The phenomenon of Gravitational Wave (GW) analysis has grown in popularity as technology has advanced and the process of observing gravitational waves has become more precise. Although the sensitivity and the frequency of observation of GW signals are constantly improving, the possibility of noise in the collected GW data remains. In this paper, we propose two new Machine and Deep learning ensemble approaches (i.e., ShallowWaves and DeepWaves Ensembles) for detecting different types of noise and patterns in datasets from GW observatories. Our research also investigates various Machine and Deep Learning techniques for multi-class classification and provides a comprehensive benchmark, emphasizing the best results in terms of three commonly used performance metrics (i.e., accuracy, precision, and recall). We train and test our models on a dataset consisting of annotated time series from real-world data collected by the Advanced Laser Interferometer GW Observatory (LIGO). We empirically show that the best overall accuracy is obtained by the proposed DeepWaves Ensemble, followed close by the ShallowWaves Ensemble.
Domain generalization asks for models trained over a set of training environments to generalize well in unseen test environments. Recently, a series of algorithms such as Invariant Risk Minimization (IRM) have been proposed for domain generalization. However, Rosenfeld et al. (2021) shows that in a simple linear data model, even if non-convexity issues are ignored, IRM and its extensions cannot generalize to unseen environments with less than $d_s+1$ training environments, where $d_s$ is the dimension of the spurious-feature subspace. In this work, we propose Invariant-feature Subspace Recovery (ISR): a new class of algorithms to achieve provable domain generalization across the settings of classification and regression problems. First, in the binary classification setup of Rosenfeld et al. (2021), we show that our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments. Our second algorithm, ISR-Cov, further reduces the required number of training environments to $O(1)$ using the information of second-order moments. Notably, unlike IRM, our algorithms bypass non-convexity issues and enjoy global convergence guarantees. Next, we extend ISR-Mean to the more general setting of multi-class classification and propose ISR-Multiclass, which leverages class information and provably recovers the invariant-feature subspace with $\lceil d_s/k\rceil+1$ training environments for $k$-class classification. Finally, for regression problems, we propose ISR-Regression that can identify the invariant-feature subspace with $d_s+1$ training environments. Empirically, we demonstrate the superior performance of our ISRs on synthetic benchmarks. Further, ISR can be used as post-processing methods for feature extractors such as neural nets.
Hierarchical classification (HC) plays a pivotal role in multi-class classification tasks, where objects are organized into a hierarchical structure. This study explores the performance of HC through a comprehensive analysis that encompasses both hierarchy generation and hierarchy exploitation. This analysis is particularly relevant in scenarios where a predefined hierarchy structure is not readily accessible. Notably, two novel hierarchy exploitation schemes, LCPN+ and LCPN+F, which extend the capabilities of LCPN and combine the strengths of global and local classification, have been introduced and evaluated alongside existing methods. The findings reveal the consistent superiority of LCPN+F, which outperforms other schemes across various datasets and scenarios. Moreover, this research emphasizes not only effectiveness but also efficiency, as LCPN+ and LCPN+F maintain runtime performance comparable to Flat Classification (FC). Additionally, this study underscores the importance of selecting the right hierarchy exploitation scheme to maximize classification performance. This work extends our understanding of HC and establishes a benchmark for future research, fostering advancements in multi-class classification methodologies.
Transformer-based models, specifically BERT, have propelled research in various NLP tasks. However, these models are limited to a maximum token limit of 512 tokens. Consequently, this makes it non-trivial to apply it in a practical setting with long input. Various complex methods have claimed to overcome this limit, but recent research questions the efficacy of these models across different classification tasks. These complex architectures evaluated on carefully curated long datasets perform at par or worse than simple baselines. In this work, we propose a relatively simple extension to vanilla BERT architecture called ChunkBERT that allows finetuning of any pretrained models to perform inference on arbitrarily long text. The proposed method is based on chunking token representations and CNN layers, making it compatible with any pre-trained BERT. We evaluate chunkBERT exclusively on a benchmark for comparing long-text classification models across a variety of tasks (including binary classification, multi-class classification, and multi-label classification). A BERT model finetuned using the ChunkBERT method performs consistently across long samples in the benchmark while utilizing only a fraction (6.25\%) of the original memory footprint. These findings suggest that efficient finetuning and inference can be achieved through simple modifications to pre-trained BERT models.
