Graph and language embedding models are becoming commonplace in large scale analyses given their ability to represent complex sparse data densely in low-dimensional space. Integrating these models' complementary relational and communicative data may be especially helpful if predicting rare events or classifying members of hidden populations - tasks requiring huge and sparse datasets for generalizable analyses. For example, due to social stigma and comorbidities, mental health support groups often form in amorphous online groups. Predicting suicidality among individuals in these settings using standard network analyses is prohibitive due to resource limits (e.g., memory), and adding auxiliary data like text to such models exacerbates complexity- and sparsity-related issues. Here, I show how merging graph and language embedding models (metapath2vec and doc2vec) avoids these limits and extracts unsupervised clustering data without domain expertise or feature engineering. Graph and language distances to a suicide support group have little correlation (\r{ho} < 0.23), implying the two models are not embedding redundant information. When used separately to predict suicidality among individuals, graph and language data generate relatively accurate results (69% and 76%, respectively); however, when integrated, both data produce highly accurate predictions (90%, with 10% false-positives and 12% false-negatives). Visualizing graph embeddings annotated with predictions of potentially suicidal individuals shows the integrated model could classify such individuals even if they are positioned far from the support group. These results extend research on the importance of simultaneously analyzing behavior and language in massive networks and efforts to integrate embedding models for different kinds of data when predicting and classifying, particularly when they involve rare events.
Nowadays, an abundance of short text is being generated that uses nonstandard writing styles influenced by regional languages. Such informal and code-switched content are under-resourced in terms of labeled datasets and language models even for popular tasks like sentiment classification. In this work, we (1) present a labeled dataset called MultiSenti for sentiment classification of code-switched informal short text, (2) explore the feasibility of adapting resources from a resource-rich language for an informal one, and (3) propose a deep learning-based model for sentiment classification of code-switched informal short text. We aim to achieve this without any lexical normalization, language translation, or code-switching indication. The performance of the proposed models is compared with three existing multilingual sentiment classification models. The results show that the proposed model performs better in general and adapting character-based embeddings yield equivalent performance while being computationally more efficient than training word-based domain-specific embeddings.
This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different patterns of an image, we are inspired by a method called "PCANet" in "PCANet: A Simple Deep Learning Baseline for Image Classification?" to choose filter vectors from basis vectors in frequency domain like Fourier coefficients or wavelets without back propagation. Researchers have demonstrated that those basis in frequency domain can usually provide physical insights, which adds to the interpretability of the model by analyzing the frequencies selected. Besides, the training process will also be more time efficient, mathematically clear and interpretable compared with the "black-box" training process of CNN.
Many real-world phenomena are observed at multiple resolutions. Predictive models designed to predict these phenomena typically consider different resolutions separately. This approach might be limiting in applications where predictions are desired at fine resolutions but available training data is scarce. In this paper, we propose classification algorithms that leverage supervision from coarser resolutions to help train models on finer resolutions. The different resolutions are modeled as different views of the data in a multi-view framework that exploits the complementarity of features across different views to improve models on both views. Unlike traditional multi-view learning problems, the key challenge in our case is that there is no one-to-one correspondence between instances across different views in our case, which requires explicit modeling of the correspondence of instances across resolutions. We propose to use the features of instances at different resolutions to learn the correspondence between instances across resolutions using an attention mechanism.Experiments on the real-world application of mapping urban areas using satellite observations and sentiment classification on text data show the effectiveness of the proposed methods.
The paper presents a comparative study of state-of-the-art approaches for question classification task: Logistic Regression, Convolutional Neural Networks (CNN), Long Short-Term Memory Network (LSTM) and Quasi-Recurrent Neural Networks (QRNN). All models use pre-trained GLoVe word embeddings and trained on human-labeled data. The best accuracy is achieved using CNN model with five convolutional layers and various kernel sizes stacked in parallel, followed by one fully connected layer. The model reached 90.7% accuracy on TREC 10 test set. All the model architectures in this paper were developed from scratch on PyTorch, in few cases based on reliable open-source implementation.
