Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high. To overcome this problem, we propose a new weakly-supervised learning setting where only similar (S) data pairs (two examples belong to the same class) and unlabeled (U) data points are needed instead of fully labeled data, which is called SU classification. We show that an unbiased estimator of the classification risk can be obtained only from SU data, and the estimation error of its empirical risk minimizer achieves the optimal parametric convergence rate. Finally, we demonstrate the effectiveness of the proposed method through experiments.
In this paper, we evaluate the accuracy of deep learning approaches on geospatial vector geometry classification tasks. The purpose of this evaluation is to investigate the ability of deep learning models to learn from geometry coordinates directly. Previous machine learning research applied to geospatial polygon data did not use geometries directly, but derived properties thereof. These are produced by way of extracting geometry properties such as Fourier descriptors. Instead, our introduced deep neural net architectures are able to learn on sequences of coordinates mapped directly from polygons. In three classification tasks we show that the deep learning architectures are competitive with common learning algorithms that require extracted features.
Kernel Methods Next Generation (KMNG) introduces a framework to use kernel approximates in the mini-batch setting with SGD Optimizer as an alternative to Deep Learning. McKernel is a C++ library for KMNG ML Large-scale. It contains a CPU optimized implementation of the Fastfood algorithm that allows the computation of approximated kernel expansions in log-linear time. The algorithm requires to compute the product of Walsh Hadamard Transform (WHT) matrices. A cache friendly SIMD Fast Walsh Hadamard Transform (FWHT) that achieves compelling speed and outperforms current state-of-the-art methods has been developed. McKernel allows to obtain non-linear classification combining Fastfood and a linear classifier.
Adaptive gradient methods for stochastic optimization adjust the learning rate for each parameter locally. However, there is also a global learning rate which must be tuned in order to get the best performance. In this paper, we present a new algorithm that adapts the learning rate locally for each parameter separately, and also globally for all parameters together. Specifically, we modify Adam, a popular method for training deep learning models, with a coefficient that captures properties of the objective function. Empirically, we show that our method, which we call Eve, outperforms Adam and other popular methods in training deep neural networks, like convolutional neural networks for image classification, and recurrent neural networks for language tasks.
Dialogue Act (DA) tagging is crucial for spoken language understanding systems, as it provides a general representation of speakers' intents, not bound to a particular dialogue system. Unfortunately, publicly available data sets with DA annotation are all based on different annotation schemes and thus incompatible with each other. Moreover, their schemes often do not cover all aspects necessary for open-domain human-machine interaction. In this paper, we propose a methodology to map several publicly available corpora to a subset of the ISO standard, in order to create a large task-independent training corpus for DA classification. We show the feasibility of using this corpus to train a domain-independent DA tagger testing it on out-of-domain conversational data, and argue the importance of training on multiple corpora to achieve robustness across different DA categories.
Deep Neural Networks have recently gained lots of success after enabling several breakthroughs in notoriously challenging problems. Training these networks is computationally expensive and requires vast amounts of training data. Selling such pre-trained models can, therefore, be a lucrative business model. Unfortunately, once the models are sold they can be easily copied and redistributed. To avoid this, a tracking mechanism to identify models as the intellectual property of a particular vendor is necessary. In this work, we present an approach for watermarking Deep Neural Networks in a black-box way. Our scheme works for general classification tasks and can easily be combined with current learning algorithms. We show experimentally that such a watermark has no noticeable impact on the primary task that the model is designed for and evaluate the robustness of our proposal against a multitude of practical attacks. Moreover, we provide a theoretical analysis, relating our approach to previous work on backdooring.
Attention-based long short-term memory (LSTM) networks have proven to be useful in aspect-level sentiment classification. However, due to the difficulties in annotating aspect-level data, existing public datasets for this task are all relatively small, which largely limits the effectiveness of those neural models. In this paper, we explore two approaches that transfer knowledge from document- level data, which is much less expensive to obtain, to improve the performance of aspect-level sentiment classification. We demonstrate the effectiveness of our approaches on 4 public datasets from SemEval 2014, 2015, and 2016, and we show that attention-based LSTM benefits from document-level knowledge in multiple ways.
