In order to classify the indeterministic termination behavior of the open source SAT solver CryptoMiniSat in multi-threading mode while processing hard to solve boolean satisfiability problem instances, internal solver runtime parameters have been collected and analyzed. A subset of these parameters has been selected and employed as features vector to successfully create a machine learning model for the binary classification of the solver's termination behavior with any single new solving run of a not yet solved instance. The model can be used for the early estimation of a solving attempt as belonging or not belonging to the class of candidates with good chances for a fast termination. In this context a combination of active profiles of runtime characteristics appear to mirror the influence of the solver's momentary heuristics on the immediate quality of the solver's resolution process. Because runtime parameters of already the first two solving iterations are enough to forecast termination of the attempt with good success scores, the results of the present work deliver a promising basis which can be further developed in order to enrich CryptoMiniSat or generally any modern SAT solver with AI abilities.
The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary classification problem (Hate and Not Offensive) offered for all three languages. Task B is a fine-grained classification problem for three classes (HATE) Hate speech, OFFENSIVE and PROFANITY offered for English and Hindi. Overall, 652 runs were submitted by 65 teams. The performance of the best classification algorithms for task A are F1 measures 0.91, 0.78 and 0.83 for Marathi, Hindi and English, respectively. This overview presents the tasks and the data development as well as the detailed results. The systems submitted to the competition applied a variety of technologies. The best performing algorithms were mainly variants of transformer architectures.
The widespread diffusion of synthetically generated content is a serious threat that needs urgent countermeasures. As a matter of fact, the generation of synthetic content is not restricted to multimedia data like videos, photographs or audio sequences, but covers a significantly vast area that can include biological images as well, such as western blot and microscopic images. In this paper, we focus on the detection of synthetically generated western blot images. These images are largely explored in the biomedical literature and it has been already shown they can be easily counterfeited with few hopes to spot manipulations by visual inspection or by using standard forensics detectors. To overcome the absence of publicly available data for this task, we create a new dataset comprising more than 14K original western blot images and 24K synthetic western blot images, generated using four different state-of-the-art generation methods. We investigate different strategies to detect synthetic western blots, exploring binary classification methods as well as one-class detectors. In both scenarios, we never exploit synthetic western blot images at training stage. The achieved results show that synthetically generated western blot images can be spot with good accuracy, even though the exploited detectors are not optimized over synthetic versions of these scientific images. We also test the robustness of the developed detectors against post-processing operations commonly performed on scientific images, showing that we can be robust to JPEG compression and that some generative models are easily recognizable, despite the application of editing might alter the artifacts they leave.
In the institutional research mode, in order to explore which characteristics are the best indicators for predicting academic risk from the student behavior data sets that have high-dimensional, unbalanced classified small sample, it transforms the academic risk prediction of college students into a binary classification task. It predicts academic risk based on the LightGBM model and the interpretable machine learning method of Shapley value. The simulation results show that from the global perspective of the prediction model, characteristics such as the quality of academic partners, the seating position in classroom, the dormitory study atmosphere, the English scores of the college entrance examination, the quantity of academic partners, the addiction level of video games, the mobility of academic partners, and the degree of truancy are the best 8 predictors for academic risk. It is contrary to intuition that characteristics such as living in campus or not, work-study, lipstick addiction, student leader or not, lover amount, and smoking have little correlation with university academic risk in this experiment. From the local perspective of the sample, the factors affecting academic risk vary from person to person. It can perform personalized interpretable analysis through Shapley values, which cannot be done by traditional mathematical statistical prediction models. The academic contributions of this research are mainly in two aspects: First, the learning interaction networks is proposed for the first time, so that social behavior can be used to compensate for the one-sided individual behavior and improve the performance of academic risk prediction. Second, the introduction of Shapley value calculation makes machine learning that lacks a clear reasoning process visualized, and provides intuitive decision support for education managers.
Counterfactual explanations represent the minimal change to a data sample that alters its predicted classification, typically from an unfavorable initial class to a desired target class. Counterfactuals help answer questions such as "what needs to change for this application to get accepted for a loan?". A number of recently proposed approaches to counterfactual generation give varying definitions of "plausible" counterfactuals and methods to generate them. However, many of these methods are computationally intensive and provide unconvincing explanations. Here we introduce SharpShooter, a method for binary classification that starts by creating a projected version of the input that classifies as the target class. Counterfactual candidates are then generated in latent space on the interpolation line between the input and its projection. We then demonstrate that our framework translates core characteristics of a sample to its counterfactual through the use of learned representations. Furthermore, we show that SharpShooter is competitive across common quality metrics on tabular and image datasets while being orders of magnitude faster than two comparable methods and excels at measures of realism, making it well-suited for high velocity machine learning applications which require timely explanations.
