called BaggedCNN that treats long texts as bags containing short texts. We propose a state-of-the-art CLT model called Length Transfer Networks (LeTraNets) that introduces a two-way encoding scheme for short and long texts using multiple training mechanisms. We test our models and find that existing models perform worse than the BaggedCNN baseline, while LeTraNets outperforms all models.

arXiv:1909.08166

Recursive Graphical Neural Networks for Text Classification

The complicated syntax structure of natural language is hard to be explicitly modeled by sequence-based models. Graph is a natural structure to describe the complicated relation between tokens. The recent advance in Graph Neural Networks (GNN) provides a powerful tool to model graph structure data, but simple graph models such as Graph Convolutional Networks (GCN) suffer from over-smoothing problem, that is, when stacking multiple layers, all nodes will converge to the same value. In this paper, we propose a novel Recursive Graphical Neural Networks model (ReGNN) to represent text organized in the form of graph. In our proposed model, LSTM is used to dynamically decide which part of the aggregated neighbor information should be transmitted to upper layers thus alleviating the over-smoothing problem. Furthermore, to encourage the exchange between the local and global information, a global graph-level node is designed. We conduct experiments on both single and multiple label text classification tasks. Experiment results show that our ReGNN model surpasses the strong baselines significantly in most of the datasets and greatly alleviates the over-smoothing problem.

arXiv:1909.08135공식 코드 · Papers with Code

SUPP.AI: Finding Evidence for Supplement-Drug Interactions

Dietary supplements are used by a large portion of the population, but information on their pharmacologic interactions is incomplete. To address this challenge, we present SUPP.AI, an application for browsing evidence of supplement-drug interactions (SDIs) extracted from the biomedical literature. We train a model to automatically extract supplement information and identify such interactions from the scientific literature. To address the lack of labeled data for SDI identification, we use labels of the closely related task of identifying drug-drug interactions (DDIs) for supervision. We fine-tune the contextualized word representations of the RoBERTa language model using labeled DDI data, and apply the fine-tuned model to identify supplement interactions. We extract 195k evidence sentences from 22M articles (P=0.82, R=0.58, F1=0.68) for 60k interactions. We create the SUPP.AI application for users to search evidence sentences extracted by our model. SUPP.AI is an attempt to close the information gap on dietary supplements by making up-to-date evidence on SDIs more discoverable for researchers, clinicians, and consumers.

arXiv:1909.08097

Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements. In this paper, we present a framework for learning compact CNN models with improved classification performance and model generalization. For this, we propose a CNN architecture of a compact student model with parallel branches which are trained using ground truth labels and information from high capacity teacher networks in an ensemble learning fashion. Our framework provides two main benefits: i) Distilling knowledge from different teachers into the student network promotes heterogeneity in feature learning at different branches of the student network and enables the network to learn diverse solutions to the target problem. ii) Coupling the branches of the student network through ensembling encourages collaboration and improves the quality of the final predictions by reducing variance in the network outputs. Experiments on the well established CIFAR-10 and CIFAR-100 datasets show that our Ensemble Knowledge Distillation (EKD) improves classification accuracy and model generalization especially in situations with limited training data. Experiments also show that our EKD based compact networks outperform in terms of mean accuracy on the test datasets compared to state-of-the-art knowledge distillation based methods.

arXiv:1909.07969

Statistical and Machine Learning-based Decision Techniques for Physical Layer Authentication

In this paper we assess the security performance of key-less physical layer authentication schemes in the case of time-varying fading channels, considering both partial and no channel state information (CSI) on the receiver's side. We first present a generalization of a well-known protocol previously proposed for flat fading channels and we study different statistical decision methods and the corresponding optimal attack strategies in order to improve the authentication performance in the considered scenario. We then consider the application of machine learning techniques in the same setting, exploiting different one-class nearest neighbor (OCNN) classification algorithms. We observe that, under the same probability of false alarm, one-class classification (OCC) algorithms achieve the lowest probability of missed detection when a low spatial correlation exists between the main channel and the adversary one, while statistical methods are advantageous when the spatial correlation between the two channels is higher.