Support vector machine (SVM) is one of the most studied paradigms in the realm of machine learning for classification and regression problems. It relies on vectorized input data. However, a significant portion of the real-world data exists in matrix format, which is given as input to SVM by reshaping the matrices into vectors. The process of reshaping disrupts the spatial correlations inherent in the matrix data. Also, converting matrices into vectors results in input data with a high dimensionality, which introduces significant computational complexity. To overcome these issues in classifying matrix input data, support matrix machine (SMM) is proposed. It represents one of the emerging methodologies tailored for handling matrix input data. The SMM method preserves the structural information of the matrix data by using the spectral elastic net property which is a combination of the nuclear norm and Frobenius norm. This article provides the first in-depth analysis of the development of the SMM model, which can be used as a thorough summary by both novices and experts. We discuss numerous SMM variants, such as robust, sparse, class imbalance, and multi-class classification models. We also analyze the applications of the SMM model and conclude the article by outlining potential future research avenues and possibilities that may motivate academics to advance the SMM algorithm.
We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a prevalent NC phenomenon comprising of the following properties for the last-layer features: (i) the variability of features within every class collapses to zero, (ii) the set of feature means form an equi-angular tight frame (ETF), and (iii) the last layer classifiers collapse to the feature mean upon some scaling. We generalize the study to multi-label learning, and prove for the first time that a generalized NC phenomenon holds with the "pick-all-label" formulation, which we term as MLab NC. While the ETF geometry remains consistent for features with a single label, multi-label scenarios introduce a unique combinatorial aspect we term the "tag-wise average" property, where the means of features with multiple labels are the scaled averages of means for single-label instances. Theoretically, under proper assumptions on the features, we establish that the only global optimizer of the pick-all-label cross-entropy loss satisfy the multi-label NC. In practice, we demonstrate that our findings can lead to better test performance with more efficient training techniques for MLab learning.
We study the key framework of learning with abstention in the multi-class classification setting. In this setting, the learner can choose to abstain from making a prediction with some pre-defined cost. We present a series of new theoretical and algorithmic results for this learning problem in the predictor-rejector framework. We introduce several new families of surrogate losses for which we prove strong non-asymptotic and hypothesis set-specific consistency guarantees, thereby resolving positively two existing open questions. These guarantees provide upper bounds on the estimation error of the abstention loss function in terms of that of the surrogate loss. We analyze both a single-stage setting where the predictor and rejector are learned simultaneously and a two-stage setting crucial in applications, where the predictor is learned in a first stage using a standard surrogate loss such as cross-entropy. These guarantees suggest new multi-class abstention algorithms based on minimizing these surrogate losses. We also report the results of extensive experiments comparing these algorithms to the current state-of-the-art algorithms on CIFAR-10, CIFAR-100 and SVHN datasets. Our results demonstrate empirically the benefit of our new surrogate losses and show the remarkable performance of our broadly applicable two-stage abstention algorithm.
Learning with abstention is a key scenario where the learner can abstain from making a prediction at some cost. In this paper, we analyze the score-based formulation of learning with abstention in the multi-class classification setting. We introduce new families of surrogate losses for the abstention loss function, which include the state-of-the-art surrogate losses in the single-stage setting and a novel family of loss functions in the two-stage setting. We prove strong non-asymptotic and hypothesis set-specific consistency guarantees for these surrogate losses, which upper-bound the estimation error of the abstention loss function in terms of the estimation error of the surrogate loss. Our bounds can help compare different score-based surrogates and guide the design of novel abstention algorithms by minimizing the proposed surrogate losses. We experimentally evaluate our new algorithms on CIFAR-10, CIFAR-100, and SVHN datasets and the practical significance of our new surrogate losses and two-stage abstention algorithms. Our results also show that the relative performance of the state-of-the-art score-based surrogate losses can vary across datasets.
Since its introduction in 2019, the whole end-to-end neural diarization (EEND) line of work has been addressing speaker diarization as a frame-wise multi-label classification problem with permutation-invariant training. Despite EEND showing great promise, a few recent works took a step back and studied the possible combination of (local) supervised EEND diarization with (global) unsupervised clustering. Yet, these hybrid contributions did not question the original multi-label formulation. We propose to switch from multi-label (where any two speakers can be active at the same time) to powerset multi-class classification (where dedicated classes are assigned to pairs of overlapping speakers). Through extensive experiments on 9 different benchmarks, we show that this formulation leads to significantly better performance (mostly on overlapping speech) and robustness to domain mismatch, while eliminating the detection threshold hyperparameter, critical for the multi-label formulation.
The effectiveness of network intrusion detection systems, predominantly based on machine learning, are highly influenced by the dataset they are trained on. Ensuring an accurate reflection of the multifaceted nature of benign and malicious traffic in these datasets is essential for creating models capable of recognizing and responding to a wide array of intrusion patterns. However, existing datasets often fall short, lacking the necessary diversity and alignment with the contemporary network environment, thereby limiting the effectiveness of intrusion detection. This paper introduces TII-SSRC-23, a novel and comprehensive dataset designed to overcome these challenges. Comprising a diverse range of traffic types and subtypes, our dataset is a robust and versatile tool for the research community. Additionally, we conduct a feature importance analysis, providing vital insights into critical features for intrusion detection tasks. Through extensive experimentation, we also establish firm baselines for supervised and unsupervised intrusion detection methodologies using our dataset, further contributing to the advancement and adaptability of intrusion detection models in the rapidly changing landscape of network security. Our dataset is available at https://kaggle.com/datasets/daniaherzalla/tii-ssrc-23.