The Facebook network allows its users to record their reactions to text via a typology of emotions. This network, taken at scale, is therefore a prime data set of annotated sentiment data. This paper uses millions of such reactions, derived from a decade worth of Facebook post data centred around a Sri Lankan context, to model an eye of the beholder approach to sentiment detection for online Sinhala textual content. Three different sentiment analysis models are built, taking into account a limited subset of reactions, all reactions, and another that derives a positive/negative star rating value. The efficacy of these models in capturing the reactions of the observers are then computed and discussed. The analysis reveals that binary classification of reactions, for Sinhala content, is significantly more accurate than the other approaches. Furthermore, the inclusion of the like reaction hinders the capability of accurately predicting other reactions.
With the global issue of plastic debris ever expanding, it is about time that the technology industry stepped in. This study aims to assess whether deep learning can successfully distinguish between marine life and man-made debris underwater. The aim is to find if we are safely able to clean up our oceans with Artificial Intelligence without disrupting the delicate balance of the aquatic ecosystems. The research explores the use of Convolutional Neural Networks from the perspective of protecting the ecosystem, rather than primarily collecting rubbish. We did this by building a custom-built, deep learning model, with an original database including 1,644 underwater images and used a binary classification to sort synthesised material from aquatic life. We concluded that although it is possible to safely distinguish between debris and life, further exploration with a larger database and stronger CNN structure has the potential for much more promising results.
Increasing the cardinality of categorical variables might decrease the overall performance of machine learning (ML) algorithms. This paper presents a novel computational preprocessing method to convert categorical to numerical variables ML algorithms. It uses a supervised binary classifier to extract additional context-related features from the categorical values. Up to two numerical variables per categorical variable are created, depending on the compression achieved by the Principal Component Analysis (PCA). The method requires two hyperparameters: a threshold related to the distribution of categories in the variables and the PCA representativeness. This paper applies the proposed approach to the well-known cybersecurity NSLKDD dataset to select and convert three categorical features to numerical features. After choosing the threshold parameter, we use conditional probabilities to convert the three categorical variables into six new numerical variables. After that, we feed these numerical variables to the PCA algorithm and select the whole or partial numbers of the Principal Components (PCs). Finally, by applying binary classification with ten different classifiers, we measure the performance of the new encoder and compare it with the other 17 well-known category encoders. The new technique achieves the highest performance related to accuracy and Area Under the Curve (AUC) on high cardinality categorical variables. Also, we define the harmonic average metrics to find the best trade-off between train and test performances and prevent underfitting and overfitting. Ultimately, the number of newly created numerical variables is minimal. This data reduction improves computational processing time in Internet of things (IoT) devices in future telecommunication networks.
We introduce definitions of computable PAC learning for binary classification over computable metric spaces. We provide sufficient conditions for learners that are empirical risk minimizers (ERM) to be computable, and bound the strong Weihrauch degree of an ERM learner under more general conditions. We also give a presentation of a hypothesis class that does not admit any proper computable PAC learner with computable sample function, despite the underlying class being PAC learnable.
Given a real-valued hypothesis class $\mathcal{H}$, we investigate under what conditions there is a differentially private algorithm which learns an optimal hypothesis from $\mathcal{H}$ given i.i.d. data. Inspired by recent results for the related setting of binary classification (Alon et al., 2019; Bun et al., 2020), where it was shown that online learnability of a binary class is necessary and sufficient for its private learnability, Jung et al. (2020) showed that in the setting of regression, online learnability of $\mathcal{H}$ is necessary for private learnability. Here online learnability of $\mathcal{H}$ is characterized by the finiteness of its $\eta$-sequential fat shattering dimension, ${\rm sfat}_\eta(\mathcal{H})$, for all $\eta > 0$. In terms of sufficient conditions for private learnability, Jung et al. (2020) showed that $\mathcal{H}$ is privately learnable if $\lim_{\eta \downarrow 0} {\rm sfat}_\eta(\mathcal{H})$ is finite, which is a fairly restrictive condition. We show that under the relaxed condition $\lim \inf_{\eta \downarrow 0} \eta \cdot {\rm sfat}_\eta(\mathcal{H}) = 0$, $\mathcal{H}$ is privately learnable, establishing the first nonparametric private learnability guarantee for classes $\mathcal{H}$ with ${\rm sfat}_\eta(\mathcal{H})$ diverging as $\eta \downarrow 0$. Our techniques involve a novel filtering procedure to output stable hypotheses for nonparametric function classes.
