When training overparameterized deep networks for classification tasks, it has been widely observed that the learned features exhibit a so-called "neural collapse" phenomenon. More specifically, for the output features of the penultimate layer, for each class the within-class features converge to their means, and the means of different classes exhibit a certain tight frame structure, which is also aligned with the last layer's classifier. As feature normalization in the last layer becomes a common practice in modern representation learning, in this work we theoretically justify the neural collapse phenomenon for normalized features. Based on an unconstrained feature model, we simplify the empirical loss function in a multi-class classification task into a nonconvex optimization problem over the Riemannian manifold by constraining all features and classifiers over the sphere. In this context, we analyze the nonconvex landscape of the Riemannian optimization problem over the product of spheres, showing a benign global landscape in the sense that the only global minimizers are the neural collapse solutions while all other critical points are strict saddles with negative curvature. Experimental results on practical deep networks corroborate our theory and demonstrate that better representations can be learned faster via feature normalization.
The Natarajan dimension is a fundamental tool for characterizing multi-class PAC learnability, generalizing the Vapnik-Chervonenkis (VC) dimension from binary to multi-class classification problems. This work establishes upper bounds on Natarajan dimensions for certain function classes, including (i) multi-class decision tree and random forests, and (ii) multi-class neural networks with binary, linear and ReLU activations. These results may be relevant for describing the performance of certain multi-class learning algorithms.
There is a considerable demand to apply classification in medical analysis. A traditional classifier requires training samples from each class. However, in reality, it is possible that the testing set may include courses that are not in the training set. This inevitably causes an issue: data from an undefined class will be assigned to predefined classes. To tackle this, we propose a semi-supervised variational Gaussian mixture model to perform multi-class classification with novelty detection. Compared to some popular novelty detection methods, we demonstrate that it gets better performance on thyroid disease data, by generating the distribution of predefined classes and undefined classes, without explicitly setting a threshold.
Interactive Machine Learning (IML) shall enable intelligent systems to interactively learn from their end-users, and is quickly becoming more and more important. Although it puts the human in the loop, interactions are mostly performed via mutual explanations that miss contextual information. Furthermore, current model-agnostic IML strategies like CAIPI are limited to 'destructive' feedback, meaning they solely allow an expert to prevent a learner from using irrelevant features. In this work, we propose a novel interaction framework called Semantic Interactive Learning for the text domain. We frame the problem of incorporating constructive and contextual feedback into the learner as a task to find an architecture that (a) enables more semantic alignment between humans and machines and (b) at the same time helps to maintain statistical characteristics of the input domain when generating user-defined counterexamples based on meaningful corrections. Therefore, we introduce a technique called SemanticPush that is effective for translating conceptual corrections of humans to non-extrapolating training examples such that the learner's reasoning is pushed towards the desired behavior. In several experiments, we show that our method clearly outperforms CAIPI, a state of the art IML strategy, in terms of Predictive Performance as well as Local Explanation Quality in downstream multi-class classification tasks.
Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these CL methods fail to be directly adapted to multi-label image classification due to the difficulty in defining the positive and negative instances to contrast a given anchor image in multi-label scenario, let the label missing one alone, implying that borrowing a commonly-used way from contrastive multi-class learning to define them will incur a lot of false negative instances unfavorable for learning. In this paper, with the introduction of a label correction mechanism to identify missing labels, we first elegantly generate positives and negatives for individual semantic labels of an anchor image, then define a unique contrastive loss for multi-label image classification with missing labels (CLML), the loss is able to accurately bring images close to their true positive images and false negative images, far away from their true negative images. Different from existing multi-label CL losses, CLML also preserves low-rank global and local label dependencies in the latent representation space where such dependencies have been shown to be helpful in dealing with missing labels. To the best of our knowledge, this is the first general multi-label CL loss in the missing-label scenario and thus can seamlessly be paired with those losses of any existing multi-label learning methods just via a single hyperparameter. The proposed strategy has been shown to improve the classification performance of the Resnet101 model by margins of 1.2%, 1.6%, and 1.3% respectively on three standard datasets, MSCOCO, VOC, and NUS-WIDE. Code is available at https://github.com/chuangua/ContrastiveLossMLML.
Cybersecurity breaches are the common anomalies for distributed cyber-physical systems (CPS). However, the cyber security breach classification is still a difficult problem, even using cutting-edge artificial intelligence (AI) approaches. In this paper, we study the multi-class classification problem in cyber security for attack detection. A challenging multi-node data-censoring case is considered. In such a case, data within each data center/node cannot be shared while the local data is incomplete. Particularly, local nodes contain only a part of the multiple classes. In order to train a global multi-class classifier without sharing the raw data across all nodes, the main result of our study is designing a multi-node multi-class classification ensemble approach. By gathering the estimated parameters of the binary classifiers and data densities from each local node, the missing information for each local node is completed to build the global multi-class classifier. Numerical experiments are given to validate the effectiveness of the proposed approach under the multi-node data-censoring case. Under such a case, we even show the out-performance of the proposed approach over the full-data approach.
