In this paper, we propose a Seed-Augment-Train/Transfer (SAT) framework that contains a synthetic seed image dataset generation procedure for languages with different numeral systems using freely available open font file datasets. This seed dataset of images is then augmented to create a purely synthetic training dataset, which is in turn used to train a deep neural network and test on held-out real world handwritten digits dataset spanning five Indic scripts, Kannada, Tamil, Gujarati, Malayalam, and Devanagari. We showcase the efficacy of this approach both qualitatively, by training a Boundary-seeking GAN (BGAN) that generates realistic digit images in the five languages, and also quantitatively by testing a CNN trained on the synthetic data on the real-world datasets. This establishes not only an interesting nexus between the font-datasets-world and transfer learning but also provides a recipe for universal-digit classification in any script.
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce the loss, we extend the GNNs frameworks by exploring the aggregation and iteration scheme in the methodology of mutual information. We propose a new approach of enlarging the normal neighborhood in the aggregation of GNNs, which aims at maximizing mutual information. Based on a series of experiments conducted on several benchmark datasets, we show that the proposed approach improves the state-of-the-art performance for four types of graph tasks, including supervised and semi-supervised graph classification, graph link prediction and graph edge generation and classification.
We study the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies: Bluetooth, Zigbee, and WiFi. We employ deep learning algorithms trained on received samples taken from a 10 MHz band in the 2.4 GHz ISM Band. We obtain a classification accuracy of around 89.5% using any of four different deep neural network architectures: CNN, ResNet, CLDNN, and LSTM, which demonstrate the generality of the effectiveness of deep learning at the considered task. Interestingly, our proposed CNN architecture requires approximately 60% of the training time required by the state of the art while achieving slightly larger classification accuracy. We then focus on the CNN architecture and further optimize its training time while incurring minimal loss in classification accuracy using three different approaches: 1- Band Selection, where we only use samples belonging to the lower and uppermost 2 MHz bands, 2- SNR Selection, where we only use training samples belonging to a single SNR value, and 3- Sample Selection, where we try various sub-Nyquist sampling methods to select the subset of samples most relevant to the classification task. Our results confirm the feasibility of fast deep learning for wireless interference identification, by showing that the training time can be reduced by as much as 30x with minimal loss in accuracy.
Factorization machines (FM) are a popular model class to learn pairwise interactions by a low-rank approximation. Different from existing FM-based approaches which use a fixed rank for all features, this paper proposes a Rank-Aware FM (RaFM) model which adopts pairwise interactions from embeddings with different ranks. The proposed model achieves a better performance on real-world datasets where different features have significantly varying frequencies of occurrences. Moreover, we prove that the RaFM model can be stored, evaluated, and trained as efficiently as one single FM, and under some reasonable conditions it can be even significantly more efficient than FM. RaFM improves the performance of FMs in both regression tasks and classification tasks while incurring less computational burden, therefore also has attractive potential in industrial applications.
We study pragmatics in political campaign text, through analysis of speech acts and the target of each utterance. We propose a new annotation schema incorporating domain-specific speech acts, such as commissive-action, and present a novel annotated corpus of media releases and speech transcripts from the 2016 Australian election cycle. We show how speech acts and target referents can be modeled as sequential classification, and evaluate several techniques, exploiting contextualized word representations, semi-supervised learning, task dependencies and speaker meta-data.
Image classifiers are an important component of today's software, from consumer and business applications to safety-critical domains. The advent of Deep Neural Networks (DNNs) is the key catalyst behind such wide-spread success. However, wide adoption comes with serious concerns about the robustness of software systems dependent on DNNs for image classification, as several severe erroneous behaviors have been reported under sensitive and critical circumstances. We argue that developers need to rigorously test their software's image classifiers and delay deployment until acceptable. We present an approach to testing image classifier robustness based on class property violations. We found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others. These bugs usually violate some class properties of one or more of those classes. Most DNN testing techniques focus on per-image violations, so fail to detect class-level confusions or biases. We developed a testing technique to automatically detect class-based confusion and bias errors in DNN-driven image classification software. We evaluated our implementation, DeepInspect, on several popular image classifiers with precision up to 100% (avg.~72.6%) for confusion errors, and up to 84.3% (avg.~66.8%) for bias errors. DeepInspect found hundreds of classification mistakes in widely-used models, many exposing errors indicating confusion or bias.