arXiv:1909.08528

k-Relevance Vectors: Considering Relevancy Beside Nearness

This study combines two different learning paradigms, k-nearest neighbor (k-NN) rule, as memory-based learning paradigm and relevance vector machines (RVM), as statistical learning paradigm. This combination is performed in kernel space and is called k-relevance vector (k-RV). The purpose is to improve the performance of k-NN rule. The proposed model significantly prunes irrelevant attributes. We also introduced a new parameter, responsible for early stopping of iterations in RVM. We show that the new parameter improves the classification accuracy of k-RV. Intensive experiments are conducted on several classification datasets from University of California Irvine (UCI) repository and two real datasets from computer vision domain. The performance of k-RV is highly competitive compared to a few state-of-the-arts in terms of classification accuracy.

arXiv:1909.08402공식 코드 · Papers with Code

Enriching BERT with Knowledge Graph Embeddings for Document Classification

In this paper, we focus on the classification of books using short descriptive texts (cover blurbs) and additional metadata. Building upon BERT, a deep neural language model, we demonstrate how to combine text representations with metadata and knowledge graph embeddings, which encode author information. Compared to the standard BERT approach we achieve considerably better results for the classification task. For a more coarse-grained classification using eight labels we achieve an F1- score of 87.20, while a detailed classification using 343 labels yields an F1-score of 64.70. We make the source code and trained models of our experiments publicly available

arXiv:1909.08383

A continual learning survey: Defying forgetting in classification tasks

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern 1) a taxonomy and extensive overview of the state-of-the-art, 2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner, 3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.

arXiv:1909.08203

Dual Adversarial Co-Learning for Multi-Domain Text Classification

In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance.

arXiv:1909.08190

PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification

A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work. SSL contains four key ingredients: 1) successive near-to-far neighborhood expansion; 2) unsupervised dimension reduction via subspace approximation; 3) supervised dimension reduction via label-assisted regression (LAG); and 4) feature concatenation and decision making. An image-based object classification method, called PixelHop, is proposed to illustrate the SSL design. It is shown by experimental results that the PixelHop method outperforms the classic CNN model of similar model complexity in three benchmarking datasets (MNIST, Fashion MNIST and CIFAR-10). Although SSL and deep learning (DL) have some high-level concept in common, they are fundamentally different in model formulation, the training process and training complexity. Extensive discussion on the comparison of SSL and DL is made to provide further insights into the potential of SSL.

arXiv:1909.08018

Neural Population Coding for Effective Temporal Classification

Neural encoding plays an important role in faithfully describing the temporally rich patterns, whose instances include human speech and environmental sounds. For tasks that involve classifying such spatio-temporal patterns with the Spiking Neural Networks (SNNs), how these patterns are encoded directly influence the difficulty of the task. In this paper, we compare several existing temporal and population coding schemes and evaluate them on both speech (TIDIGITS) and sound (RWCP) datasets. We show that, with population neural codings, the encoded patterns are linearly separable using the Support Vector Machine (SVM). We note that the population neural codings effectively project the temporal information onto the spatial domain, thus improving linear separability in the spatial dimension, achieving an accuracy of 95\% and 100\% for TIDIGITS and RWCP datasets classified using the SVM, respectively. This observation suggests that an effective neural coding scheme greatly simplifies the classification problem such that a simple linear classifier would suffice. The above datasets are then classified using the Tempotron, an SNN-based classifier. SNN classification results agree with the SVM findings that population neural codings help to improve classification accuracy. Hence, other than the learning algorithm, effective neural encoding is just as important as an SNN designed to recognize spatio-temporal patterns. It is an often neglected but powerful abstraction that deserves further study.

arXiv:1909.07512

Short-Text Classification Using Unsupervised Keyword Expansion

Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset, and add new features to testing data. This paper applies a novel approach to text expansion by generating new words directly for each input sentence, thus requiring no additional datasets or previous training. In this unsupervised approach, new keywords are formed within the hidden states of a pre-trained language model and then used to create extended pseudo documents. The word generation process was assessed by examining how well the predicted words matched to topics of the input sentence. It was found that this method could produce 3-10 relevant new words for each target topic, while generating just 1 word related to each non-target topic. Generated words were then added to short news headlines to create extended pseudo headlines. Experimental results have shown that models trained using the pseudo headlines can improve classification accuracy when limiting the number of training examples.

arXiv:1909.07526공식 코드 · Papers with Code

Data-Efficient Classification of Birdcall Through Convolutional Neural Networks Transfer Learning