Estimating accurate and reliable fruit and vegetable counts from images in real-world settings, such as orchards, is a challenging problem that has received significant recent attention. Estimating fruit counts before harvest provides useful information for logistics planning. While considerable progress has been made toward fruit detection, estimating the actual counts remains challenging. In practice, fruits are often clustered together. Therefore, methods that only detect fruits fail to offer general solutions to estimate accurate fruit counts. Furthermore, in horticultural studies, rather than a single yield estimate, finer information such as the distribution of the number of apples per cluster is desirable. In this work, we formulate fruit counting from images as a multi-class classification problem and solve it by training a Convolutional Neural Network. We first evaluate the per-image accuracy of our method and compare it with a state-of-the-art method based on Gaussian Mixture Models over four test datasets. Even though the parameters of the Gaussian Mixture Model-based method are specifically tuned for each dataset, our network outperforms it in three out of four datasets with a maximum of 94\% accuracy. Next, we use the method to estimate the yield for two datasets for which we have ground truth. Our method achieved 96-97\% accuracies. For additional details please see our video here: https://www.youtube.com/watch?v=Le0mb5P-SYc}{https://www.youtube.com/watch?v=Le0mb5P-SYc.
Long-term vertebral fractures severely affect the life quality of patients, causing kyphotic, lumbar deformity and even paralysis. Computed tomography (CT) is a common clinical examination to screen for this disease at early stages. However, the faint radiological appearances and unspecific symptoms lead to a high risk of missed diagnosis, especially for the mild vertebral fractures. In this paper, we argue that reinforcing the faint fracture features to encourage the inter-class separability is the key to improving the accuracy. Motivated by this, we propose a supervised contrastive learning based model to estimate Genent's Grade of vertebral fracture with CT scans. The supervised contrastive learning, as an auxiliary task, narrows the distance of features within the same class while pushing others away, enhancing the model's capability of capturing subtle features of vertebral fractures. Our method has a specificity of 99% and a sensitivity of 85% in binary classification, and a macro-F1 of 77% in multi-class classification, indicating that contrastive learning significantly improves the accuracy of vertebrae fracture screening. Considering the lack of datasets in this field, we construct a database including 208 samples annotated by experienced radiologists. Our desensitized data and codes will be made publicly available for the community.
We present FOLD-SE, an efficient, explainable machine learning algorithm for classification tasks given tabular data containing numerical and categorical values. FOLD-SE generates a set of default rules-essentially a stratified normal logic program-as an (explainable) trained model. Explainability provided by FOLD-SE is scalable, meaning that regardless of the size of the dataset, the number of learned rules and learned literals stay quite small while good accuracy in classification is maintained. A model with smaller number of rules and literals is easier to understand for human beings. FOLD-SE is competitive with state-of-the-art machine learning algorithms such as XGBoost and Multi-Layer Perceptrons (MLP) wrt accuracy of prediction. However, unlike XGBoost and MLP, the FOLD-SE algorithm is explainable. The FOLD-SE algorithm builds upon our earlier work on developing the explainable FOLD-R++ machine learning algorithm for binary classification and inherits all of its positive features. Thus, pre-processing of the dataset, using techniques such as one-hot encoding, is not needed. Like FOLD-R++, FOLD-SE uses prefix sum to speed up computations resulting in FOLD-SE being an order of magnitude faster than XGBoost and MLP in execution speed. The FOLD-SE algorithm outperforms FOLD-R++ as well as other rule-learning algorithms such as RIPPER in efficiency, performance and scalability, especially for large datasets. A major reason for scalable explainability of FOLD-SE is the use of a literal selection heuristics based on Gini Impurity, as opposed to Information Gain used in FOLD-R++. A multi-category classification version of FOLD-SE is also presented.
In this paper we propose a novel method for semi-supervised anomaly detection (SSAD). Our classifier is named QMS22 as its inception was dated 2022 upon the framework of quadratic multiform separation (QMS), a recently introduced classification model. QMS22 tackles SSAD by solving a multi-class classification problem involving both the training set and the test set of the original problem. The classification problem intentionally includes classes with overlapping samples. One of the classes contains mixture of normal samples and outliers, and all other classes contain only normal samples. An outlier score is then calculated for every sample in the test set using the outcome of the classification problem. We also include performance evaluation of QMS22 against top performing classifiers using ninety-five benchmark imbalanced datasets from the KEEL repository. These classifiers are BRM (Bagging-Random Miner), OCKRA (One-Class K-means with Randomly-projected features Algorithm), ISOF (Isolation Forest), and ocSVM (One-Class Support Vector Machine). It is shown by using the area under the curve of the receiver operating characteristic curve as the performance measure, QMS22 significantly outperforms ISOF and ocSVM. Moreover, the Wilcoxon signed-rank tests reveal that there is no statistically significant difference when testing QMS22 against BRM nor QMS22 against OCKRA.