Latest algorithms for automatic neural architecture search perform remarkable but are basically directionless in search space and computational expensive in training of every intermediate architecture. In this paper, we propose a method for efficient architecture search called EENA (Efficient Evolution of Neural Architecture). Due to the elaborately designed mutation and crossover operations, the evolution process can be guided by the information have already been learned. Therefore, less computational effort will be required while the searching and training time can be reduced significantly. On CIFAR-10 classification, EENA using minimal computational resources (0.65 GPU-days) can design highly effective neural architecture which achieves 2.56% test error with 8.47M parameters. Furthermore, the best architecture discovered is also transferable for CIFAR-100.
The paper introduces manually annotated test sets for the task of tracing diachronic (temporal) semantic shifts in Russian. The two test sets are complementary in that the first one covers comparatively strong semantic changes occurring to nouns and adjectives from pre-Soviet to Soviet times, while the second one covers comparatively subtle socially and culturally determined shifts occurring in years from 2000 to 2014. Additionally, the second test set offers more granular classification of shifts degree, but is limited to only adjectives. The introduction of the test sets allowed us to evaluate several well-established algorithms of semantic shifts detection (posing this as a classification problem), most of which have never been tested on Russian material. All of these algorithms use distributional word embedding models trained on the corresponding in-domain corpora. The resulting scores provide solid comparison baselines for future studies tackling similar tasks. We publish the datasets, code and the trained models in order to facilitate further research in automatically detecting temporal semantic shifts for Russian words, with time periods of different granularities.
In this paper, we introduce the problem of jointly learning feed-forward neural networks across a set of relevant but diverse datasets. Compared to learning a separate network from each dataset in isolation, joint learning enables us to extract correlated information across multiple datasets to significantly improve the quality of learned networks. We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks. Instead of hand-encoding the shared network layers, we solve an optimization problem to automatically determine how layers should be shared between each pair of datasets. Experimental results show that our approach outperforms baselines without joint learning and those using pretraining-and-fine-tuning. We show the effectiveness of our approach on three tasks: image classification, learning auto-encoders, and image generation.
Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as accurate as Batch Normalization. We resolve a theoretical limitation of Batch Normalization by introducing an unbiased technique for computing the gradient of normalized activations. Online Normalization works with automatic differentiation by adding statistical normalization as a primitive. This technique can be used in cases not covered by some other normalizers, such as recurrent networks, fully connected networks, and networks with activation memory requirements prohibitive for batching. We show its applications to image classification, image segmentation, and language modeling. We present formal proofs and experimental results on ImageNet, CIFAR, and PTB datasets.
We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operations are not natural on graph data. To address these challenges, we propose novel graph pooling (gPool) and unpooling (gUnpool) operations in this work. The gPool layer adaptively selects some nodes to form a smaller graph based on their scalar projection values on a trainable projection vector. We further propose the gUnpool layer as the inverse operation of the gPool layer. The gUnpool layer restores the graph into its original structure using the position information of nodes selected in the corresponding gPool layer. Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models.
Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets.
Graph Neural Nets (GNNs) have received increasing attentions, partially due to their superior performance in many node and graph classification tasks. However, there is a lack of understanding on what they are learning and how sophisticated the learned graph functions are. In this work, we propose a dissection of GNNs on graph classification into two parts: 1) the graph filtering, where graph-based neighbor aggregations are performed, and 2) the set function, where a set of hidden node features are composed for prediction. To study the importance of both parts, we propose to linearize them separately. We first linearize the graph filtering function, resulting Graph Feature Network (GFN), which is a simple lightweight neural net defined on a \textit{set} of graph augmented features. Further linearization of GFN's set function results in Graph Linear Network (GLN), which is a linear function. Empirically we perform evaluations on common graph classification benchmarks. To our surprise, we find that, despite the simplification, GFN could match or exceed the best accuracies produced by recently proposed GNNs (with a fraction of computation cost), while GLN underperforms significantly. Our results demonstrate the importance of non-linear set function, and suggest that linear graph filtering with non-linear set function is an efficient and powerful scheme for modeling existing graph classification benchmarks.
Supervised classification is the most active and emerging research trends in today's scenario. In this view, Artificial Neural Network (ANN) techniques have been widely employed and growing interest to the researchers day by day. ANN training aims to find the proper setting of parameters such as weights ($\textbf{W}$) and biases ($b$) to properly classify the given data samples. The training process is formulated in an error minimization problem which consists of many local optima in the search landscape. In this paper, an enhanced Particle Swarm Optimization is proposed to minimize the error function for classifying real-life data sets. A stability analysis is performed to establish the efficiency of the proposed method for improving classification accuracy. The performance measurement such as confusion matrix, $F$-measure and convergence graph indicates the significant improvement in the classification accuracy.
