PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1911.05712

Streaming Bayesian Inference for Crowdsourced Classification

A key challenge in crowdsourcing is inferring the ground truth from noisy and unreliable data. To do so, existing approaches rely on collecting redundant information from the crowd, and aggregating it with some probabilistic method. However, oftentimes such methods are computationally inefficient, are restricted to some specific settings, or lack theoretical guarantees. In this paper, we revisit the problem of binary classification from crowdsourced data. Specifically we propose Streaming Bayesian Inference for Crowdsourcing (SBIC), a new algorithm that does not suffer from any of these limitations. First, SBIC has low complexity and can be used in a real-time online setting. Second, SBIC has the same accuracy as the best state-of-the-art algorithms in all settings. Third, SBIC has provable asymptotic guarantees both in the online and offline settings.

arXiv:1911.05443

Dynamic Connected Neural Decision Classifier and Regressor with Dynamic Softing Pruning

To deal with various datasets over different complexity, this paper presents an self-adaptive learning model that combines the proposed Dynamic Connected Neural Decision Networks (DNDN) and a new pruning method--Dynamic Soft Pruning (DSP). DNDN is a combination of random forests and deep neural networks that enjoys both the advantages of strong classification capability of tree-like structure and representation learning capability of network structure. Based on Deep Neural Decision Forests (DNDF), this paper adopts an end-to-end training approach by representing the classification distribution with multiple randomly initialized softmax layers, which further allows an ensemble of multiple random forests attached to layers of neural network with different depth. We also propose a soft pruning method DSP to reduce the redundant connections of the network adaptively to avoid over-fitting simple dataset. The model demonstrates no performance loss compared with unpruned models and even higher robustness over different data and feature distribution. Extensive experiments on different datasets demonstrate the superiority of the proposed model over other popular algorithms in solving classification tasks.

arXiv:1911.05369

Fair Adversarial Gradient Tree Boosting

Fair classification has become an important topic in machine learning research. While most bias mitigation strategies focus on neural networks, we noticed a lack of work on fair classifiers based on decision trees even though they have proven very efficient. In an up-to-date comparison of state-of-the-art classification algorithms in tabular data, tree boosting outperforms deep learning. For this reason, we have developed a novel approach of adversarial gradient tree boosting. The objective of the algorithm is to predict the output $Y$ with gradient tree boosting while minimizing the ability of an adversarial neural network to predict the sensitive attribute $S$. The approach incorporates at each iteration the gradient of the neural network directly in the gradient tree boosting. We empirically assess our approach on 4 popular data sets and compare against state-of-the-art algorithms. The results show that our algorithm achieves a higher accuracy while obtaining the same level of fairness, as measured using a set of different common fairness definitions.

arXiv:1911.05350

Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features

Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods are the most commonly used techniques to derive efficient large-scale learning algorithms. In this study, we consider solving a binary classification problem using random features and stochastic gradient descent. In recent research, an exponential convergence rate of the expected classification error under the strong low-noise condition has been shown. We extend these analyses to a random features setting, analyzing the error induced by the approximation of random features in terms of the distance between the generated hypothesis including population risk minimizers and empirical risk minimizers when using general Lipschitz loss functions, to show that an exponential convergence of the expected classification error is achieved even if random features approximation is applied. Additionally, we demonstrate that the convergence rate does not depend on the number of features and there is a significant computational benefit in using random features in classification problems because of the strong low-noise condition.

arXiv:1911.05263공식 코드 · Papers with Code

LexiPers: An ontology based sentiment lexicon for Persian

Sentiment analysis refers to the use of natural language processing to identify and extract subjective information from textual resources. One approach for sentiment extraction is using a sentiment lexicon. A sentiment lexicon is a set of words associated with the sentiment orientation that they express. In this paper, we describe the process of generating a general purpose sentiment lexicon for Persian. A new graph-based method is introduced for seed selection and expansion based on an ontology. Sentiment lexicon generation is then mapped to a document classification problem. We used the K-nearest neighbors and nearest centroid methods for classification. These classifiers have been evaluated based on a set of hand labeled synsets. The final sentiment lexicon has been generated by the best classifier. The results show an acceptable performance in terms of accuracy and F-measure in the generated sentiment lexicon.