Weak supervision has emerged as a promising approach for rapid and large-scale dataset creation in response to the increasing demand for accelerated NLP development. By leveraging labeling functions, weak supervision allows practitioners to generate datasets quickly by creating learned label models that produce soft-labeled datasets. This paper aims to show how such an approach can be utilized to build an Indonesian NLP dataset from conservation news text. We construct two types of datasets: multi-class classification and sentiment classification. We then provide baseline experiments using various pretrained language models. These baseline results demonstrate test performances of 59.79% accuracy and 55.72% F1-score for sentiment classification, 66.87% F1-score-macro, 71.5% F1-score-micro, and 83.67% ROC-AUC for multi-class classification. Additionally, we release the datasets and labeling functions used in this work for further research and exploration.
Sigmoid output layers are widely used in multi-label classification (MLC) tasks, in which multiple labels can be assigned to any input. In many practical MLC tasks, the number of possible labels is in the thousands, often exceeding the number of input features and resulting in a low-rank output layer. In multi-class classification, it is known that such a low-rank output layer is a bottleneck that can result in unargmaxable classes: classes which cannot be predicted for any input. In this paper, we show that for MLC tasks, the analogous sigmoid bottleneck results in exponentially many unargmaxable label combinations. We explain how to detect these unargmaxable outputs and demonstrate their presence in three widely used MLC datasets. We then show that they can be prevented in practice by introducing a Discrete Fourier Transform (DFT) output layer, which guarantees that all sparse label combinations with up to $k$ active labels are argmaxable. Our DFT layer trains faster and is more parameter efficient, matching the F1@k score of a sigmoid layer while using up to 50% fewer trainable parameters. Our code is publicly available at https://github.com/andreasgrv/sigmoid-bottleneck.
Given an image and an associated textual question, the purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of external knowledge bases. Prior KB-VQA models are usually formulated as a retriever-classifier framework, where a pre-trained retriever extracts textual or visual information from knowledge graphs and then makes a prediction among the candidates. Despite promising progress, there are two drawbacks with existing models. Firstly, modeling question-answering as multi-class classification limits the answer space to a preset corpus and lacks the ability of flexible reasoning. Secondly, the classifier merely consider "what is the answer" without "how to get the answer", which cannot ground the answer to explicit reasoning paths. In this paper, we confront the challenge of \emph{explainable open-set} KB-VQA, where the system is required to answer questions with entities at wild and retain an explainable reasoning path. To resolve the aforementioned issues, we propose a new retriever-ranker paradigm of KB-VQA, Graph pATH rankER (GATHER for brevity). Specifically, it contains graph constructing, pruning, and path-level ranking, which not only retrieves accurate answers but also provides inference paths that explain the reasoning process. To comprehensively evaluate our model, we reformulate the benchmark dataset OK-VQA with manually corrected entity-level annotations and release it as ConceptVQA. Extensive experiments on real-world questions demonstrate that our framework is not only able to perform open-set question answering across the whole knowledge base but provide explicit reasoning path.
Machine learning methods usually rely on large sample size to have good performance, while it is difficult to provide labeled set in many applications. Pool-based active learning methods are there to detect, among a set of unlabeled data, the ones that are the most relevant for the training. We propose in this paper a meta-approach for pool-based active learning strategies in the context of multi-class classification tasks based on Proper Topological Regions. PTR, based on topological data analysis (TDA), are relevant regions used to sample cold-start points or within the active learning scheme. The proposed method is illustrated empirically on various benchmark datasets, being competitive to the classical methods from the literature.
Quantum computers can theoretically have significant acceleration over classical computers; but, the near-future era of quantum computing is limited due to small number of qubits that are also error prone. Quilt is a framework for performing multi-class classification task designed to work effectively on current error-prone quantum computers. Quilt is evaluated with real quantum machines as well as with projected noise levels as quantum machines become more noise-free. Quilt demonstrates up to 85% multi-class classification accuracy with the MNIST dataset on a five-qubit system.
Saliency maps have become one of the most widely used interpretability techniques for convolutional neural networks (CNN) due to their simplicity and the quality of the insights they provide. However, there are still some doubts about whether these insights are a trustworthy representation of what CNNs use to come up with their predictions. This paper explores how rescuing the sign of the gradients from the saliency map can lead to a deeper understanding of multi-class classification problems. Using both pretrained and trained from scratch CNNs we unveil that considering the sign and the effect not only of the correct class, but also the influence of the other classes, allows to better identify the pixels of the image that the network is really focusing on. Furthermore, how occluding or altering those pixels is expected to affect the outcome also becomes clearer.
