Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision and Natural Language Processing. In the latter, such models used to rely on fixed word embeddings before the advent of transformers. Additionally, some models used in Computer Vision are yet to be tested in NLP applications. In this paper, we compare all these models, first adapting those made in the field of image processing to NLP, and second providing them access to transformers. We then test these models equipped with the same transformer-based encoder on the intent detection task, known for having a large number of classes. Our results reveal that while methods perform almost equally on the ARSC dataset, this is not the case for the Intent Detection task, where the most recent and supposedly best competitors perform worse than older and simpler ones (while all are given access to transformers). We also show that a simple baseline is surprisingly strong. All the new developed models, as well as the evaluation framework, are made publicly available.
Deep neural networks (DNNs) used for brain-computer-interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts. While some success is found in such an approach, we suggest that this interpretation is limited and an alternative would better leverage the newly (publicly) available massive EEG datasets. We consider how to adapt techniques and architectures used for language modelling (LM), that appear capable of ingesting awesome amounts of data, towards the development of encephalography modelling (EM) with DNNs in the same vein. We specifically adapt an approach effectively used for automatic speech recognition, which similarly (to LMs) uses a self-supervised training objective to learn compressed representations of raw data signals. After adaptation to EEG, we find that a single pre-trained model is capable of modelling completely novel raw EEG sequences recorded with differing hardware, and different subjects performing different tasks. Furthermore, both the internal representations of this model and the entire architecture can be fine-tuned to a variety of downstream BCI and EEG classification tasks, outperforming prior work in more task-specific (sleep stage classification) self-supervision.
The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint training when limited target-language data is available during training. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability and show that meta-learning thrives in settings with a heterogeneous task distribution. We propose a simple, yet effective adjustment to existing meta-learning methods which allows for better and more stable learning, and set a new state of the art on several languages while performing on-par on others, using only a small amount of labeled data.
Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of text classification with label noise, and aim to capture this noise through an auxiliary noise model over the classifier. We first assign a probability score to each training sample of having a noisy label, through a beta mixture model fitted on the losses at an early epoch of training. Then, we use this score to selectively guide the learning of the noise model and classifier. Our empirical evaluation on two text classification tasks shows that our approach can improve over the baseline accuracy, and prevent over-fitting to the noise.
We introduce tf_geometric, an efficient and friendly library for graph deep learning, which is compatible with both TensorFlow 1.x and 2.x. tf_geometric provides kernel libraries for building Graph Neural Networks (GNNs) as well as implementations of popular GNNs. The kernel libraries consist of infrastructures for building efficient GNNs, including graph data structures, graph map-reduce framework, graph mini-batch strategy, etc. These infrastructures enable tf_geometric to support single-graph computation, multi-graph computation, graph mini-batch, distributed training, etc.; therefore, tf_geometric can be used for a variety of graph deep learning tasks, such as transductive node classification, inductive node classification, link prediction, and graph classification. Based on the kernel libraries, tf_geometric implements a variety of popular GNN models for different tasks. To facilitate the implementation of GNNs, tf_geometric also provides some other libraries for dataset management, graph sampling, etc. Different from existing popular GNN libraries, tf_geometric provides not only Object-Oriented Programming (OOP) APIs, but also Functional APIs, which enable tf_geometric to handle advanced graph deep learning tasks such as graph meta-learning. The APIs of tf_geometric are friendly, and they are suitable for both beginners and experts. In this paper, we first present an overview of tf_geometric's framework. Then, we conduct experiments on some benchmark datasets and report the performance of several popular GNN models implemented by tf_geometric.
Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation. We, therefore, propose a generative approach based on a variant of Latent Dirichlet Allocation to analyse task similarity to optimise and better understand the performance of meta-learning. We demonstrate that the proposed method can provide an insightful evaluation for meta-learning algorithms on two few-shot classification benchmarks that matches common intuition: the more similar the higher performance. Based on this similarity measure, we propose a task-selection strategy for meta-learning and show that it can produce more accurate classification results than methods that randomly select training tasks.
