In binary classification, there are situations where negative (N) data are too diverse to be fully labeled and we often resort to positive-unlabeled (PU) learning in these scenarios. However, collecting a non-representative N set that contains only a small portion of all possible N data can often be much easier in practice. This paper studies a novel classification framework which incorporates such biased N (bN) data in PU learning. We provide a method based on empirical risk minimization to address this PUbN classification problem. Our approach can be regarded as a novel example-weighting algorithm, with the weight of each example computed through a preliminary step that draws inspiration from PU learning. We also derive an estimation error bound for the proposed method. Experimental results demonstrate the effectiveness of our algorithm in not only PUbN learning scenarios but also ordinary PU learning scenarios on several benchmark datasets.
Graph Neural Networks (GNNs) are an effective framework for representation learning of graphs. GNNs follow a neighborhood aggregation scheme, where the representation vector of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes. Many GNN variants have been proposed and have achieved state-of-the-art results on both node and graph classification tasks. However, despite GNNs revolutionizing graph representation learning, there is limited understanding of their representational properties and limitations. Here, we present a theoretical framework for analyzing the expressive power of GNNs to capture different graph structures. Our results characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures. We then develop a simple architecture that is provably the most expressive among the class of GNNs and is as powerful as the Weisfeiler-Lehman graph isomorphism test. We empirically validate our theoretical findings on a number of graph classification benchmarks, and demonstrate that our model achieves state-of-the-art performance.
Link prediction in a graph is the problem of detecting the missing links that would be formed in the near future. Using a graph representation of the data, we can convert the problem of classification to the problem of link prediction which aims at finding the missing links between the unlabeled data (unlabeled nodes) and their classes. To our knowledge, despite the fact that numerous algorithms use the graph representation of the data for classification, none are using link prediction as the heart of their classifying procedure. In this work, we propose a novel algorithm called CULP (Classification Using Link Prediction) which uses a new structure namely Label Embedded Graph or LEG and a link predictor to find the class of the unlabeled data. Different link predictors along with Compatibility Score - a new link predictor we proposed that is designed specifically for our settings - has been used and showed promising results for classifying different datasets. This paper further improved CULP by designing an extension called CULM which uses a majority vote (hence the M in the acronym) procedure with weights proportional to the predictions' confidences to use the predictive power of multiple link predictors and also exploits the low level features of the data. Extensive experimental evaluations shows that both CULP and CULM are highly accurate and competitive with the cutting edge graph classifiers and general classifiers.
In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients. To address the vanishing gradient issue, we study a framework, where we insert an intermediate output branch after each layer in the computational graph and use the corresponding prediction loss for feeding the gradient to the early layers. The framework - which we name Elastic network - is tested with several well-known networks on CIFAR10 and CIFAR100 datasets, and the experimental results show that the proposed framework improves the accuracy on both shallow networks (e.g., MobileNet) and deep convolutional neural networks (e.g., DenseNet). We also identify the types of networks where the framework does not improve the performance and discuss the reasons. Finally, as a side product, the computational complexity of the resulting networks can be adjusted in an elastic manner by selecting the output branch according to current computational budget.
We introduce modifications to state-of-the-art approaches to aggregating local video descriptors by using attention mechanisms and function approximations. Rather than using ensembles of existing architectures, we provide an insight on creating new architectures. We demonstrate our solutions in the "The 2nd YouTube-8M Video Understanding Challenge", by using frame-level video and audio descriptors. We obtain testing accuracy similar to the state of the art, while meeting budget constraints, and touch upon strategies to improve the state of the art. Model implementations are available in https://github.com/pomonam/LearnablePoolingMethods.
Despite being very effective in several classification tasks, Dynamic Ensemble Selection (DES) techniques can select classifiers that classify all samples in the region of competence as being from the same class. The Frienemy Indecision REgion DES (FIRE-DES) tackles this problem by pre-selecting classifiers that correctly classify at least one pair of samples from different classes in the region of competence of the test sample. However, FIRE-DES applies the pre-selection for the classification of a test sample if and only if its region of competence is composed of samples from different classes (indecision region), even though this criterion is not reliable for determining if a test sample is located close to the borders of classes (true indecision region) when the region of competence is obtained using classical nearest neighbors approach. Because of that, FIRE-DES mistakes noisy regions for true indecision regions, leading to the pre-selection of incompetent classifiers, and mistakes true indecision regions for safe regions, leaving samples in such regions without any pre-selection. To tackle these issues, we propose the FIRE-DES++, an enhanced FIRE-DES that removes noise and reduces the overlap of classes in the validation set; and defines the region of competence using an equal number of samples of each class, avoiding selecting a region of competence with samples of a single class. Experiments are conducted using FIRE-DES++ with 8 different dynamic selection techniques on 64 classification datasets. Experimental results show that FIRE-DES++ increases the classification performance of all DES techniques considered in this work, outperforming FIRE-DES with 7 out of the 8 DES techniques, and outperforming state-of-the-art DES frameworks.
