Imbalanced classification tasks are widespread in many real-world applications. For such classification tasks, in comparison with the accuracy rate, it is usually much more appropriate to use non-decomposable performance measures such as the Area Under the receiver operating characteristic Curve (AUC) and the $F_\beta$ measure as the classification criterion since the label class is imbalanced. On the other hand, the minimax probability machine is a popular method for binary classification problems and aims at learning a linear classifier by maximizing the accuracy rate, which makes it unsuitable to deal with imbalanced classification tasks. The purpose of this paper is to develop a new minimax probability machine for the $F_\beta$ measure, called MPMF, which can be used to deal with imbalanced classification tasks. A brief discussion is also given on how to extend the MPMF model for several other non-decomposable performance measures listed in the paper. To solve the MPMF model effectively, we derive its equivalent form which can then be solved by an alternating descent method to learn a linear classifier. Further, the kernel trick is employed to derive a nonlinear MPMF model to learn a nonlinear classifier. Several experiments on real-world benchmark datasets demonstrate the effectiveness of our new model.
PySensors is a Python package for selecting and placing a sparse set of sensors for classification and reconstruction tasks. Specifically, PySensors implements algorithms for data-driven sparse sensor placement optimization for reconstruction (SSPOR) and sparse sensor placement optimization for classification (SSPOC). In this work we provide a brief description of the mathematical algorithms and theory for sparse sensor optimization, along with an overview and demonstration of the features implemented in PySensors (with code examples). We also include practical advice for user and a list of potential extensions to PySensors. Software is available at https://github.com/dynamicslab/pysensors.
The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization, where the input is randomly embedded into a different feature space in each layer. In this paper, we propose an interpretation method for a deep multilayer perceptron, which is the most general architecture of NNs, based on identity initialization (namely, initialization using identity matrices). The proposed method allows us to analyze the contribution of each neuron to classification and class likelihood in each hidden layer. As a property of the identity-initialized perceptron, the weight matrices remain near the identity matrices even after learning. This property enables us to treat the change of features from the input to each hidden layer as the contribution to classification. Furthermore, we can separate the output of each hidden layer into a contribution map that depicts the contribution to classification and class likelihood, by adding extra dimensions to each layer according to the number of classes, thereby allowing the calculation of the recognition accuracy in each layer and thus revealing the roles of independent layers, such as feature extraction and classification.
Recently, convolutional Neural Networks (CNNs) have exhibited commendable performance for hyperspectral image (HSI) classification. Generally, an important number of samples are needed for each class to properly train CNNs. However, existing HSI datasets suffer from a significant class imbalance problem, where many classes do not have enough samples to characterize the spectral information. The performance of existing CNN models is biased towards the majority classes, which possess more samples for the training. This paper addresses this issue of imbalanced data in HSI classification. In particular, a new 3D-HyperGAMO model is proposed which uses generative adversarial minority oversampling. The proposed 3D-HyperGAMO automatically generates more samples for minority classes at training time, using the existing samples of that class. The samples are generated in the form of a 3D hyperspectral patch. A different classifier from the generator and the discriminator is used in the 3D-HyperGAMO model, which is trained using both original and generated samples to {determine} the classes of newly generated samples to which they actually belong. The generated data are combined class-wise with the original training dataset to learn the network parameters of the class. Finally, the trained 3D classifier network validates the performance of the model using the test set. Four benchmark HSI datasets, namely Indian Pines~(IP), Kennedy Space Center~(KSC), University of Pavia~(UP), and Botswana~(BW), have been considered in our experiments. The proposed model shows outstanding data generation ability during the training, which significantly improves the classification performance over the considered datasets. The source code is available publicly at \url{https://github.com/mhaut/3D-HyperGAMO}.
Some data analysis applications comprise datasets, where explanatory variables are expensive or tedious to acquire, but auxiliary data are readily available and might help to construct an insightful training set. An example is neuroimaging research on mental disorders, specifically learning a diagnosis/prognosis model based on variables derived from expensive Magnetic Resonance Imaging (MRI) scans, which often requires large sample sizes. Auxiliary data, such as demographics, might help in selecting a smaller sample that comprises the individuals with the most informative MRI scans. In active learning literature, this problem has not yet been studied, despite promising results in related problem settings that concern the selection of instances or instance-feature pairs. Therefore, we formulate this complementary problem of Active Selection of Classification Features (ASCF): Given a primary task, which requires to learn a model f: x-> y to explain/predict the relationship between an expensive-to-acquire set of variables x and a class label y. Then, the ASCF-task is to use a set of readily available selection variables z to select these instances, that will improve the primary task's performance most when acquiring their expensive features z and including them to the primary training set. We propose two utility-based approaches for this problem, and evaluate their performance on three public real-world benchmark datasets. In addition, we illustrate the use of these approaches to efficiently acquire MRI scans in the context of neuroimaging research on mental disorders, based on a simulated study design with real MRI data.