Online learning systems have multiple data repositories in the form of transcripts, books and questions. To enable ease of access, such systems organize the content according to a well defined taxonomy of hierarchical nature (subject-chapter-topic). The task of categorizing inputs to the hierarchical labels is usually cast as a flat multi-class classification problem. Such approaches ignore the semantic relatedness between the terms in the input and the tokens in the hierarchical labels. Alternate approaches also suffer from class imbalance when they only consider leaf level nodes as labels. To tackle the issues, we formulate the task as a dense retrieval problem to retrieve the appropriate hierarchical labels for each content. In this paper, we deal with categorizing questions. We model the hierarchical labels as a composition of their tokens and use an efficient cross-attention mechanism to fuse the information with the term representations of the content. We also propose an adaptive in-batch hard negative sampling approach which samples better negatives as the training progresses. We demonstrate that the proposed approach \textit{TagRec++} outperforms existing state-of-the-art approaches on question datasets as measured by Recall@k. In addition, we demonstrate zero-shot capabilities of \textit{TagRec++} and ability to adapt to label changes.
A key challenge in Machine Learning is class imbalance, where the sample size of some classes (majority classes) are much higher than that of the other classes (minority classes). If we were to train a classifier directly on imbalanced data, it is more likely for the classifier to predict a new sample as one of the majority classes. In the extreme case, the classifier could completely ignore the minority classes. This could have serious sociological implications in healthcare, as the minority classes are usually the disease classes (e.g., death or positive clinical test result). In this paper, we introduce a software that uses Generative Adversarial Networks to oversample the minority classes so as to improve downstream classification. To the best of our knowledge, this is the first tool that allows multi-class classification (where the target can have an arbitrary number of classes). The code of the tool is publicly available in our github repository (https://github.com/yuxiaohuang/research/tree/master/gwu/working/cigan/code).
In minimally invasive surgery, surgical workflow segmentation from video analysis is a well studied topic. The conventional approach defines it as a multi-class classification problem, where individual video frames are attributed a surgical phase label. We introduce a novel reinforcement learning formulation for offline phase transition retrieval. Instead of attempting to classify every video frame, we identify the timestamp of each phase transition. By construction, our model does not produce spurious and noisy phase transitions, but contiguous phase blocks. We investigate two different configurations of this model. The first does not require processing all frames in a video (only <60% and <20% of frames in 2 different applications), while producing results slightly under the state-of-the-art accuracy. The second configuration processes all video frames, and outperforms the state-of-the art at a comparable computational cost. We compare our method against the recent top-performing frame-based approaches TeCNO and Trans-SVNet on the public dataset Cholec80 and also on an in-house dataset of laparoscopic sacrocolpopexy. We perform both a frame-based (accuracy, precision, recall and F1-score) and an event-based (event ratio) evaluation of our algorithms.
Factorizable joint shift (FJS) was recently proposed as a type of dataset shift for which the complete characteristics can be estimated from feature data observations on the test dataset by a method called Joint Importance Aligning. For the multinomial (multiclass) classification setting, we derive a representation of factorizable joint shift in terms of the source (training) distribution, the target (test) prior class probabilities and the target marginal distribution of the features. On the basis of this result, we propose alternatives to joint importance aligning and, at the same time, point out that factorizable joint shift is not fully identifiable if no class label information on the test dataset is available and no additional assumptions are made. Other results of the paper include correction formulae for the posterior class probabilities both under general dataset shift and factorizable joint shift. In addition, we investigate the consequences of assuming factorizable joint shift for the bias caused by sample selection.
The reviews of customers play an essential role in online shopping. People often refer to reviews or comments of previous customers to decide whether to buy a new product. Catching up with this behavior, some people create untruths and illegitimate reviews to hoax customers about the fake quality of products. These are called spam reviews, confusing consumers on online shopping platforms and negatively affecting online shopping behaviors. We propose the dataset called ViSpamReviews, which has a strict annotation procedure for detecting spam reviews on e-commerce platforms. Our dataset consists of two tasks: the binary classification task for detecting whether a review is spam or not and the multi-class classification task for identifying the type of spam. The PhoBERT obtained the highest results on both tasks, 86.89% and 72.17%, respectively, by macro average F1 score.