For most animal species, quick and reliable identification of visual objects is critical for survival. This applies also to rodents, which, in recent years, have become increasingly popular models of visual functions. For this reason in this work we analyzed how various properties of visual objects are represented in rat primary visual cortex (V1). The analysis has been carried out through supervised (classification) and unsupervised (clustering) learning methods. We assessed quantitatively the discrimination capabilities of V1 neurons by demonstrating how photometric properties (luminosity and object position in the scene) can be derived directly from the neuronal responses.
Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In practice, collecting large scale accurately labeled datasets is a challenging and tedious task in most scenarios of remote sensing image analysis, thus cheap surrogate procedures are employed to label the dataset. Training deep neural networks on such datasets with inaccurate labels easily overfits to the noisy training labels and degrades the performance of the classification tasks drastically. To mitigate this effect, we propose an original solution with entropic optimal transportation. It allows to learn in an end-to-end fashion deep neural networks that are, to some extent, robust to inaccurately labeled samples. We empirically demonstrate on several remote sensing datasets, where both scene and pixel-based hyperspectral images are considered for classification. Our method proves to be highly tolerant to significant amounts of label noise and achieves favorable results against state-of-the-art methods.
Automatic sleep staging has been often treated as a simple classification problem that aims at determining the label of individual target polysomnography (PSG) epochs one at a time. In this work, we tackle the task as a sequence-to-sequence classification problem that receives a sequence of multiple epochs as input and classifies all of their labels at once. For this purpose, we propose a hierarchical recurrent neural network named SeqSleepNet. At the epoch processing level, the network consists of a filterbank layer tailored to learn frequency-domain filters for preprocessing and an attention-based recurrent layer designed for short-term sequential modelling. At the sequence processing level, a recurrent layer placed on top of the learned epoch-wise features for long-term modelling of sequential epochs. The classification is then carried out on the output vectors at every time step of the top recurrent layer to produce the sequence of output labels. Despite being hierarchical, we present a strategy to train the network in an end-to-end fashion. We show that the proposed network outperforms state-of-the-art approaches, achieving an overall accuracy, macro F1-score, and Cohen's kappa of 87.1%, 83.3%, and 0.815 on a publicly available dataset with 200 subjects.
The goal of confidence-set learning in the binary classification setting is to construct two sets, each with a specific probability guarantee to cover a class. An observation outside the overlap of the two sets is deemed to be from one of the two classes, while the overlap is an ambiguity region which could belong to either class. Instead of plug-in approaches, we propose a support vector classifier to construct confidence sets in a flexible manner. Theoretically, we show that the proposed learner can control the non-coverage rates and minimize the ambiguity with high probability. Efficient algorithms are developed and numerical studies illustrate the effectiveness of the proposed method.
A real-world dataset is provided from a pulp-and-paper manufacturing industry. The dataset comes from a multivariate time series process. The data contains a rare event of paper break that commonly occurs in the industry. The data contains sensor readings at regular time-intervals (x's) and the event label (y). The primary purpose of the data is thought to be building a classification model for early prediction of the rare event. However, it can also be used for multivariate time series data exploration and building other supervised and unsupervised models.
In this paper, we target the problem of fracture classification from clinical X-Ray images towards an automated Computer Aided Diagnosis (CAD) system. Although primarily dealing with an image classification problem, we argue that localizing the fracture in the image is crucial to make good class predictions. Therefore, we propose and thoroughly analyze several schemes for simultaneous fracture localization and classification. We show that using an auxiliary localization task, in general, improves the classification performance. Moreover, it is possible to avoid the need for additional localization annotations thanks to recent advancements in weakly-supervised deep learning approaches. Among such approaches, we investigate and adapt Spatial Transformers (ST), Self-Transfer Learning (STL), and localization from global pooling layers. We provide a detailed quantitative and qualitative validation on a dataset of 1347 femur fractures images and report high accuracy with regard to inter-expert correlation values reported in the literature. Our investigations show that i) lesion localization improves the classification outcome, ii) weakly-supervised methods improve baseline classification without any additional cost, iii) STL guides feature activations and boost performance. We plan to make both the dataset and code available.