Searching for new information requires talking to the system. In this research, an Open-domain Conversational information search system has been developed. This system has been implemented using the TREC CAsT 2019 track, which is one of the first attempts to build a framework in this area. According to the user's previous questions, the system firstly completes the question (using the first and the previous question in each turn) and then classifies it (based on the question words). This system extracts the related answers according to the rules of each question. In this research, a simple yet effective method with high performance has been used, which on average, extracts 20% more relevant results than the baseline.
Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated dataset-specific methods. Moreover, typical tasks such as classification and retrieval lack a systematic evaluation on standard benchmarks and training datasets, which make it hard to identify durable and generalizable scientific contributions. We aim at unifying remote sensing image retrieval and classification with a new large-scale training and testing dataset, SF300, including both vertical and oblique aerial images and made available to the research community, and an associated fine-tuning method. We additionally propose a new adversarial fine-tuning method for global descriptors. We show that our framework systematically achieves a boost of retrieval and classification performance on nine different datasets compared to an ImageNet pretrained baseline, with currently no other method to compare to.
Deep learning approaches have shown great success in image classification tasks and can aid greatly towards the fast and reliable classification of pollen grain aerial imagery. However, often-times deep learning methods in the setting of natural images can suffer generalization problems and yield poor performance on unseen test distribution. In this work, we present and a robust deep learning framework that can generalize well for pollen grain aerobiological imagery classification. We develop a convolutional neural network-based pollen grain classification approach and combine some of the best practices in deep learning for better generalization. In addition to commonplace approaches like data-augmentation and weight regularization, we utilize implicit regularization methods like manifold mixup to allow learning of smoother decision boundaries. We also make use of proven state-of-the-art architectural choices like EfficientNet convolutional neural networks. Inspired by the success of generative modeling with variational autoencoders, we train models with a richer learning objective which can allow the model to focus on the relevant parts of the image. Finally, we create an ensemble of neural networks, for the robustness of the test set predictions. Based on our experiments, we show improved generalization performance as measured with a weighted F1-score with the aforementioned approaches. The proposed approach earned a fourth-place in the final rankings in the ICPR-2020 Pollen Grain Classification Challenge; with a 0.972578 weighted F1 score,0.950828 macro average F1 scores, and 0.972877 recognition accuracy.
As witnessed in the past year, where the world was brought to the ground by a pandemic, fighting Life-threatening diseases have found greater focus than ever. The first step in fighting a disease is to diagnose it at the right time. Diabetes has been affecting people for a long time and is growing among people faster than ever. The number of people who have Diabetes reached 422 million in 2018, as reported by WHO, and the global prevalence of diabetes among adults above the age of 18 has risen to 8.5%. Now Diabetes is a disease that shows no or very few symptoms among the people affected by it for a long time, and even in some cases, people realize they have it when they have lost any chance of controlling it. So getting Diabetes diagnosed at an early stage can make a huge difference in how one can approach curing it. Moving in this direction in this paper, we have designed a liquid machine learning approach to detect Diabetes with no cost using deep learning. In this work, we have used a dataset of 520 instances. Our approach shows a significant improvement in the previous state-of-the-art results. Its power to generalize well on small dataset deals with the critical problem of lesser data in medical sciences.
Deployment, operation and maintenance of large IT systems becomes increasingly complex and puts human experts under extreme stress when problems occur. Therefore, utilization of machine learning (ML) and artificial intelligence (AI) is applied on IT system operation and maintenance - summarized in the term AIOps. One specific direction aims at the recognition of re-occurring anomaly types to enable remediation automation. However, due to IT system specific properties, especially their frequent changes (e.g. software updates, reconfiguration or hardware modernization), recognition of reoccurring anomaly types is challenging. Current methods mainly assume a static dimensionality of provided data. We propose a method that is invariant to dimensionality changes of given data. Resource metric data such as CPU utilization, allocated memory and others are modelled as multivariate time series. The extraction of temporal and spatial features together with the subsequent anomaly classification is realized by utilizing TELESTO, our novel graph convolutional neural network (GCNN) architecture. The experimental evaluation is conducted in a real-world cloud testbed deployment that is hosting two applications. Classification results of injected anomalies on a cassandra database node show that TELESTO outperforms the alternative GCNNs and achieves an overall classification accuracy of 85.1%. Classification results for the other nodes show accuracy values between 85% and 60%.