Deep Learning predictions with measurable confidence are increasingly desirable for real-world problems, especially in high-risk settings. The Conformal Prediction (CP) framework is a versatile solution that guarantees a maximum error rate given minimal constraints. In this paper, we propose a novel conformal loss function that approximates the traditionally two-step CP approach in a single step. By evaluating and penalising deviations from the stringent expected CP output distribution, a Deep Learning model may learn the direct relationship between the input data and the conformal p-values. We carry out a comprehensive empirical evaluation to show our novel loss function's competitiveness for seven binary and multi-class prediction tasks on five benchmark datasets. On the same datasets, our approach achieves significant training time reductions up to 86% compared to Aggregated Conformal Prediction (ACP), while maintaining comparable approximate validity and predictive efficiency.
Estimating uncertainties associated with the predictions of Machine Learning (ML) models is of crucial importance to assess their robustness and predictive power. In this submission, we introduce MAPIE (Model Agnostic Prediction Interval Estimator), an open-source Python library that quantifies the uncertainties of ML models for single-output regression and multi-class classification tasks. MAPIE implements conformal prediction methods, allowing the user to easily compute uncertainties with strong theoretical guarantees on the marginal coverages and with mild assumptions on the model or on the underlying data distribution. MAPIE is hosted on scikit-learn-contrib and is fully "scikit-learn-compatible". As such, it accepts any type of regressor or classifier coming with a scikit-learn API. The library is available at: https://github.com/scikit-learn-contrib/MAPIE/.
The exponential growth of data generated on the Internet in the current information age is a driving force for the digital economy. Extraction of information is the major value in an accumulated big data. Big data dependency on statistical analysis and hand-engineered rules machine learning algorithms are overwhelmed with vast complexities inherent in human languages. Natural Language Processing (NLP) is equipping machines to understand these human diverse and complicated languages. Text Classification is an NLP task which automatically identifies patterns based on predefined or undefined labeled sets. Common text classification application includes information retrieval, modeling news topic, theme extraction, sentiment analysis, and spam detection. In texts, some sequences of words depend on the previous or next word sequences to make full meaning; this is a challenging dependency task that requires the machine to be able to store some previous important information to impact future meaning. Sequence models such as RNN, GRU, and LSTM is a breakthrough for tasks with long-range dependencies. As such, we applied these models to Binary and Multi-class classification. Results generated were excellent with most of the models performing within the range of 80% and 94%. However, this result is not exhaustive as we believe there is room for improvement if machines are to compete with humans.
This report presents the open-source package which implements the series of our boosting works in the past years. In particular, the package includes mainly three lines of techniques, among which the following two are already the standard implementations in popular boosted tree platforms: (i) The histogram-based (feature-binning) approach makes the tree implementation convenient and efficient. In Li et al (2007), a simple fixed-length adaptive binning algorithm was developed. In this report, we demonstrate that such a simple algorithm is still surprisingly effective compared to more sophisticated variants in popular tree platforms. (ii) The explicit gain formula in Li (20010) for tree splitting based on second-order derivatives of the loss function typically improves, often considerably, over the first-order methods. Although the gain formula in Li (2010) was derived for logistic regression loss, it is a generic formula for loss functions with second-derivatives. For example, the open-source package also includes $L_p$ regression for $p\geq 1$. The main contribution of this package is the ABC-Boost (adaptive base class boosting) for multi-class classification. The initial work in Li (2008) derived a new set of derivatives of the classical multi-class logistic regression by specifying a "base class". The accuracy can be substantially improved if the base class is chosen properly. The major technical challenge is to design a search strategy to select the base class. The prior published works implemented an exhaustive search procedure to find the base class which is computationally too expensive. Recently, a new report (Li and Zhao, 20022) presents a unified framework of "Fast ABC-Boost" which allows users to efficiently choose the proper search space for the base class. The package provides interfaces for linux, windows, mac, matlab, R, python.
Categorization of mutual funds or Exchange-Traded-funds (ETFs) have long served the financial analysts to perform peer analysis for various purposes starting from competitor analysis, to quantifying portfolio diversification. The categorization methodology usually relies on fund composition data in the structured format extracted from the Form N-1A. Here, we initiate a study to learn the categorization system directly from the unstructured data as depicted in the forms using natural language processing (NLP). Positing as a multi-class classification problem with the input data being only the investment strategy description as reported in the form and the target variable being the Lipper Global categories, and using various NLP models, we show that the categorization system can indeed be learned with high accuracy. We discuss implications and applications of our findings as well as limitations of existing pre-trained architectures in applying them to learn fund categorization.