Multiple query criteria active learning (MQCAL) methods have a higher potential performance than conventional active learning methods in which only one criterion is deployed for sample selection. A central issue related to MQCAL methods concerns the development of an integration criteria strategy (ICS) that makes full use of all criteria. The conventional ICS adopted in relevant research all facilitate the desired effects, but several limitations still must be addressed. For instance, some of the strategies are not sufficiently scalable during the design process, and the number and type of criteria involved are dictated. Thus, it is challenging for the user to integrate other criteria into the original process unless modifications are made to the algorithm. Other strategies are too dependent on empirical parameters, which can only be acquired by experience or cross-validation and thus lack generality; additionally, these strategies are counter to the intention of active learning, as samples need to be labeled in the validation set before the active learning process can begin. To address these limitations, we propose a novel MQCAL method for classification tasks that employs a third strategy via weighted rank aggregation. The proposed method serves as a heuristic means to select high-value samples of high scalability and generality and is implemented through a three-step process: (1) the transformation of the sample selection to sample ranking and scoring, (2) the computation of the self-adaptive weights of each criterion, and (3) the weighted aggregation of each sample rank list. Ultimately, the sample at the top of the aggregated ranking list is the most comprehensively valuable and must be labeled. Several experiments generating 257 wins, 194 ties and 49 losses against other state-of-the-art MQCALs are conducted to verify that the proposed method can achieve superior results.
We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks more introspective by adding a new training loss which prevents them from being overconfident. Our method is more efficient than Bayesian neural networks or model ensembles which, despite providing more reliable uncertainty scores, are more cumbersome to train and slower to test. We evaluate DDN on the the task of image classification on the CIFAR-10 dataset and show that our calibration results are competitive even when compared to 100 Monte Carlo samples from a dropout network while they also increase the classification accuracy. We also propose better calibration within the state of the art Faster R-CNN object detection framework and show, using the COCO dataset, that DDN helps train better calibrated object detectors.
In this paper we will attempt to classify Lindenmayer systems based on properties of sets of rules and the kind of strings those rules generate. This classification will be referred to as a parametrization of the L-space: the L-space is the phase space in which all possible L-developments are represented. This space is infinite, because there is no halting algorithm for L-grammars; but it is also subjected to hard conditions, because there are grammars and developments which are not possible states of an L-system: a very well-known example is the space of normal grammars. Just as the space of normal grammars is parametrized into Regular, Context-Free, Context-Sensitive, and Unrestricted (with proper containment relations holding among them; see Chomsky, 1959: Theorem 1), we contend here that the L-space is a very rich landscape of grammars which cluster into kinds that are not mutually translatable.
The automated wafer inspection and quality control is a complex and time-consuming task, which can speed up using neuromorphic memristive architectures, as a separate inspection device or integrating directly into sensors. This paper presents the performance analysis and comparison of different neuromorphic architectures for patterned wafer quality inspection and classification. The application of non-volatile memristive devices in these architectures ensures low power consumption, small on-chip area scalability. We demonstrate that Long-Short Term Memory (LSTM) outperforms other architectures for the same number of training iterations, and has relatively low on-chip area and power consumption.
We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.
Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification. We examine batch normalization on the one hand and the dynamical systems view of residual networks on the other hand. Our goal is in understanding the notions of stability and smoothness of the inter-layer propagation of ResNets so as to explain when they contribute to significantly enhanced performance. We postulate that such stability is of importance for the trained ResNet to transfer.
In this paper, we propose a novel technique for sampling sequential images using a cylindrical transform in a cylindrical coordinate system for kidney semantic segmentation in abdominal computed tomography (CT). The images generated from a cylindrical transform augment a limited annotated set of images in three dimensions. This approach enables us to train contemporary classification deep convolutional neural networks (DCNNs) instead of fully convolutional networks (FCNs) for semantic segmentation. Typical semantic segmentation models segment a sequential set of images (e.g. CT or video) by segmenting each image independently. However, the proposed method not only considers the spatial dependency in the x-y plane, but also the spatial sequential dependency along the z-axis. The results show that classification DCNNs, trained on cylindrical transformed images, can achieve a higher segmentation performance value than FCNs using a limited number of annotated images.
Computer-aided diagnosis systems for classification of different type of skin lesions have been an active field of research in recent decades. It has been shown that introducing lesions and their attributes masks into lesion classification pipeline can greatly improve the performance. In this paper, we propose a framework by incorporating transfer learning for segmenting lesions and their attributes based on the convolutional neural networks. The proposed framework is based on the encoder-decoder architecture which utilizes a variety of pre-trained networks in the encoding path and generates the prediction map by combining multi-scale information in decoding path using a pyramid pooling manner. To address the lack of training data and increase the proposed model generalization, an extensive set of novel domain-specific augmentation routines have been applied to simulate the real variations in dermoscopy images. Finally, by performing broad experiments on three different data sets obtained from International Skin Imaging Collaboration archive (ISIC2016, ISIC2017, and ISIC2018 challenges data sets), we show that the proposed method outperforms other state-of-the-art approaches for ISIC2016 and ISIC2017 segmentation task and achieved the first rank on the leader-board of ISIC2018 attribute detection task.