In this paper, we propose a new metric to measure goodness-of-fit for classifiers, the Real World Cost function. This metric factors in information about a real world problem, such as financial impact, that other measures like accuracy or F1 do not. This metric is also more directly interpretable for users. To optimize for this metric, we introduce the Real-World- Weight Crossentropy loss function, in both binary and single-label classification variants. Both variants allow direct input of real world costs as weights. For single-label, multicategory classification, our loss function also allows direct penalization of probabilistic false positives, weighted by label, during the training of a machine learning model. We compare the design of our loss function to the binary crossentropy and categorical crossentropy functions, as well as their weighted variants, to discuss the potential for improvement in handling a variety of known shortcomings of machine learning, ranging from imbalanced classes to medical diagnostic error to reinforcement of social bias. We create scenarios that emulate those issues using the MNIST data set and demonstrate empirical results of our new loss function. Finally, we sketch a proof of this function based on Maximum Likelihood Estimation and discuss future directions.
Insects are abundant species on the earth, and the task of identification and identification of insects is complex and arduous. How to apply artificial intelligence technology and digital image processing methods to automatic identification of insect species is a hot issue in current research. In this paper, the problem of automatic detection and classification recognition of butterfly photographs is studied, and a method of bio-labeling suitable for butterfly classification is proposed. On the basis of YOLO algorithm, by synthesizing the results of YOLO models with different training mechanisms, a butterfly automatic detection and classification recognition algorithm based on YOLO algorithm is proposed. It greatly improves the generalization ability of YOLO algorithm and makes it have better ability to solve small sample problems. The experimental results show that the proposed annotation method and integrated YOLO algorithm have high accuracy and recognition rate in butterfly automatic detection and recognition.
Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is important for image semantic segmentation. To avoid this problem, we propose a graph model initialized by a fully convolutional network (FCN) named Graph-FCN for image semantic segmentation. Firstly, the image grid data is extended to graph structure data by a convolutional network, which transforms the semantic segmentation problem into a graph node classification problem. Then we apply graph convolutional network to solve this graph node classification problem. As far as we know, it is the first time that we apply the graph convolutional network in image semantic segmentation. Our method achieves competitive performance in mean intersection over union (mIOU) on the VOC dataset(about 1.34% improvement), compared to the original FCN model.
We describe a search and classification procedure for gravitational waves emitted by core-collapse supernova (CCSN) explosions, using a convolutional neural network (CNN) combined with an event trigger generator known as Wavelet Detection Filter (WDF). We employ both a 1-D CNN search using time series gravitational-wave data as input, and a 2-D CNN search with time-frequency representation of the data as input. To test the accuracies of our 1-D and 2-D CNN classification, we add CCSN waveforms from the most recent hydrodynamical simulations of neutrino-driven core-collapse to simulated Gaussian colored noise with the Virgo interferometer and the planned Einstein Telescope sensitivity curve. We find classification accuracies, for a single detector, of over 95% for both 1-D and 2-D CNN pipelines. For the first time in machine learning CCSN studies, we add short duration detector noise transients to our data to test the robustness of our method against false alarms created by detector noise artifacts. Further to this, we show that the CNN can distinguish between different types of CCSN waveform models.
Accurate identification and localization of the vertebrae in CT scans is a critical and standard preprocessing step for clinical spinal diagnosis and treatment. Existing methods are mainly based on the integration of multiple neural networks, and most of them use the Gaussian heat map to locate the vertebrae's centroid. However, the process of obtaining the vertebrae's centroid coordinates using heat maps is non-differentiable, so it is impossible to train the network to label the vertebrae directly. Therefore, for end-to-end differential training of vertebra coordinates on CT scans, a robust and accurate automatic vertebral labeling algorithm is proposed in this study. Firstly, a novel residual-based multi-label classification and localization network is developed, which can capture multi-scale features, but also utilize the residual module and skip connection to fuse the multi-level features. Secondly, to solve the problem that the process of finding coordinates is non-differentiable and the spatial structure is not destructible, integral regression module is used in the localization network. It combines the advantages of heat map representation and direct regression coordinates to achieve end-to-end training, and can be compatible with any key point detection methods of medical image based on heat map. Finally, multi-label classification of vertebrae is carried out, which use bidirectional long short term memory (Bi-LSTM) to enhance the learning of long contextual information to improve the classification performance. The proposed method is evaluated on a challenging dataset and the results are significantly better than the state-of-the-art methods (mean localization error <3mm).
Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class classification problem, we propose a framework for uncertainty-based OOD classification: UBOOD. It is based on the effect that an agent's epistemic uncertainty is reduced for situations encountered during training (in-distribution), and thus lower than for unencountered (OOD) situations. Being agnostic towards the approach used for estimating epistemic uncertainty, combinations with different uncertainty estimation methods, e.g. approximate Bayesian inference methods or ensembling techniques are possible. We further present a first viable solution for calculating a dynamic classification threshold, based on the uncertainty distribution of the training data. Evaluation shows that the framework produces reliable classification results when combined with ensemble-based estimators, while the combination with concrete dropout-based estimators fails to reliably detect OOD situations. In summary, UBOOD presents a viable approach for OOD classification in deep RL settings by leveraging the epistemic uncertainty of the agent's value function.
We propose a novel method for automatic reasoning on knowledge graphs based on debate dynamics. The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to promote the fact being true (thesis) or the fact being false (antithesis), respectively. Based on these arguments, a binary classifier, called the judge, decides whether the fact is true or false. The two agents can be considered as sparse, adversarial feature generators that present interpretable evidence for either the thesis or the antithesis. In contrast to other black-box methods, the arguments allow users to get an understanding of the decision of the judge. Since the focus of this work is to create an explainable method that maintains a competitive predictive accuracy, we benchmark our method on the triple classification and link prediction task. Thereby, we find that our method outperforms several baselines on the benchmark datasets FB15k-237, WN18RR, and Hetionet. We also conduct a survey and find that the extracted arguments are informative for users.
Physiological signals that provide the objective repression of human affective states are attracted increasing attention in the emotion recognition field. However, the single signal is difficult to obtain completely and accurately description for emotion. Multiple physiological signals fusing models, building the uniform classification model by means of consistent and complementary information from different emotions to improve recognition performance. Original fusing models usually choose the particular classification method to recognition, which is ignoring different distribution of multiple signals. Aiming above problems, in this work, we propose an emotion classification model through multiple modal physiological signals for different emotions. Features are extracted from EEG, EMG, EOG signals for characterizing emotional state on valence and arousal levels. For characterization, four bands filtering theta, beta, alpha, gamma for signal preprocessing are adopted and three Hjorth parameters are computing as features. To improve classification performance, an ensemble classifier is built. Experiments are conducted on the benchmark DEAP datasets. For the two-class task, the best result on arousal is 94.42\%, the best result on valence is 94.02\%, respectively. For the four-class task, the highest average classification accuracy is 90.74, and it shows good stability. The influence of different peripheral physiological signals for results is also analyzed in this paper.
In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel encoding scheme in BERT, a powerful language representation model solely based on attention mechanisms. Incomplete data in natural language processing refer to text with missing or incorrect words, and its presence can hinder the performance of current models that were not implemented to withstand such noises, but must still perform well even under duress. This is due to the fact that current approaches are built for and trained with clean and complete data, and thus are not able to extract features that can adequately represent incomplete data. Our proposed approach consists of obtaining intermediate input representations by applying an embedding layer to the input tokens followed by vanilla transformers. These intermediate features are given as input to novel denoising transformers which are responsible for obtaining richer input representations. The proposed approach takes advantage of stacks of multilayer perceptrons for the reconstruction of missing words' embeddings by extracting more abstract and meaningful hidden feature vectors, and bidirectional transformers for improved embedding representation. We consider two datasets for training and evaluation: the Chatbot Natural Language Understanding Evaluation Corpus and Kaggle's Twitter Sentiment Corpus. Our model shows improved F1-scores and better robustness in informal/incorrect texts present in tweets and in texts with Speech-to-Text error in the sentiment and intent classification tasks.
Tweet classification has attracted considerable attention recently. Most of the existing work on tweet classification focuses on topic classification, which classifies tweets into several predefined categories, and sentiment classification, which classifies tweets into positive, negative and neutral. Since tweets are different from conventional text in that they generally are of limited length and contain informal, irregular or new words, so it is difficult to determine user intention to publish a tweet and user attitude towards certain topic. In this paper, we aim to simultaneously classify tweet purpose, i.e., the intention for user to publish a tweet, and position, i.e., supporting, opposing or being neutral to a given topic. By transforming this problem to a multi-label classification problem, a multi-label classification method with post-processing is proposed. Experiments on real-world data sets demonstrate the effectiveness of this method and the results outperform the individual classification methods.