Cervical cancer, one of the most common fatal cancers among women, can be prevented by regular screening to detect any precancerous lesions at early stages and treat them. Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors. To improve the manual screening practice, machine learning (ML) and deep learning (DL) based computer-aided diagnostic (CAD) systems have been investigated widely to classify cervical pap cells. Most of the existing researches require pre-segmented images to obtain good classification results, whereas accurate cervical cell segmentation is challenging because of cell clustering. Some studies rely on handcrafted features, which cannot guarantee the classification stage's optimality. Moreover, DL provides poor performance for a multiclass classification task when there is an uneven distribution of data, which is prevalent in the cervical cell dataset. This investigation has addressed those limitations by proposing DeepCervix, a hybrid deep feature fusion (HDFF) technique based on DL to classify the cervical cells accurately. Our proposed method uses various DL models to capture more potential information to enhance classification performance. Our proposed HDFF method is tested on the publicly available SIPAKMED dataset and compared the performance with base DL models and the LF method. For the SIPAKMED dataset, we have obtained the state-of-the-art classification accuracy of 99.85%, 99.38%, and 99.14% for 2-class, 3-class, and 5-class classification. Moreover, our method is tested on the Herlev dataset and achieves an accuracy of 98.32% for binary class and 90.32% for 7-class classification.
Most of the classic texts in Kurdish literature are poems. Knowing the meter of the poems is helpful for correct reading, a better understanding of the meaning, and avoidance of ambiguity. This paper presents a rule-based method for automatic classification of the poem meter for the Central Kurdish language. The metrical system of Kurdish poetry is divided into three classes of quantitative, syllabic, and free verses. As the vowel length is not phonemic in the language, there are uncertainties in syllable weight and meter identification. The proposed method generates all the possible situations and then, by considering all lines of the input poem and the common meter patterns of Kurdish poetry, identifies the most probable meter type and pattern of the input poem. Evaluation of the method on a dataset from VejinBooks Kurdish corpus resulted in 97.3% of precision in meter type and 96.2% of precision in pattern identification.
Multi-class classification problem is among the most popular and well-studied statistical frameworks. Modern multi-class datasets can be extremely ambiguous and single-output predictions fail to deliver satisfactory performance. By allowing predictors to predict a set of label candidates, set-valued classification offers a natural way to deal with this ambiguity. Several formulations of set-valued classification are available in the literature and each of them leads to different prediction strategies. The present survey aims to review popular formulations using a unified statistical framework. The proposed framework encompasses previously considered and leads to new formulations as well as it allows to understand underlying trade-offs of each formulation. We provide infinite sample optimal set-valued classification strategies and review a general plug-in principle to construct data-driven algorithms. The exposition is supported by examples and pointers to both theoretical and practical contributions. Finally, we provide experiments on real-world datasets comparing these approaches in practice and providing general practical guidelines.
Online property business or known as e-commerce is currently experiencing an increase in home sales. Indonesia's e-commerce property business has positive trending shown by the increasing sales of more than 500% from 2011 to 2015. A prediction of the property price is important to help investors or the public to have accurate information before buying property. One of the methods for prediction is a classification based on several distinctive property industry attributes, such as building size, land size, number of rooms, and location. Today, data is easily obtained, there are many open data from E-commerce sites. E-commerce contains information about homes and other properties advertised to sell. People also regularly visit the site to find the right property or to sell the property using price information which collectively available as open data. To predict the property sales, this research employed two different classification methods in Data Mining which are Decision Tree and k-NN classification. We compare which model classification is better to predict property price and their attributes. We use Indonesia's biggest property-based e-commerce site Rumah123.com as our open data source, and choose location Bandung in our experiment. The accuracy result of the decision tree is 75% and KNN is 71%, other than that k-NN can explore more data patterns than the Decision Tree.
Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classification etc. Graph embedding, which learns low-dimensional representations for vertices or edges in the graph, usually employs deep models to derive the embedding vector. However, these models are vulnerable. We envision that graph embedding methods based on deep models can be easily attacked using adversarial examples. Thus, in this paper, we propose Graphfool, a novel targeted label adversarial attack on graph embedding. It can generate adversarial graph to attack graph embedding methods via classifying boundary and gradient information in graph convolutional network (GCN). Specifically, we perform the following steps: 1),We first estimate the classification boundaries of different classes. 2), We calculate the minimal perturbation matrix to misclassify the attacked vertex according to the target classification boundary. 3), We modify the adjacency matrix according to the maximal absolute value of the disturbance matrix. This process is implemented iteratively. To the best of our knowledge, this is the first targeted label attack technique. The experiments on real-world graph networks demonstrate that Graphfool can derive better performance than state-of-art techniques. Compared with the second best algorithm, Graphfool can achieve an average improvement of 11.44% in attack success rate.