arXiv:1911.05256

A Hierarchy of Graph Neural Networks Based on Learnable Local Features

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to compare different architectures and how to construct GNNs systematically. Here, we propose a hierarchy of GNNs based on their aggregation regions. We derive theoretical results about the discriminative power and feature representation capabilities of each class. Then, we show how this framework can be utilized to systematically construct arbitrarily powerful GNNs. As an example, we construct a simple architecture that exceeds the expressiveness of the Weisfeiler-Lehman graph isomorphism test. We empirically validate our theory on both synthetic and real-world benchmarks, and demonstrate our example's theoretical power translates to strong results on node classification, graph classification, and graph regression tasks.

arXiv:1911.04862

An End-to-end Approach for Lexical Stress Detection based on Transformer

The dominant automatic lexical stress detection method is to split the utterance into syllable segments using phoneme sequence and their time-aligned boundaries. Then we extract features from syllable to use classification method to classify the lexical stress. However, we can't get very accurate time boundaries of each phoneme and we have to design some features in the syllable segments to classify the lexical stress. Therefore, we propose a end-to-end approach using sequence to sequence model of transformer to estimate lexical stress. For this, we train transformer model using feature sequence of audio and their phoneme sequence with lexical stress marks. During the recognition process, the recognized phoneme sequence is restricted according to the original standard phoneme sequence without lexical stress marks, but the lexical stress mark of each phoneme is not limited. We train the model in different subset of Librispeech and do lexical stress recognition in TIMIT and L2-ARCTIC dataset. For all subsets, the end-to-end model will perform better than the syllable segments classification method. Our method can achieve a 6.36% phoneme error rate on the TIMIT dataset, which exceeds the 7.2% error rate in other studies.

arXiv:1911.04970

Robust and Fast Automatic Modulation Classification with CNN under Multipath Fading Channels

Automatic modulation classification (AMC) has been studied for more than a quarter of a century; however, it has been difficult to design a classifier that operates successfully under changing multipath fading conditions and other impairments. Recently, deep learning (DL)-based methods are adopted by AMC systems and major improvements are reported. In this paper, a novel convolutional neural network (CNN) classifier model is proposed to classify modulation classes in terms of their families, i.e., types. The proposed classifier is robust against realistic wireless channel impairments and in relation to that when the data sets that are utilized for testing and evaluating the proposed methods are considered, it is seen that RadioML2016.10a is the main dataset utilized for testing and evaluation of the proposed methods. However, the channel effects incorporated in this dataset and some others may lack the appropriate modeling of the real-world conditions since it only considers two distributions for channel models for a single tap configuration. Therefore, in this paper, a more comprehensive dataset, named as HisarMod2019.1, is also introduced, considering real-life applicability. HisarMod2019.1 includes 26 modulation classes passing through the channels with 5 different fading types and several numbers of taps for classification. It is shown that the proposed model performs better than the existing models in terms of both accuracy and training time under more realistic conditions. Even more, surpassed their performance when the RadioML2016.10a dataset is utilized.

arXiv:1911.04898

Generating an Explainable ECG Beat Space With Variational Auto-Encoders

Electrocardiogram signals are omnipresent in medicine. A vital aspect in the analysis of this data is the identification and classification of heart beat types which is often done through automated algorithms. Advancements in neural networks and deep learning have led to a high classification accuracy. However, the final adoption of these models into clinical practice is limited due to the black-box nature of the methods. In this work, we explore the use of variational auto-encoders based on linear dense networks to learn human interpretable beat embeddings in time-series data. We demonstrate that using this method, an interpretable and explainable ECG beat space can be generated, set up by characteristic base beats.

arXiv:1911.04822공식 코드 · Papers with Code

A Capsule Network-based Model for Learning Node Embeddings

In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data. To achieve this, we propose Caps2NE -- a new unsupervised embedding model leveraging a network of two capsule layers. Caps2NE induces a routing process to aggregate feature vectors of context neighbors of a given target node at the first capsule layer, then feed these features into the second capsule layer to infer a plausible embedding for the target node. Experimental results show that our proposed Caps2NE obtains state-of-the-art performances on benchmark datasets for the node classification task. Our code is available at: \url{https://github.com/daiquocnguyen/Caps2NE}.

arXiv:1911.04666

Segment Relevance Estimation for Audio Analysis and Weakly-Labelled Classification