Text classification systems will help to solve the text clustering problem in the Azerbaijani language. There are some text-classification applications for foreign languages, but we tried to build a newly developed system to solve this problem for the Azerbaijani language. Firstly, we tried to find out potential practice areas. The system will be useful in a lot of areas. It will be mostly used in news feed categorization. News websites can automatically categorize news into classes such as sports, business, education, science, etc. The system is also used in sentiment analysis for product reviews. For example, the company shares a photo of a new product on Facebook and the company receives a thousand comments for new products. The systems classify the comments into categories like positive or negative. The system can also be applied in recommended systems, spam filtering, etc. Various machine learning techniques such as Naive Bayes, SVM, Decision Trees have been devised to solve the text classification problem in Azerbaijani language.
Nowadays, deep learning methods, especially the convolutional neural networks (CNNs), have shown impressive performance on extracting abstract and high-level features from the hyperspectral image. However, general training process of CNNs mainly considers the pixel-wise information or the samples' correlation to formulate the penalization while ignores the statistical properties especially the spectral variability of each class in the hyperspectral image. These samples-based penalizations would lead to the uncertainty of the training process due to the imbalanced and limited number of training samples. To overcome this problem, this work characterizes each class from the hyperspectral image as a statistical distribution and further develops a novel statistical loss with the distributions, not directly with samples for deep learning. Based on the Fisher discrimination criterion, the loss penalizes the sample variance of each class distribution to decrease the intra-class variance of the training samples. Moreover, an additional diversity-promoting condition is added to enlarge the inter-class variance between different class distributions and this could better discriminate samples from different classes in hyperspectral image. Finally, the statistical estimation form of the statistical loss is developed with the training samples through multi-variant statistical analysis. Experiments over the real-world hyperspectral images show the effectiveness of the developed statistical loss for deep learning.
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden. In this work, we propose a lightweight yet high-performing baseline network inspired by MobileNetV2, which replaces square convolutional kernels with unidirectional ones to extract features alternately in temporal and frequency dimensions. Furthermore, we explore a dynamic architecture space built on the basis of the proposed baseline with the recent Neural Architecture Search (NAS) paradigm, which first trains a supernet that incorporates all candidate networks and then applies a well-known evolutionary algorithm NSGA-II to discover more efficient networks with higher accuracy and lower computational cost. Experimental results demonstrate that our searched network is competent in ASC tasks, which achieves 90.3% F1-score on the DCASE2018 task 5 evaluation set, marking a new state-of-the-art performance while saving 25% of FLOPs compared to our baseline network.
Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and arithmetic that could be conducted on dedicated embedded systems. In the previous works, the parameter bitwidth is set homogeneously and there is a trade-off between superior performance and aggressive compression. Actually the stacked network layers, which are generally regarded as hierarchical feature extractors, contribute diversely to the overall performance. For a well-trained neural network, the feature distributions of different categories differentiate gradually as the network propagates forward. Hence the capability requirement on the subsequent feature extractors is reduced. It indicates that the neurons in posterior layers could be assigned with lower bitwidth for quantized neural networks. Based on this observation, a simple but effective mixed-precision quantized neural network with progressively ecreasing bitwidth is proposed to improve the trade-off between accuracy and compression. Extensive experiments on typical network architectures and benchmark datasets demonstrate that the proposed method could achieve better or comparable results while reducing the memory space for quantized parameters by more than 30\% in comparison with the homogeneous counterparts. In addition, the results also demonstrate that the higher-precision bottom layers could boost the 1-bit network performance appreciably due to a better preservation of the original image information while the lower-precision posterior layers contribute to the regularization of $k-$bit networks.
We consider the problem of publicly releasing a dataset for support vector machine classification while not infringing on the privacy of data subjects (i.e., individuals whose private information is stored in the dataset). The dataset is systematically obfuscated using an additive noise for privacy protection. Motivated by the Cramer-Rao bound, inverse of the trace of the Fisher information matrix is used as a measure of the privacy. Conditions are established for ensuring that the classifier extracted from the original dataset and the obfuscated one are close to each other (capturing the utility). The optimal noise distribution is determined by maximizing a weighted sum of the measures of privacy and utility. The optimal privacy-preserving noise is proved to achieve local differential privacy. The results are generalized to a broader class of optimization-based supervised machine learning algorithms. Applicability of the methodology is demonstrated on multiple datasets.