Histopathology slides are routinely marked by pathologists using permanent ink markers that should not be removed as they form part of the medical record. Often tumour regions are marked up for the purpose of highlighting features or other downstream processing such an gene sequencing. Once digitised there is no established method for removing this information from the whole slide images limiting its usability in research and study. Removal of marker ink from these high-resolution whole slide images is non-trivial and complex problem as they contaminate different regions and in an inconsistent manner. We propose an efficient pipeline using convolution neural networks that results in ink-free images without compromising information and image resolution. Our pipeline includes a sequential classical convolution neural network for accurate classification of contaminated image tiles, a fast region detector and a domain adaptive cycle consistent adversarial generative model for restoration of foreground pixels. Both quantitative and qualitative results on four different whole slide images show that our approach yields visually coherent ink-free whole slide images.
Understanding biological network dynamics is a fundamental issue in various scientific and engineering fields. Network theory is capable of revealing the relationship between elements and their propagation; however, for complex collective motions, the network properties often transiently and complexly change. A fundamental question addressed here pertains to the classification of collective motion network based on physically-interpretable dynamical properties. Here we apply a data-driven spectral analysis called graph dynamic mode decomposition, which obtains the dynamical properties for collective motion classification. Using a ballgame as an example, we classified the strategic collective motions in different global behaviours and discovered that, in addition to the physical properties, the contextual node information was critical for classification. Furthermore, we discovered the label-specific stronger spectra in the relationship among the nearest agents, providing physical and semantic interpretations. Our approach contributes to the understanding of principles of biological complex network dynamics from the perspective of nonlinear dynamical systems.
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. The resulting graph of prototypes can be continually re-used and updated for new tasks and classes. We also introduce two practical test/inference settings which differ according to whether the test task can leverage any weakly-supervised information as in training. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.
Machine learning techniques typically rely on large datasets to create accurate classifiers. However, there are situations when data is scarce and expensive to acquire. This is the case of studies that rely on state-of-the-art computational models which typically take days to run, thus hindering the potential of machine learning tools. In this work, we present a novel classifier that takes advantage of lower fidelity models and inexpensive approximations to predict the binary output of expensive computer simulations. We postulate an autoregressive model between the different levels of fidelity with Gaussian process priors. We adopt a fully Bayesian treatment for the hyper-parameters and use Markov Chain Mont Carlo samplers. We take advantage of the probabilistic nature of the classifier to implement active learning strategies. We also introduce a sparse approximation to enhance the ability of themulti-fidelity classifier to handle large datasets. We test these multi-fidelity classifiers against their single-fidelity counterpart with synthetic data, showing a median computational cost reduction of 23% for a target accuracy of 90%. In an application to cardiac electrophysiology, the multi-fidelity classifier achieves an F1 score, the harmonic mean of precision and recall, of 99.6% compared to 74.1% of a single-fidelity classifier when both are trained with 50 samples. In general, our results show that the multi-fidelity classifiers outperform their single-fidelity counterpart in terms of accuracy in all cases. We envision that this new tool will enable researchers to study classification problems that would otherwise be prohibitively expensive. Source code is available at https://github.com/fsahli/MFclass.
Pattern analysis often requires a pre-processing stage for extracting or selecting features in order to help the classification, prediction, or clustering stage discriminate or represent the data in a better way. The reason for this requirement is that the raw data are complex and difficult to process without extracting or selecting appropriate features beforehand. This paper reviews theory and motivation of different common methods of feature selection and extraction and introduces some of their applications. Some numerical implementations are also shown for these methods. Finally, the methods in feature selection and extraction are compared.
Objective: This work addresses two key problems of skin lesion classification. The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification. The second problem is the high class imbalance encountered in real-world multi-class datasets. Methods: To use high-resolution images, we propose a novel patch-based attention architecture that provides global context between small, high-resolution patches. We modify three pretrained architectures and study the performance of patch-based attention. To counter class imbalance problems, we compare oversampling, balanced batch sampling, and class-specific loss weighting. Additionally, we propose a novel diagnosis-guided loss weighting method which takes the method used for ground-truth annotation into account. Results: Our patch-based attention mechanism outperforms previous methods and improves the mean sensitivity by 7%. Class balancing significantly improves the mean sensitivity and we show that our diagnosis-guided loss weighting method improves the mean sensitivity by 3% over normal loss balancing. Conclusion: The novel patch-based attention mechanism can be integrated into pretrained architectures and provides global context between local patches while outperforming other patch-based methods. Hence, pretrained architectures can be readily used with high-resolution images without downsampling. The new diagnosis-guided loss weighting method outperforms other methods and allows for effective training when facing class imbalance. Significance: The proposed methods improve automatic skin lesion classification. They can be extended to other clinical applications where high-resolution image data and class imbalance are relevant.