We propose a method that quantifies the importance, namely relevance, of audio segments for classification in weakly-labelled problems. It works by drawing information from a set of class-wise one-vs-all classifiers. By selecting the classifiers used in each specific classification problem, the relevance measure adapts to different user-defined viewpoints without requiring additional neural network training. This characteristic allows the relevance measure to highlight audio segments that quickly adapt to user-defined criteria. Such functionality can be used for computer-assisted audio analysis. Also, we propose a neural network architecture, namely RELNET, that leverages the relevance measure for weakly-labelled audio classification problems. RELNET was evaluated in the DCASE2018 dataset and achieved competitive classification results when compared to previous attention-based proposals.

arXiv:1911.04660

Random Projections of Mel-Spectrograms as Low-Level Features for Automatic Music Genre Classification

In this work, we analyse the random projections of Mel-spectrograms as low-level features for music genre classification. This approach was compared to handcrafted features, features learned using an auto-encoder and features obtained from a transfer learning setting. Tests in five different well-known, publicly available datasets show that random projections leads to results comparable to learned features and outperforms features obtained via transfer learning in a shallow learning scenario. Random projections do not require using extensive specialist knowledge and, simultaneously, requires less computational power for training than other projection-based low-level features. Therefore, they can be are a viable choice for usage in shallow learning content-based music genre classification.

arXiv:1911.04623공식 코드 · Papers with Code

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization outperforms prior results in three out of five settings on the miniImageNet dataset.

arXiv:1911.05024

Pose Guided Attention for Multi-label Fashion Image Classification

We propose a compact framework with guided attention for multi-label classification in the fashion domain. Our visual semantic attention model (VSAM) is supervised by automatic pose extraction creating a discriminative feature space. VSAM outperforms the state of the art for an in-house dataset and performs on par with previous works on the DeepFashion dataset, even without using any landmark annotations. Additionally, we show that our semantic attention module brings robustness to large quantities of wrong annotations and provides more interpretable results.

arXiv:1911.04255

Decoding Imagined Speech and Computer Control using Brain Waves

In this work, we explore the possibility of decoding Imagined Speech brain waves using machine learning techniques. We propose a covariance matrix of Electroencephalogram channels as input features, projection to tangent space of covariance matrices for obtaining vectors from covariance matrices, principal component analysis for dimension reduction of vectors, an artificial feed-forward neural network as a classification model and bootstrap aggregation for creating an ensemble of neural network models. After the classification, two different Finite State Machines are designed that create an interface for controlling a computer system using an Imagined Speech-based BCI system. The proposed approach is able to decode the Imagined Speech signal with a maximum mean classification accuracy of 85% on binary classification task of one long word and a short word. We also show that our proposed approach is able to differentiate between imagined speech brain signals and rest state brain signals with maximum mean classification accuracy of 94%. We compared our proposed method with other approaches for decoding imagined speech and show that our approach performs equivalent to the state of the art approach on decoding long vs. short words and outperforms it significantly on the other two tasks of decoding three short words and three vowels with an average margin of 11% and 9%, respectively. We also obtain an information transfer rate of 21-bits-per-minute when using an IS based system to operate a computer. These results show that the proposed approach is able to decode a wide variety of imagined speech signals without any human-designed features.

arXiv:1911.03803

XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification

Capitalizing on the need for addressing the existing challenges associated with gesture recognition via sparse multichannel surface Electromyography (sEMG) signals, the paper proposes a novel deep learning model, referred to as the XceptionTime architecture. The proposed innovative XceptionTime is designed by integration of depthwise separable convolutions, adaptive average pooling, and a novel non-linear normalization technique. At the heart of the proposed architecture is several XceptionTime modules concatenated in series fashion designed to capture both temporal and spatial information-bearing contents of the sparse multichannel sEMG signals without the need for data augmentation and/or manual design of feature extraction. In addition, through integration of adaptive average pooling, Conv1D, and the non-linear normalization approach, XceptionTime is less prone to overfitting, more robust to temporal translation of the input, and more importantly is independent from the input window size. Finally, by utilizing the depthwise separable convolutions, the XceptionTime network has far fewer parameters resulting in a less complex network. The performance of XceptionTime is tested on a sub Ninapro dataset, DB1, and the results showed a superior performance in comparison to any existing counterparts. In this regard, 5:71% accuracy improvement, on a window size 200ms, is reported in this paper, for the first time.

arXiv:1911.03711

Unsupervised adulterated red-chili pepper content transformation for hyperspectral classification

