Throughout cosmological simulations, the properties of the matter density field in the initial conditions have a decisive impact on the features of the structures formed today. In this paper we use a random-forest classification algorithm to infer whether or not dark matter particles, traced back to the initial conditions, would end up in dark matter halos whose masses are above some threshold. This problem might be posed as a binary classification task, where the initial conditions of the matter density field are mapped into classification labels provided by a halo finder program. Our results show that random forests are effective tools to predict the output of cosmological simulations without running the full process. These techniques might be used in the future to decrease the computational time and to explore more efficiently the effect of different dark matter/dark energy candidates on the formation of cosmological structures.
Pre-trained language models such as ClinicalBERT have achieved impressive results on tasks such as medical Natural Language Inference. At first glance, this may suggest that these models are able to perform medical reasoning tasks, such as mapping symptoms to diseases. However, we find that standard benchmarks such as MedNLI contain relatively few examples that require such forms of reasoning. To better understand the medical reasoning capabilities of existing language models, in this paper we introduce DisKnE, a new benchmark for Disease Knowledge Evaluation. To construct this benchmark, we annotated each positive MedNLI example with the types of medical reasoning that are needed. We then created negative examples by corrupting these positive examples in an adversarial way. Furthermore, we define training-test splits per disease, ensuring that no knowledge about test diseases can be learned from the training data, and we canonicalize the formulation of the hypotheses to avoid the presence of artefacts. This leads to a number of binary classification problems, one for each type of reasoning and each disease. When analysing pre-trained models for the clinical/biomedical domain on the proposed benchmark, we find that their performance drops considerably.
An anomalous sound detection system to detect unknown anomalous sounds usually needs to be built using only normal sound data. Moreover, it is desirable to improve the system by effectively using a small amount of anomalous sound data, which will be accumulated through the system's operation. As one of the methods to meet these requirements, we focus on a binary classification model that is developed by using not only normal data but also outlier data in the other domains as pseudo-anomalous sound data, which can be easily updated by using anomalous data. In this paper, we implement a new loss function based on metric learning to learn the distance relationship from each class centroid in feature space for the binary classification model. The proposed multi-task learning of the binary classification and the metric learning makes it possible to build the feature space where the within-class variance is minimized and the between-class variance is maximized while keeping normal and anomalous classes linearly separable. We also investigate the effectiveness of additionally using anomalous sound data for further improving the binary classification model. Our results showed that multi-task learning using binary classification and metric learning to consider the distance from each class centroid in the feature space is effective, and performance can be significantly improved by using even a small amount of anomalous data during training.
The design of complex engineering systems leads to solving very large optimization problems involving different disciplines. Strategies allowing disciplines to optimize in parallel by providing sub-objectives and splitting the problem into smaller parts, such as Collaborative Optimization, are promising solutions.However, most of them have slow convergence which reduces their practical use. Earlier efforts to fasten convergence by learning surrogate models have not yet succeeded at sufficiently improving the competitiveness of these strategies.This paper shows that, in the case of Collaborative Optimization, faster and more reliable convergence can be obtained by solving an interesting instance of binary classification: on top of the target label, the training data of one of the two classes contains the distance to the decision boundary and its derivative. Leveraging this information, we propose to train a neural network with an asymmetric loss function, a structure that guarantees Lipshitz continuity, and a regularization towards respecting basic distance function properties. The approach is demonstrated on a toy learning example, and then applied to a multidisciplinary aircraft design problem.
In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents. In contrast to most existing research papers in this area where the focus is on solving just one component of a deployable chatbot, we present an end-to-end set of solutions to take the reader from an unlabelled chatlogs to a deployed chatbot. This set of solutions includes creating a self-supervised dataset and a weakly labelled dataset from chatlogs, as well as a systematic approach to selecting a fixed list of canned responses. We present a hierarchical-based RNN architecture for the response selection model, chosen for its ability to cache intermediate utterance embeddings, which helped to meet deployment inference speed requirements. We compare the performance of this architecture across 3 different learning objectives: self-supervised contrastive learning, binary classification, and multi-class classification. We find that using a self-supervised contrastive learning model outperforms training the binary and multi-class classification models on a weakly labelled dataset. Our results validate that the self-supervised contrastive learning approach can be effectively used for a real-world chatbot scenario.
Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make predictions based on context-response content similarity. However, over-reliance on content similarity makes the models less sensitive to the presence of inconsistencies, incorrect time expressions and other factors important for response appropriateness and coherence. We propose approaches for automatically creating adversarial negative training data to help ranking and evaluation models learn features beyond content similarity. We propose mask-and-fill and keyword-guided approaches that generate negative examples for training more robust dialogue systems. These generated adversarial responses have high content similarity with the contexts but are either incoherent, inappropriate or not fluent. Our approaches are fully data-driven and can be easily incorporated in existing models and datasets. Experiments on classification, ranking and evaluation tasks across multiple datasets demonstrate that our approaches outperform strong baselines in providing informative negative examples for training dialogue systems.
This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is general, and the (optimal) Bayes risk is not necessarily zero. In this setting, it is shown that gradient descent with early stopping achieves population risk arbitrarily close to optimal in terms of not just logistic and misclassification losses, but also in terms of calibration, meaning the sigmoid mapping of its outputs approximates the true underlying conditional distribution arbitrarily finely. Moreover, the necessary iteration, sample, and architectural complexities of this analysis all scale naturally with a certain complexity measure of the true conditional model. Lastly, while it is not shown that early stopping is necessary, it is shown that any univariate classifier satisfying a local interpolation property is inconsistent.
We study the behavior of linear discriminant functions for binary classification in the infinite-imbalance limit, where the sample size of one class grows without bound while the sample size of the other remains fixed. The coefficients of the classifier minimize an empirical loss specified through a weight function. We show that for a broad class of weight functions, the intercept diverges but the rest of the coefficient vector has a finite almost sure limit under infinite imbalance, extending prior work on logistic regression. The limit depends on the left-tail growth rate of the weight function, for which we distinguish two cases: subexponential and exponential. The limiting coefficient vectors reflect robustness or conservatism properties in the sense that they optimize against certain worst-case alternatives. In the subexponential case, the limit is equivalent to an implicit choice of upsampling distribution for the minority class. We apply these ideas in a credit risk setting, with particular emphasis on performance in the high-sensitivity and high-specificity regions.
Transfer learning can significantly improve the sample efficiency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source task. Despite years of successful applications, transfer learning practice often relies on ad-hoc solutions, while theoretical understanding of these procedures is still limited. In the present work, we re-think a solvable model of synthetic data as a framework for modeling correlation between data-sets. This setup allows for an analytic characterization of the generalization performance obtained when transferring the learned feature map from the source to the target task. Focusing on the problem of training two-layer networks in a binary classification setting, we show that our model can capture a range of salient features of transfer learning with real data. Moreover, by exploiting parametric control over the correlation between the two data-sets, we systematically investigate under which conditions the transfer of features is beneficial for generalization.
Neural-based multi-task learning has been successfully used in many real-world large-scale applications such as recommendation systems. For example, in movie recommendations, beyond providing users movies which they tend to purchase and watch, the system might also optimize for users liking the movies afterwards. With multi-task learning, we aim to build a single model that learns these multiple goals and tasks simultaneously. However, the prediction quality of commonly used multi task models is often sensitive to the relationships between tasks. It is therefore important to study the modeling tradeoffs between task-specific objectives and inter-task relationships. In this work, we propose a novel multi-task learning approach, Multi-gate Mixture-of-Experts (MMoE), which explicitly learns to model task relationships from data. We adapt the Mixture-of-Experts (MoE) structure to multi-task learning by sharing the expert submodels across all tasks, while also having a gating network trained to optimize each task. To validate our approach on data with different levels of task relatedness, we first apply it to a synthetic dataset where we control the task relatedness. We show that the proposed approach performs better than baseline methods when the tasks are less related. We also show that the MMoE structure results in an additional trainability benefit, depending on different levels of randomness in the training data and model initialization. Furthermore, we demonstrate the performance improvements by MMoE on real tasks including a binary classification benchmark, and a large-scale content recommendation system at Google.