Congenital heart disease (CHD) is the most common type of birth defect, which occurs 1 in every 110 births in the United States. CHD usually comes with severe variations in heart structure and great artery connections that can be classified into many types. Thus highly specialized domain knowledge and the time-consuming human process is needed to analyze the associated medical images. On the other hand, due to the complexity of CHD and the lack of dataset, little has been explored on the automatic diagnosis (classification) of CHDs. In this paper, we present ImageCHD, the first medical image dataset for CHD classification. ImageCHD contains 110 3D Computed Tomography (CT) images covering most types of CHD, which is of decent size Classification of CHDs requires the identification of large structural changes without any local tissue changes, with limited data. It is an example of a larger class of problems that are quite difficult for current machine-learning-based vision methods to solve. To demonstrate this, we further present a baseline framework for the automatic classification of CHD, based on a state-of-the-art CHD segmentation method. Experimental results show that the baseline framework can only achieve a classification accuracy of 82.0\% under a selective prediction scheme with 88.4\% coverage, leaving big room for further improvement. We hope that ImageCHD can stimulate further research and lead to innovative and generic solutions that would have an impact in multiple domains. Our dataset is released to the public compared with existing medical imaging datasets.
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the combination of both could potentially be effective for tackling task-specific labelled data shortage. To bridge this gap, we combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task. Compared to strong supervised learning baselines, our semi-supervised classification framework is highly competitive and outperforms the state-of-the-art counterparts in low-resource settings across several languages.
We propose a novel method to detect and visualize malware through image classification. The executable binaries are represented as grayscale images obtained from the count of N-grams (N=2) of bytes in the Discrete Cosine Transform (DCT) domain and a neural network is trained for malware detection. A shallow neural network is trained for classification, and its accuracy is compared with deep-network architectures such as ResNet that are trained using transfer learning. Neither dis-assembly nor behavioral analysis of malware is required for these methods. Motivated by the visual similarity of these images for different malware families, we compare our deep neural network models with standard image features like GIST descriptors to evaluate the performance. A joint feature measure is proposed to combine different features using error analysis to get an accurate ensemble model for improved classification performance. A new dataset called MaleX which contains around 1 million malware and benign Windows executable samples is created for large-scale malware detection and classification experiments. Experimental results are quite promising with 96% binary classification accuracy on MaleX. The proposed model is also able to generalize well on larger unseen malware samples and the results compare favorably with state-of-the-art static analysis-based malware detection algorithms.
Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain incremental). One of the key challenges of continual learning is to avoid catastrophic forgetting (CF), i.e., forgetting old tasks in the presence of more recent tasks. Over the past few years, many methods and tricks have been introduced to address this problem, but many have not been fairly and systematically compared under a variety of realistic and practical settings. To better understand the relative advantages of various approaches and the settings where they work best, this survey aims to (1) compare state-of-the-art methods such as MIR, iCARL, and GDumb and determine which works best at different experimental settings; (2) determine if the best class incremental methods are also competitive in domain incremental setting; (3) evaluate the performance of 7 simple but effective trick such as "review" trick and nearest class mean (NCM) classifier to assess their relative impact. Regarding (1), we observe iCaRL remains competitive when the memory buffer is small; GDumb outperforms many recently proposed methods in medium-size datasets and MIR performs the best in larger-scale datasets. For (2), we note that GDumb performs quite poorly while MIR -- already competitive for (1) -- is also strongly competitive in this very different but important setting. Overall, this allows us to conclude that MIR is overall a strong and versatile method across a wide variety of settings. For (3), we find that all 7 tricks are beneficial, and when augmented with the "review" trick and NCM classifier, MIR produces performance levels that bring online continual learning much closer to its ultimate goal of matching offline training.