We establish an equivalence between a family of adversarial training problems for non-parametric binary classification and a family of regularized risk minimization problems where the regularizer is a nonlocal perimeter functional. The resulting regularized risk minimization problems admit exact convex relaxations of the type $L^1+$ (nonlocal) $\operatorname{TV}$, a form frequently studied in image analysis and graph-based learning. A rich geometric structure is revealed by this reformulation which in turn allows us to establish a series of properties of optimal solutions of the original problem, including the existence of minimal and maximal solutions (interpreted in a suitable sense), and the existence of regular solutions (also interpreted in a suitable sense). In addition, we highlight how the connection between adversarial training and perimeter minimization problems provides a novel, directly interpretable, statistical motivation for a family of regularized risk minimization problems involving perimeter/total variation. The majority of our theoretical results are independent of the distance used to define adversarial attacks.
Self-supervised contrastive learning frameworks have progressed rapidly over the last few years. In this paper, we propose a novel loss function for contrastive learning. We model our pre-training task as a binary classification problem to induce an implicit contrastive effect. We further improve the n\"aive loss function after removing the effect of the positive-positive repulsion and incorporating the upper bound of the negative pair repulsion. Unlike existing methods, the proposed loss function optimizes the mutual information in positive and negative pairs. We also present a closed-form expression for the parameter gradient flow and compare the behaviour of self-supervised contrastive frameworks using Hessian eigenspectrum to analytically study their convergence. The proposed method outperforms SOTA self-supervised contrastive frameworks on benchmark datasets such as CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet. After 200 pretraining epochs with ResNet-18 as the backbone, the proposed model achieves an accuracy of 86.36%, 58.18%, 80.50%, and 30.87% on the CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet datasets, respectively, and surpasses the SOTA contrastive baseline by 1.93%, 3.57%, 4.85%, and 0.33%, respectively. The proposed framework also achieves a state-of-the-art accuracy of 78.4% (200 epochs) and 65.22% (100 epochs) Top-1 Linear Evaluation accuracy on ImageNet100 and ImageNet1K datasets, respectively.
In light of the success of transferring language models into NLP tasks, we ask whether the full BERT model is always the best and does it exist a simple but effective method to find the winning ticket in state-of-the-art deep neural networks without complex calculations. We construct a series of BERT-based models with different size and compare their predictions on 8 binary classification tasks. The results show there truly exist smaller sub-networks performing better than the full model. Then we present a further study and propose a simple method to shrink BERT appropriately before fine-tuning. Some extended experiments indicate that our method could save time and storage overhead extraordinarily with little even no accuracy loss.
Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty. Probability-estimation models are trained on observed outcomes (e.g. whether it has rained or not, or whether a patient has died or not), because the ground-truth probabilities of the events of interest are typically unknown. The problem is therefore analogous to binary classification, with the difference that the objective is to estimate probabilities rather than predicting the specific outcome. This work investigates probability estimation from high-dimensional data using deep neural networks. There exist several methods to improve the probabilities generated by these models but they mostly focus on model (epistemic) uncertainty. For problems with inherent uncertainty, it is challenging to evaluate performance without access to ground-truth probabilities. To address this, we build a synthetic dataset to study and compare different computable metrics. We evaluate existing methods on the synthetic data as well as on three real-world probability estimation tasks, all of which involve inherent uncertainty: precipitation forecasting from radar images, predicting cancer patient survival from histopathology images, and predicting car crashes from dashcam videos. We also give a theoretical analysis of a model for high-dimensional probability estimation which reproduces several of the phenomena evinced in our experiments. Finally, we propose a new method for probability estimation using neural networks, which modifies the training process to promote output probabilities that are consistent with empirical probabilities computed from the data. The method outperforms existing approaches on most metrics on the simulated as well as real-world data.