Sexism has become an increasingly major problem on social networks during the last years. The first shared task on sEXism Identification in Social neTworks (EXIST) at IberLEF 2021 is an international competition in the field of Natural Language Processing (NLP) with the aim to automatically identify sexism in social media content by applying machine learning methods. Thereby sexism detection is formulated as a coarse (binary) classification problem and a fine-grained classification task that distinguishes multiple types of sexist content (e.g., dominance, stereotyping, and objectification). This paper presents the contribution of the AIT_FHSTP team at the EXIST2021 benchmark for both tasks. To solve the tasks we applied two multilingual transformer models, one based on multilingual BERT and one based on XLM-R. Our approach uses two different strategies to adapt the transformers to the detection of sexist content: first, unsupervised pre-training with additional data and second, supervised fine-tuning with additional and augmented data. For both tasks our best model is XLM-R with unsupervised pre-training on the EXIST data and additional datasets and fine-tuning on the provided dataset. The best run for the binary classification (task 1) achieves a macro F1-score of 0.7752 and scores 5th rank in the benchmark; for the multiclass classification (task 2) our best submission scores 6th rank with a macro F1-score of 0.5589.
Over-parameterized models can perfectly learn various types of data distributions, however, generalization error is usually lower for real data in comparison to artificial data. This suggests that the properties of data distributions have an impact on generalization capability. This work focuses on the search space defined by the input data and assumes that the correlation between labels of neighboring input values influences generalization. If correlation is low, the randomness of the input data space is high leading to high generalization error. We suggest to measure the randomness of an input data space using Maurer's universal. Results for synthetic classification tasks and common image classification benchmarks (MNIST, CIFAR10, and Microsoft's cats vs. dogs data set) find a high correlation between the randomness of input data spaces and the generalization error of deep neural networks for binary classification problems.
Cyberbullying or Online harassment detection on social media for various major languages is currently being given a good amount of focus by researchers worldwide. Being the seventh most speaking language in the world and increasing usage of online platform among the Bengali speaking people urge to find effective detection technique to handle the online harassment. In this paper, we have proposed binary and multiclass classification model using hybrid neural network for bully expression detection in Bengali language. We have used 44,001 users comments from popular public Facebook pages, which fall into five classes - Non-bully, Sexual, Threat, Troll and Religious. We have examined the performance of our proposed models from different perspective. Our binary classification model gives 87.91% accuracy, whereas introducing ensemble technique after neural network for multiclass classification, we got 85% accuracy.
In transfer learning, we wish to make inference about a target population when we have access to data both from the distribution itself, and from a different but related source distribution. We introduce a flexible framework for transfer learning in the context of binary classification, allowing for covariate-dependent relationships between the source and target distributions that are not required to preserve the Bayes decision boundary. Our main contributions are to derive the minimax optimal rates of convergence (up to poly-logarithmic factors) in this problem, and show that the optimal rate can be achieved by an algorithm that adapts to key aspects of the unknown transfer relationship, as well as the smoothness and tail parameters of our distributional classes. This optimal rate turns out to have several regimes, depending on the interplay between the relative sample sizes and the strength of the transfer relationship, and our algorithm achieves optimality by careful, decision tree-based calibration of local nearest-neighbour procedures.
Machine learning researchers and practitioners steadily enlarge the multitude of successful learning models. They achieve this through in-depth theoretical analyses and experiential heuristics. However, there is no known general-purpose procedure for rigorously evaluating whether newly proposed models indeed successfully learn from data. We show that such a procedure cannot exist. For PAC binary classification, uniform and universal online learning, and exact learning through teacher-learner interactions, learnability is in general undecidable, both in the sense of independence of the axioms in a formal system and in the sense of uncomputability. Our proofs proceed via computable constructions that encode the consistency problem for formal systems and the halting problem for Turing machines into whether certain function classes are trivial/finite or highly complex, which we then relate to whether these classes are learnable via established characterizations of learnability through complexity measures. Our work shows that undecidability appears in the theoretical foundations of artificial intelligence: There is no one-size-fits-all algorithm for deciding whether a machine learning model can be successful. We cannot in general automatize the process of assessing new learning models.