In recent years, deep learning algorithms have become increasingly more prominent for their unparalleled ability to automatically learn discriminant features from large amounts of data. However, within the field of electromyography-based gesture recognition, deep learning algorithms are seldom employed as they require an unreasonable amount of effort from a single person, to generate tens of thousands of examples. This work's hypothesis is that general, informative features can be learned from the large amounts of data generated by aggregating the signals of multiple users, thus reducing the recording burden while enhancing gesture recognition. Consequently, this paper proposes applying transfer learning on aggregated data from multiple users, while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets. Two datasets comprised of 19 and 17 able-bodied participants respectively (the first one is employed for pre-training) were recorded for this work, using the Myo Armband. A third Myo Armband dataset was taken from the NinaPro database and is comprised of 10 able-bodied participants. Three different deep learning networks employing three different modalities as input (raw EMG, Spectrograms and Continuous Wavelet Transform (CWT)) are tested on the second and third dataset. The proposed transfer learning scheme is shown to systematically and significantly enhance the performance for all three networks on the two datasets, achieving an offline accuracy of 98.31% for 7 gestures over 17 participants for the CWT-based ConvNet and 68.98% for 18 gestures over 10 participants for the raw EMG-based ConvNet. Finally, a use-case study employing eight able-bodied participants suggests that real-time feedback allows users to adapt their muscle activation strategy which reduces the degradation in accuracy normally experienced over time.
The folding structure of the DNA molecule combined with helper molecules, also referred to as the chromatin, is highly relevant for the functional properties of DNA. The chromatin structure is largely determined by the underlying primary DNA sequence, though the interaction is not yet fully understood. In this paper we develop a convolutional neural network that takes an image-representation of primary DNA sequence as its input, and predicts key determinants of chromatin structure. The method is developed such that it is capable of detecting interactions between distal elements in the DNA sequence, which are known to be highly relevant. Our experiments show that the method outperforms several existing methods both in terms of prediction accuracy and training time.
The 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. To date, there is no in-depth analysis paper to critically discuss FNC-1's experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods. In this paper, we provide such an in-depth analysis for the three top-performing systems. We first find that FNC-1's proposed evaluation metric favors the majority class, which can be easily classified, and thus overestimates the true discriminative power of the methods. Therefore, we propose a new F1-based metric yielding a changed system ranking. Next, we compare the features and architectures used, which leads to a novel feature-rich stacked LSTM model that performs on par with the best systems, but is superior in predicting minority classes. To understand the methods' ability to generalize, we derive a new dataset and perform both in-domain and cross-domain experiments. Our qualitative and quantitative study helps interpreting the original FNC-1 scores and understand which features help improving performance and why. Our new dataset and all source code used during the reproduction study are publicly available for future research.
We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to run in-browser inference, users can remove image features using inpainting algorithms and obtain new classifications in real time, which allows them to ask a variety of "what if" questions by experimentally modifying images and seeing how the model reacts. Our system allows users to compare and contrast what image regions humans and machine learning models use for classification, revealing a wide range of surprising results ranging from spectacular failures (e.g., a "water bottle" image becomes a "concert" when removing a person) to impressive resilience (e.g., a "baseball player" image remains correctly classified even without a glove or base). We demonstrate our system at The 2018 Conference on Computer Vision and Pattern Recognition (CVPR) for the audience to try it live. Our system is open-sourced at https://github.com/poloclub/interactive-classification. A video demo is available at https://youtu.be/llub5GcOF6w.
In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domain-free contexts for sentence classification.
The use of user/product information in sentiment analysis is important, especially for cold-start users/products, whose number of reviews are very limited. However, current models do not deal with the cold-start problem which is typical in review websites. In this paper, we present Hybrid Contextualized Sentiment Classifier (HCSC), which contains two modules: (1) a fast word encoder that returns word vectors embedded with short and long range dependency features; and (2) Cold-Start Aware Attention (CSAA), an attention mechanism that considers the existence of cold-start problem when attentively pooling the encoded word vectors. HCSC introduces shared vectors that are constructed from similar users/products, and are used when the original distinct vectors do not have sufficient information (i.e. cold-start). This is decided by a frequency-guided selective gate vector. Our experiments show that in terms of RMSE, HCSC performs significantly better when compared with on famous datasets, despite having less complexity, and thus can be trained much faster. More importantly, our model performs significantly better than previous models when the training data is sparse and has cold-start problems.