This work addressed the problem of learning a network with communication between vertices. The communication between vertices is presented in the form of perturbation on the measure. We studied the scenario where samples are drawn from a uniform ergodic Random Graph Process (RGPs for short), which provides a natural mathematical context for the problem of interest. For the binary classification problem, the result we obtained gives uniform learn-ability as the worst-case theoretical limits. We introduced the structural Rademacher complexity, which naturally fused into the VC theory to upperbound the first moment. With the martingale method and Marton's coupling, we establish the tail bound for uniform convergence and give consistency guarantee for empirical risk minimizer. The technique used in this work to obtain high probability bounds is of independent interest to other mixing processes with and without network structure.
Federated learning allows clients to collaboratively learn statistical models while keeping their data local. Federated learning was originally used to train a unique global model to be served to all clients, but this approach might be sub-optimal when clients' local data distributions are heterogeneous. In order to tackle this limitation, recent personalized federated learning methods train a separate model for each client while still leveraging the knowledge available at other clients. In this work, we exploit the ability of deep neural networks to extract high quality vectorial representations (embeddings) from non-tabular data, e.g., images and text, to propose a personalization mechanism based on local memorization. Personalization is obtained by interpolating a collectively trained global model with a local $k$-nearest neighbors (kNN) model based on the shared representation provided by the global model. We provide generalization bounds for the proposed approach in the case of binary classification, and we show on a suite of federated datasets that this approach achieves significantly higher accuracy and fairness than state-of-the-art methods.
Mitigating the energy requirements of artificial intelligence requires novel physical substrates for computation. Phononic metamaterials have a vanishingly low power dissipation and hence are a prime candidate for green, always-on computers. However, their use in machine learning applications has not been explored due to the complexity of their design process: Current phononic metamaterials are restricted to simple geometries (e.g. periodic, tapered), and hence do not possess sufficient expressivity to encode machine learning tasks. We design and fabricate a non-periodic phononic metamaterial, directly from data samples, that can distinguish between pairs of spoken words in the presence of a simple readout nonlinearity; hence demonstrating that phononic metamaterials are a viable avenue towards zero-power smart devices.
Deep models trained through maximum likelihood have achieved state-of-the-art results for survival analysis. Despite this training scheme, practitioners evaluate models under other criteria, such as binary classification losses at a chosen set of time horizons, e.g. Brier score (BS) and Bernoulli log likelihood (BLL). Models trained with maximum likelihood may have poor BS or BLL since maximum likelihood does not directly optimize these criteria. Directly optimizing criteria like BS requires inverse-weighting by the censoring distribution. However, estimating the censoring model under these metrics requires inverse-weighting by the failure distribution. The objective for each model requires the other, but neither are known. To resolve this dilemma, we introduce Inverse-Weighted Survival Games. In these games, objectives for each model are built from re-weighted estimates featuring the other model, where the latter is held fixed during training. When the loss is proper, we show that the games always have the true failure and censoring distributions as a stationary point. This means models in the game do not leave the correct distributions once reached. We construct one case where this stationary point is unique. We show that these games optimize BS on simulations and then apply these principles on real world cancer and critically-ill patient data.
We consider the problem of multi-class classification, where a stream of adversarially chosen queries arrive and must be assigned a label online. Unlike traditional bounds which seek to minimize the misclassification rate, we minimize the total distance from each query to the region corresponding to its correct label. When the true labels are determined via a nearest neighbor partition -- i.e. the label of a point is given by which of $k$ centers it is closest to in Euclidean distance -- we show that one can achieve a loss that is independent of the total number of queries. We complement this result by showing that learning general convex sets requires an almost linear loss per query. Our results build off of regret guarantees for the geometric problem of contextual search. In addition, we develop a novel reduction technique from multiclass classification to binary classification which may be of independent interest.
We design a new adaptive learning algorithm for misclassification cost problems that attempt to reduce the cost of misclassified instances derived from the consequences of various errors. Our algorithm (adaptive cost sensitive learning - AdaCSL) adaptively adjusts the loss function such that the classifier bridges the difference between the class distributions between subgroups of samples in the training and test data sets with similar predicted probabilities (i.e., local training-test class distribution mismatch). We provide some theoretical performance guarantees on the proposed algorithm and present empirical evidence that a deep neural network used with the proposed AdaCSL algorithm yields better cost results on several binary classification data sets that have class-imbalanced and class-balanced distributions compared to other alternative approaches.