Detecting arguments in online interactions is useful to understand how conflicts arise and get resolved. Users often use figurative language, such as sarcasm, either as persuasive devices or to attack the opponent by an ad hominem argument. To further our understanding of the role of sarcasm in shaping the disagreement space, we present a thorough experimental setup using a corpus annotated with both argumentative moves (agree/disagree) and sarcasm. We exploit joint modeling in terms of (a) applying discrete features that are useful in detecting sarcasm to the task of argumentative relation classification (agree/disagree/none), and (b) multitask learning for argumentative relation classification and sarcasm detection using deep learning architectures (e.g., dual Long Short-Term Memory (LSTM) with hierarchical attention and Transformer-based architectures). We demonstrate that modeling sarcasm improves the argumentative relation classification task (agree/disagree/none) in all setups.
Convolutional Neural Networks (CNN) has been extensively studied for Hyperspectral Image Classification (HSIC) more specifically, 2D and 3D CNN models have proved highly efficient in exploiting the spatial and spectral information of Hyperspectral Images. However, 2D CNN only considers the spatial information and ignores the spectral information whereas 3D CNN jointly exploits spatial-spectral information at a high computational cost. Therefore, this work proposed a lightweight CNN (3D followed by 2D-CNN) model which significantly reduces the computational cost by distributing spatial-spectral feature extraction across a lighter model alongside a preprocessing that has been carried out to improve the classification results. Five benchmark Hyperspectral datasets (i.e., SalinasA, Salinas, Indian Pines, Pavia University, Pavia Center, and Botswana) are used for experimental evaluation. The experimental results show that the proposed pipeline outperformed in terms of generalization performance, statistical significance, and computational complexity, as compared to the state-of-the-art 2D/3D CNN models except commonly used computationally expensive design choices.
When students write programs, their program structure provides insight into their learning process. However, analyzing program structure by hand is time-consuming, and teachers need better tools for computer-assisted exploration of student solutions. As a first step towards an education-oriented program analysis toolkit, we show how supervised machine learning methods can automatically classify student programs into a predetermined set of high-level structures. We evaluate two models on classifying student solutions to the Rainfall problem: a nearest-neighbors classifier using syntax tree edit distance and a recurrent neural network. We demonstrate that these models can achieve 91% classification accuracy when trained on 108 programs. We further explore the generality, trade-offs, and failure cases of each model.
Multi-label text classification (MLTC) aims to annotate documents with the most relevant labels from a number of candidate labels. In real applications, the distribution of label frequency often exhibits a long tail, i.e., a few labels are associated with a large number of documents (a.k.a. head labels), while a large fraction of labels are associated with a small number of documents (a.k.a. tail labels). To address the challenge of insufficient training data on tail label classification, we propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to data-poor tail labels. The meta-knowledge is the mapping from few-shot network parameters to many-shot network parameters, which aims to promote the generalizability of tail classifiers. Extensive experimental results on three benchmark datasets demonstrate that HTTN consistently outperforms the state-of-the-art methods. The code and hyper-parameter settings are released for reproducibility
Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, and secure communications. Consequently, it will become a key enabler with the emerging fifth-generation (5G) and beyond 5G communications, Internet of Things networks, among others. State-of-the-art studies in wireless signal recognition have only focused on a single task which in many cases is insufficient information for a system to act on. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks in conjunction with multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. Additionally, we consider the problem of heterogeneous wireless signals such as radar and communication signals in the electromagnetic spectrum. Accordingly, we have shown how the proposed MTL model outperforms several state-of-the-art single-task learning classifiers while maintaining a lighter architecture and performing two signal characterization tasks simultaneously. Finally, we also release the only known open heterogeneous wireless signals dataset that comprises of radar and communication signals with multiple labels.