Preserving red-chili quality is of utmost importance in which the authorities demand the quality techniques to detect, classify and prevent it from the impurities. For example, salt, wheat flour, wheat bran, and rice bran contamination in grounded red chili, which typically a food, are a serious threat to people who are allergic to such items. This work presents the feasibility of utilizing visible and near-infrared (VNIR) hyperspectral imaging (HSI) to detect and classify the aforementioned adulterants in red chili. However, adulterated red chili data annotation is a big challenge for classification because the acquisition of labeled data for real-time supervised learning is expensive in terms of cost and time. Therefore, this study, for the very first time proposes a novel approach to annotate the red chili samples using a clustering mechanism at 500~nm wavelength spectral response due to its dark appearance at a specified wavelength. Later the spectral samples are classified into pure or adulterated using one-class SVM. The classification performance achieves 99% in case of pure adulterants or red chili whereas 85% for adulterated samples. We further investigate that the single classification model is enough to detect any foreign substance in red chili pepper rather than cascading multiple PLS regression models.

arXiv:1911.03658

Missing Features Reconstruction and Its Impact on Classification Accuracy

In real-world applications, we can encounter situations when a well-trained model has to be used to predict from a damaged dataset. The damage caused by missing or corrupted values can be either on the level of individual instances or on the level of entire features. Both situations have a negative impact on the usability of the model on such a dataset. This paper focuses on the scenario where entire features are missing which can be understood as a specific case of transfer learning. Our aim is to experimentally research the influence of various imputation methods on the performance of several classification models. The imputation impact is researched on a combination of traditional methods such as k-NN, linear regression, and MICE compared to modern imputation methods such as multi-layer perceptron (MLP) and gradient boosted trees (XGBT). For linear regression, MLP, and XGBT we also propose two approaches to using them for multiple features imputation. The experiments were performed on both real world and artificial datasets with continuous features where different numbers of features, varying from one feature to 50%, were missing. The results show that MICE and linear regression are generally good imputers regardless of the conditions. On the other hand, the performance of MLP and XGBT is strongly dataset dependent. Their performance is the best in some cases, but more often they perform worse than MICE or linear regression.

arXiv:1911.03645

Pairwise coupling of convolutional neural networks for better explicability of classification systems

We examine several aspects of explicability of a classification system built from neural networks. The first aspect is the pairwise explicability, which is the ability to provide the most accurate prediction when the range of possibilities is narrowed to just two. Next we consider explicability in development, which means ability to make incremental improvement in prediction accuracy based on observed deficiency of the system. Inherent stochasticity of neural network based classifiers can be interpreted using likelihood randomness explicability. Finally, sureness explicability indicates confidence of the classifying system to make any prediction at all. These concepts are examined in the framework of pairwise coupling, which is a non-trainable metamodel that originated during development of support vector machines. Several methodologies are evaluated, of which the key one is shown to be the choice of the pairwise coupling method. We compare two methods: the established Wu-Lin-Weng method with the recently proposed Bayes covariant method. Our experiments indicate that the Wu-Lin-Weng method gives more weight to a single pairwise classifier, whereas the latter tries to balance information from the whole matrix of pairwise likelihoods. This translates into higher accuracy, and better sureness predictions for the Bayes covariant method. Pairwise coupling methodology has its costs, especially in terms of the number of parameters (but not necessarily in terms of training costs). However, when additional explicability aspects beyond accuracy are desired in an application, the pairwise coupling models are a promising alternative to the established methodology.

arXiv:1911.03626공식 코드 · Papers with Code

Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification

Automatically labeling multiple styles for every song is a comprehensive application in all kinds of music websites. Recently, some researches explore review-driven multi-label music style classification and exploit style correlations for this task. However, their methods focus on mining the statistical relations between different music styles and only consider shallow style relations. Moreover, these statistical relations suffer from the underfitting problem because some music styles have little training data. To tackle these problems, we propose a novel knowledge relations integrated framework (KRF) to capture the complete style correlations, which jointly exploits the inherent relations between music styles according to external knowledge and their statistical relations. Based on the two types of relations, we use a graph convolutional network to learn the deep correlations between styles automatically. Experimental results show that our framework significantly outperforms state-of-the-art methods. Further studies demonstrate that our framework can effectively alleviate the underfitting problem and learn meaningful style correlations. The source code can be available at https://github.com/Makwen1995/MusicGenre.