Classification with abstention has gained a lot of attention in recent years as it allows to incorporate human decision-makers in the process. Yet, abstention can potentially amplify disparities and lead to discriminatory predictions. The goal of this work is to build a general purpose classification algorithm, which is able to abstain from prediction, while avoiding disparate impact. We formalize this problem as risk minimization under fairness and abstention constraints for which we derive the form of the optimal classifier. Building on this result, we propose a post-processing classification algorithm, which is able to modify any off-the-shelf score-based classifier using only unlabeled sample. We establish finite sample risk, fairness, and abstention guarantees for the proposed algorithm. In particular, it is shown that fairness and abstention constraints can be achieved independently from the initial classifier as long as sufficiently many unlabeled data is available. The risk guarantee is established in terms of the quality of the initial classifier. Our post-processing scheme reduces to a sparse linear program allowing for an efficient implementation, which we provide. Finally, we validate our method empirically showing that moderate abstention rates allow to bypass the risk-fairness trade-off.
Since its introduction two decades ago, there has been increasing interest in the problem of early classification of time series. This problem generalizes classic time series classification to ask if we can classify a time series subsequence with sufficient accuracy and confidence after seeing only some prefix of a target pattern. The idea is that the earlier classification would allow us to take immediate action, in a domain in which some practical interventions are possible. For example, that intervention might be sounding an alarm or applying the brakes in an automobile. In this work, we make a surprising claim. In spite of the fact that there are dozens of papers on early classification of time series, it is not clear that any of them could ever work in a real-world setting. The problem is not with the algorithms per se but with the vague and underspecified problem description. Essentially all algorithms make implicit and unwarranted assumptions about the problem that will ensure that they will be plagued by false positives and false negatives even if their results suggested that they could obtain near-perfect results. We will explain our findings with novel insights and experiments and offer recommendations to the community.
Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content. However, graphs with unattributed nodes widely exist in real-world applications (e.g., anonymized social networks). Previous GNNs either assign random labels to nodes (which introduces artefacts to the GNN) or assign one embedding to all nodes (which fails to explicitly distinguish one node from another). Further, when these GNNs are applied to unattributed node classification problems, they have an undesired equivariance property, which are fundamentally unable to address the data with multiple possible outputs. In this paper, we analyze the limitation of existing approaches to node classification problems. Inspired by our analysis, we propose a generalized equivariance property and a Preferential Labeling technique that satisfies the desired property asymptotically. Experimental results show that we achieve high performance in several unattributed node classification tasks.
Large, heterogeneous datasets are characterized by missing or even erroneous information. This is more evident when they are the product of community effort or automatic fact extraction methods from external sources, such as text. A special case of the aforementioned phenomenon can be seen in knowledge graphs, where this mostly appears in the form of missing or incorrect edges and nodes. Structured querying on such incomplete graphs will result in incomplete sets of answers, even if the correct entities exist in the graph, since one or more edges needed to match the pattern are missing. To overcome this problem, several algorithms for approximate structured query answering have been proposed. Inspired by modern Information Retrieval metrics, these algorithms produce a ranking of all entities in the graph, and their performance is further evaluated based on how high in this ranking the correct answers appear. In this work we take a critical look at this way of evaluation. We argue that performing a ranking-based evaluation is not sufficient to assess methods for complex query answering. To solve this, we introduce Message Passing Query Boxes (MPQB), which takes binary classification metrics back into use and shows the effect this has on the recently proposed query embedding method MPQE.
In data containing heterogeneous subpopulations, classification performance benefits from incorporating the knowledge of cluster structure in the classifier. Previous methods for such combined clustering and classification either 1) are classifier-specific and not generic, or 2) independently perform clustering and classifier training, which may not form clusters that can potentially benefit classifier performance. The question of how to perform clustering to improve the performance of classifiers trained on the clusters has received scant attention in previous literature, despite its importance in several real-world applications. In this paper, first, we theoretically analyze the generalization performance of classifiers trained on clustered data and find conditions under which clustering can potentially aid classification. This motivates the design of a simple k-means-based classification algorithm called Clustering Aware Classification (CAC) and its neural variant {DeepCAC}. DeepCAC effectively leverages deep representation learning to learn latent embeddings and finds clusters in a manner that make the clustered data suitable for training classifiers for each underlying subpopulation. Our experiments on synthetic and real benchmark datasets demonstrate the efficacy of DeepCAC over previous methods for combined clustering and classification.