The diagnosis of prostate cancer faces a problem with overdiagnosis that leads to damaging side effects due to unnecessary treatment. Research has shown that the use of multi-parametric magnetic resonance images to conduct biopsies can drastically help to mitigate the overdiagnosis, thus reducing the side effects on healthy patients. This study aims to investigate the use of deep learning techniques to explore computer-aid diagnosis based on MRI as input. Several diagnosis problems ranging from classification of lesions as being clinically significant or not to the detection and segmentation of lesions are addressed with deep learning based approaches. This thesis tackled two main problems regarding the diagnosis of prostate cancer. Firstly, XmasNet was used to conduct two large experiments on the classification of lesions. Secondly, detection and segmentation experiments were conducted, first on the prostate and afterward on the prostate cancer lesions. The former experiments explored the lesions through a two-dimensional space, while the latter explored models to work with three-dimensional inputs. For this task, the 3D models explored were the 3D U-Net and a pretrained 3D ResNet-18. A rigorous analysis of all these problems was conducted with a total of two networks, two cropping techniques, two resampling techniques, two crop sizes, five input sizes and data augmentations experimented for lesion classification. While for segmentation two models, two input sizes and data augmentations were experimented. However, while the binary classification of the clinical significance of lesions and the detection and segmentation of the prostate already achieve the desired results (0.870 AUC and 0.915 dice score respectively), the classification of the PIRADS score and the segmentation of lesions still have a large margin to improve (0.664 accuracy and 0.690 dice score respectively).
Recently, there have been several papers that discuss the extension of the Pinball loss Support Vector Machine (Pin-SVM) model, originally proposed by Huang et al.,[1][2]. Pin-SVM classifier deals with the pinball loss function, which has been defined in terms of the parameter $\tau$. The parameter $\tau$ can take values in $[ -1,1]$. The existing Pin-SVM model requires to solve the same optimization problem for all values of $\tau$ in $[ -1,1]$. In this paper, we improve the existing Pin-SVM model for the binary classification task. At first, we note that there is major difficulty in Pin-SVM model (Huang et al. [1]) for $ -1 \leq \tau < 0$. Specifically, we show that the Pin-SVM model requires the solution of different optimization problem for $ -1 \leq \tau < 0$. We further propose a unified model termed as Unified Pin-SVM which results in a QPP valid for all $-1\leq \tau \leq 1$ and hence more convenient to use. The proposed Unified Pin-SVM model can obtain a significant improvement in accuracy over the existing Pin-SVM model which has also been empirically justified by extensive numerical experiments with real-world datasets.
As machine learning algorithms start to get integrated into the decision-making process of companies and organizations, insurance products are being developed to protect their owners from liability risk. Algorithmic liability differs from human liability since it is based on a single model compared to multiple heterogeneous decision-makers and its performance is known a priori for a given set of data. Traditional actuarial tools for human liability do not take these properties into consideration, primarily focusing on the distribution of historical claims. We propose, for the first time, a quantitative framework to estimate the risk exposure of insurance contracts for machine-driven liability, introducing the concept of algorithmic insurance. Specifically, we present an optimization formulation to estimate the risk exposure of a binary classification model given a pre-defined range of premiums. We adjust the formulation to account for uncertainty in the resulting losses using robust optimization. Our approach outlines how properties of the model, such as accuracy, interpretability, and generalizability, can influence the insurance contract evaluation. To showcase a practical implementation of the proposed framework, we present a case study of medical malpractice in the context of breast cancer detection. Our analysis focuses on measuring the effect of the model parameters on the expected financial loss and identifying the aspects of algorithmic performance that predominantly affect the risk of the contract.
Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate pre-training, ELECTRA trains a discriminator that predicts whether each input token is replaced by a generator. However, this new task, as a binary classification, is less semantically informative. In this study, we present a new text encoder pre-training method that improves ELECTRA based on multi-task learning. Specifically, we train the discriminator to simultaneously detect replaced tokens and select original tokens from candidate sets. We further develop two techniques to effectively combine all pre-training tasks: (1) using attention-based networks for task-specific heads, and (2) sharing bottom layers of the generator and the discriminator. Extensive experiments on GLUE and SQuAD datasets demonstrate both the effectiveness and the efficiency of our proposed method.
In this work, we introduce a novel method for solving the set inversion problem by formulating it as a binary classification problem. Aiming to develop a fast algorithm that can work effectively with high-dimensional and computationally expensive nonlinear models, we focus on active learning, a family of new and powerful techniques which can achieve the same level of accuracy with fewer data points compared to traditional learning methods. Specifically, we propose OASIS, an active learning framework using Support Vector Machine algorithms for solving the problem of set inversion. Our method works well in high dimensions and its computational cost is relatively robust to the increase of dimension. We illustrate the performance of OASIS by several simulation studies and show that our algorithm outperforms VISIA, the state-of-the-art method.