Deep learning Convolutional Neural Network (CNN) models are powerful classification models but require a large amount of training data. In niche domains such as bird acoustics, it is expensive and difficult to obtain a large number of training samples. One method of classifying data with a limited number of training samples is to employ transfer learning. In this research, we evaluated the effectiveness of birdcall classification using transfer learning from a larger base dataset (2814 samples in 46 classes) to a smaller target dataset (351 samples in 10 classes) using the ResNet-50 CNN. We obtained 79% average validation accuracy on the target dataset in 5-fold cross-validation. The methodology of transfer learning from an ImageNet-trained CNN to a project-specific and a much smaller set of classes and images was extended to the domain of spectrogram images, where the base dataset effectively played the role of the ImageNet.

arXiv:1909.07922공식 코드 · Papers with Code

Distributed Function Minimization in Apache Spark

We report on an open-source implementation for distributed function minimization on top of Apache Spark by using gradient and quasi-Newton methods. We show-case it with an application to Optimal Transport and some scalability tests on classification and regression problems.

arXiv:1909.07502

Automatic Detection and Classification of Cognitive Distortions in Mental Health Text

In cognitive psychology, automatic and self-reinforcing irrational thought patterns are known as cognitive distortions. Left unchecked, patients exhibiting these types of thoughts can become stuck in negative feedback loops of unhealthy thinking, leading to inaccurate perceptions of reality commonly associated with anxiety and depression. In this paper, we present a machine learning framework for the automatic detection and classification of 15 common cognitive distortions in two novel mental health free text datasets collected from both crowdsourcing and a real-world online therapy program. When differentiating between distorted and non-distorted passages, our model achieved a weighted F1 score of 0.88. For classifying distorted passages into one of 15 distortion categories, our model yielded weighted F1 scores of 0.68 in the larger crowdsourced dataset and 0.45 in the smaller online counseling dataset, both of which outperformed random baseline metrics by a large margin. For both tasks, we also identified the most discriminative words and phrases between classes to highlight common thematic elements for improving targeted and therapist-guided mental health treatment. Furthermore, we performed an exploratory analysis using unsupervised content-based clustering and topic modeling algorithms as first efforts towards a data-driven perspective on the thematic relationship between similar cognitive distortions traditionally deemed unique. Finally, we highlight the difficulties in applying mental health-based machine learning in a real-world setting and comment on the implications and benefits of our framework for improving automated delivery of therapeutic treatment in conjunction with traditional cognitive-behavioral therapy.

arXiv:1909.07444

Student Performance Prediction with Optimum Multilabel Ensemble Model

One of the important measures of quality of education is the performance of students in the academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and how to improve their performance ahead of time using data mining techniques. In this paper, we developed a student performance prediction model that predicts the performance of high school students for the next semester for five courses. We modeled our prediction system as a multi-label classification task and used support vector machine (SVM), Random Forest (RF), K-nearest Neighbors (KNN), and Mult-layer perceptron (MLP) as base-classifiers to train our model. We further improved the performance of the prediction model using state-of-the-art partitioning schemes to divide the label space into smaller spaces and use Label Powerset (LP) transformation method to transform each labelset into a multi-class classification task. The proposed model achieved better performance in terms of different evaluation metrics when compared to other multi-label learning tasks such as binary relevance and classifier chains.

arXiv:1909.07368

Document classification methods

Information on different fields which are collected by users requires appropriate management and organization to be structured in a standard way and retrieved fast and more easily. Document classification is a conventional method to separate text based on their subjects among scientific text, web pages and digital library. Different methods and techniques are proposed for document classifications that have advantages and deficiencies. In this paper, several unsupervised and supervised document classification methods are studied and compared.

arXiv:1909.07155

Meta-Learning for Few-Shot Time Series Classification

Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is difficult, and where DNNs would be prone to overfitting. We leverage recent advancements in gradient-based meta-learning, and propose an approach to train a residual neural network with convolutional layers as a meta-learning agent for few-shot TSC. The network is trained on a diverse set of few-shot tasks sampled from various domains (e.g. healthcare, activity recognition, etc.) such that it can solve a target task from another domain using only a small number of training samples from the target task. Most existing meta-learning approaches are limited in practice as they assume a fixed number of target classes across tasks. We overcome this limitation in order to train a common agent across domains with each domain having different number of target classes, we utilize a triplet-loss based learning procedure that does not require any constraints to be enforced on the number of classes for the few-shot TSC tasks. To the best of our knowledge, we are the first to use meta-learning based pre-training for TSC. Our approach sets a new benchmark for few-shot TSC, outperforming several strong baselines on few-shot tasks sampled from 41 datasets in UCR TSC Archive. We observe that pre-training under the meta-learning paradigm allows the network to quickly adapt to new unseen tasks with small number of labeled instances.