Amyotrophic Lateral Sclerosis (ALS) and Myopathy present considerable challenges in the realm of neuromuscular disorder diagnostics. In this study, we employ advanced deep-learning techniques to address the detection of ALS and Myopathy, two debilitating conditions. Our methodology begins with the extraction of informative features from raw electromyography (EMG) signals, leveraging the Log-spectrum, and Delta Log spectrum, which capture the frequency contents, and spectral and temporal characteristics of the signals. Subsequently, we applied a deep-learning model, SpectroEMG-Net, combined with Convolutional Neural Networks (CNNs) and Attention for the classification of three classes. The robustness of our approach is rigorously evaluated, demonstrating its remarkable performance in distinguishing among the classes: Myopathy, Normal, and ALS, with an outstanding overall accuracy of 92\%. This study marks a contribution to addressing the diagnostic challenges posed by neuromuscular disorders through a data-driven, multi-class classification approach, providing valuable insights into the potential for early and accurate detection.
In this paper, we present a novel method to automatically classify medical images that learns and leverages weak causal signals in the image. Our framework consists of a convolutional neural network backbone and a causality-extractor module that extracts cause-effect relationships between feature maps that can inform the model on the appearance of a feature in one place of the image, given the presence of another feature within some other place of the image. To evaluate the effectiveness of our approach in low-data scenarios, we train our causality-driven architecture in a One-shot learning scheme, where we propose a new meta-learning procedure entailing meta-training and meta-testing tasks that are designed using related classes but at different levels of granularity. We conduct binary and multi-class classification experiments on a publicly available dataset of prostate MRI images. To validate the effectiveness of the proposed causality-driven module, we perform an ablation study and conduct qualitative assessments using class activation maps to highlight regions strongly influencing the network's decision-making process. Our findings show that causal relationships among features play a crucial role in enhancing the model's ability to discern relevant information and yielding more reliable and interpretable predictions. This would make it a promising approach for medical image classification tasks.
Majority voting is a simple mathematical function that returns the value that appears most often in a set. As a popular decision fusion technique, the majority voting function (MVF) finds applications in resolving conflicts, where a number of independent voters report their opinions on a classification problem. Despite its importance and its various applications in ensemble learning, data crowd-sourcing, remote sensing, and data oracles for blockchains, the accuracy of the MVF for the general multi-class classification problem has remained unknown. In this paper, we derive a new upper bound on the accuracy of the MVF for the multi-class classification problem. More specifically, we show that under certain conditions, the error rate of the MVF exponentially decays toward zero as the number of independent voters increases. Conversely, the error rate of the MVF exponentially grows with the number of independent voters if these conditions are not met. We first explore the problem for independent and identically distributed voters where we assume that every voter follows the same conditional probability distribution of voting for different classes, given the true classification of the data point. Next, we extend our results for the case where the voters are independent but non-identically distributed. Using the derived results, we then provide a discussion on the accuracy of the truth discovery algorithms. We show that in the best-case scenarios, truth discovery algorithms operate as an amplified MVF and thereby achieve a small error rate only when the MVF achieves a small error rate, and vice versa, achieve a large error rate when the MVF also achieves a large error rate. In the worst-case scenario, the truth discovery algorithms may achieve a higher error rate than the MVF. Finally, we confirm our theoretical results using numerical simulations.
Artificial neural networks (ANNs), inspired by the interconnection of real neurons, have achieved unprecedented success in various fields such as computer vision and natural language processing. Recently, a novel mathematical ANN model, known as the dendritic neuron model (DNM), has been proposed to address nonlinear problems by more accurately reflecting the structure of real neurons. However, the single-output design limits its capability to handle multi-output tasks, significantly lowering its applications. In this paper, we propose a novel multi-in and multi-out dendritic neuron model (MODN) to tackle multi-output tasks. Our core idea is to introduce a filtering matrix to the soma layer to adaptively select the desired dendrites to regress each output. Because such a matrix is designed to be learnable, MODN can explore the relationship between each dendrite and output to provide a better solution to downstream tasks. We also model a telodendron layer into MODN to simulate better the real neuron behavior. Importantly, MODN is a more general and unified framework that can be naturally specialized as the DNM by customizing the filtering matrix. To explore the optimization of MODN, we investigate both heuristic and gradient-based optimizers and introduce a 2-step training method for MODN. Extensive experimental results performed on 11 datasets on both binary and multi-class classification tasks demonstrate the effectiveness of MODN, with respect to accuracy, convergence, and generality.