Emotion recognition (ER) is an important task in Natural Language Processing (NLP), due to its high impact in real-world applications from health and well-being to author profiling, consumer analysis and security. Current approaches to ER, mainly classify emotions independently without considering that emotions can co-exist. Such approaches overlook potential ambiguities, in which multiple emotions overlap. We propose a new model "SpanEmo" casting multi-label emotion classification as span-prediction, which can aid ER models to learn associations between labels and words in a sentence. Furthermore, we introduce a loss function focused on modelling multiple co-existing emotions in the input sentence. Experiments performed on the SemEval2018 multi-label emotion data over three language sets (i.e., English, Arabic and Spanish) demonstrate our method's effectiveness. Finally, we present different analyses that illustrate the benefits of our method in terms of improving the model performance and learning meaningful associations between emotion classes and words in the sentence.
Histopathological characterization of colorectal polyps allows to tailor patients' management and follow up with the ultimate aim of avoiding or promptly detecting an invasive carcinoma. Colorectal polyps characterization relies on the histological analysis of tissue samples to determine the polyps malignancy and dysplasia grade. Deep neural networks achieve outstanding accuracy in medical patterns recognition, however they require large sets of annotated training images. We introduce UniToPatho, an annotated dataset of 9536 hematoxylin and eosin (H&E) stained patches extracted from 292 whole-slide images, meant for training deep neural networks for colorectal polyps classification and adenomas grading. We present our dataset and provide insights on how to tackle the problem of automatic colorectal polyps characterization.
Several methods have been explored for automating parts of Systematic Mapping (SM) and Systematic Review (SR) methodologies. Challenges typically evolve around the gaps in semantic understanding of text, as well as lack of domain and background knowledge necessary to bridge that gap. In this paper we investigate possible ways of automating parts of the SM/SR process, i.e. that of extracting keywords and key-phrases from scientific documents using unsupervised methods, which are then used as a basis to construct the corresponding Classification Scheme using semantic key-phrase clustering techniques. Specifically, we explore the effect of ensemble scores measure in key-phrase extraction, we explore semantic network based word embedding in embedding representation of phrase semantics and finally we also explore how clustering can be used to group related key-phrases. The evaluation is conducted on a dataset of publications pertaining the domain of "Explainable AI" which we constructed using standard publicly available digital libraries and sets of indexing terms (keywords). Results shows that: ensemble ranking score does improve the key-phrase extraction performance. Semantic-network based word embedding based on the ConceptNet Semantic Network has similar performance with contextualized word embedding, however the former are computationally more efficient. Finally Semantic key-phrase clustering at term-level can group similar terms together that can be suitable for classification scheme.
Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental limitations of handmade representations. In this work we show that we can train a single learnable frontend that outperforms mel-filterbanks on a wide range of audio signals, including speech, music, audio events and animal sounds, providing a general-purpose learned frontend for audio classification. To do so, we introduce a new principled, lightweight, fully learnable architecture that can be used as a drop-in replacement of mel-filterbanks. Our system learns all operations of audio features extraction, from filtering to pooling, compression and normalization, and can be integrated into any neural network at a negligible parameter cost. We perform multi-task training on eight diverse audio classification tasks, and show consistent improvements of our model over mel-filterbanks and previous learnable alternatives. Moreover, our system outperforms the current state-of-the-art learnable frontend on Audioset, with orders of magnitude fewer parameters.
An Orthogonal Least Squares (OLS) based feature selection method is proposed for both binomial and multinomial classification. The novel Squared Orthogonal Correlation Coefficient (SOCC) is defined based on Error Reduction Ratio (ERR) in OLS and used as the feature ranking criterion. The equivalence between the canonical correlation coefficient, Fisher's criterion, and the sum of the SOCCs is revealed, which unveils the statistical implication of ERR in OLS for the first time. It is also shown that the OLS based feature selection method has speed advantages when applied for greedy search. The proposed method is comprehensively compared with the mutual information based feature selection methods and the embedded methods using both synthetic and real world datasets. The results show that the proposed method is always in the top 5 among the 12 candidate methods. Besides, the proposed method can be directly applied to continuous features without discretisation, which is another significant advantage over mutual information based methods.