Automated service classification plays a crucial role in service discovery, selection, and composition. Machine learning has been widely used for service classification in recent years. However, the performance of conventional machine learning methods highly depends on the quality of manual feature engineering. In this paper, we present a novel deep neural network to automatically abstract low-level representation of both service name and service description to high-level merged features without feature engineering and the length limitation, and then predict service classification on 50 service categories. To demonstrate the effectiveness of our approach, we conduct a comprehensive experimental study by comparing 10 machine learning methods on 10,000 real-world web services. The result shows that the proposed deep neural network can achieve higher accuracy in classification and more robust than other machine learning methods.
We evaluated various compositional models, from bag-of-words representations to compositional RNN-based models, on several extrinsic supervised and unsupervised evaluation benchmarks. Our results confirm that weighted vector averaging can outperform context-sensitive models in most benchmarks, but structural features encoded in RNN models can also be useful in certain classification tasks. We analyzed some of the evaluation datasets to identify the aspects of meaning they measure and the characteristics of the various models that explain their performance variance.
We propose a random convolutional neural network to generate a feature space in which we study image classification and retrieval performance. Put briefly we apply random convolutional blocks followed by global average pooling to generate a new feature, and we repeat this k times to produce a k-dimensional feature space. This can be interpreted as partitioning the space of image patches with random hyperplanes which we formalize as a random depthwise convolutional neural network. In the network's final layer we perform image classification and retrieval with the linear support vector machine and k-nearest neighbor classifiers and study other empirical properties. We show that the ratio of image pixel distribution similarity across classes to within classes is higher in our network's final layer compared to the input space. When we apply the linear support vector machine for image classification we see that the accuracy is higher than if we were to train just the final layer of VGG16, ResNet18, and DenseNet40 with random weights. In the same setting we compare it to an unsupervised feature learning method and find our accuracy to be comparable on CIFAR10 but higher on CIFAR100 and STL10. We see that the accuracy is not far behind that of trained networks, particularly in the top-k setting. For example the top-2 accuracy of our network is near 90% on both CIFAR10 and a 10-class mini ImageNet, and 85% on STL10. We find that k-nearest neighbor gives a comparable precision on the Corel Princeton Image Similarity Benchmark than if we were to use the final layer of trained networks. As with other networks we find that our network fails to a black box attack even though we lack a gradient and use the sign activation. We highlight sensitivity of our network to background as a potential pitfall and an advantage. Overall our work pushes the boundary of what can be achieved with random weights.
Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations between labels. Besides, different parts of the text can contribute differently for predicting different labels, which is not considered by existing models. In this paper, we propose to view the multi-label classification task as a sequence generation problem, and apply a sequence generation model with a novel decoder structure to solve it. Extensive experimental results show that our proposed methods outperform previous work by a substantial margin. Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.
Binary classification is one of the most common problem in machine learning. It consists in predicting whether a given element belongs to a particular class. In this paper, a new algorithm for binary classification is proposed using a hypergraph representation. The method is agnostic to data representation, can work with multiple data sources or in non-metric spaces, and accommodates with missing values. As a result, it drastically reduces the need for data preprocessing or feature engineering. Each element to be classified is partitioned according to its interactions with the training set. For each class, a seminorm over the training set partition is learnt to represent the distribution of evidence supporting this class. Empirical validation demonstrates its high potential on a wide range of well-known datasets and the results are compared to the state-of-the-art. The time complexity is given and empirically validated. Its robustness with regard to hyperparameter sensitivity is studied and compared to standard classification methods. Finally, the limitation of the model space is discussed, and some potential solutions proposed.
Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to large label sets and generalize to unseen ones. Existing joint input-label text models overcome these issues by exploiting label descriptions, but they are unable to capture complex label relationships, have rigid parametrization, and their gains on unseen labels happen often at the expense of weak performance on the labels seen during training. In this paper, we propose a new input-label model which generalizes over previous such models, addresses their limitations and does not compromise performance on seen labels. The model consists of a joint non-linear input-label embedding with controllable capacity and a joint-space-dependent classification unit which is trained with cross-entropy loss to optimize classification performance. We evaluate models on full-resource and low- or zero-resource text classification of multilingual news and biomedical text with a large label set. Our model outperforms monolingual and multilingual models which do not leverage label semantics and previous joint input-label space models in both scenarios.
Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. We propose a novel visual-assisted diagnosis hybrid model based on the support vector machine (SVM) and deep neural networks (DNNs). The model incorporates complementary strengths of DNNs and SVM. Furthermore, we present a new clinical retina label collection for ophthalmology incorporating 32 retina diseases classes. Using EyeNet, our model achieves 89.73% diagnosis accuracy and the model performance is comparable to the professional ophthalmologists.