In this paper, we present Fedlearn-Algo, an open-source privacy preserving machine learning platform. We use this platform to demonstrate our research and development results on privacy preserving machine learning algorithms. As the first batch of novel FL algorithm examples, we release vertical federated kernel binary classification model and vertical federated random forest model. They have been tested to be more efficient than existing vertical federated learning models in our practice. Besides the novel FL algorithm examples, we also release a machine communication module. The uniform data transfer interface supports transferring widely used data formats between machines. We will maintain this platform by adding more functional modules and algorithm examples. The code is available at https://github.com/fedlearnAI/fedlearn-algo.
Based on PixelHop and PixelHop++, which are recently developed using the successive subspace learning (SSL) framework, we propose an enhanced solution for object classification, called E-PixelHop, in this work. E-PixelHop consists of the following steps. First, to decouple the color channels for a color image, we apply principle component analysis and project RGB three color channels onto two principle subspaces which are processed separately for classification. Second, to address the importance of multi-scale features, we conduct pixel-level classification at each hop with various receptive fields. Third, to further improve pixel-level classification accuracy, we develop a supervised label smoothing (SLS) scheme to ensure prediction consistency. Forth, pixel-level decisions from each hop and from each color subspace are fused together for image-level decision. Fifth, to resolve confusing classes for further performance boosting, we formulate E-PixelHop as a two-stage pipeline. In the first stage, multi-class classification is performed to get a soft decision for each class, where the top 2 classes with the highest probabilities are called confusing classes. Then,we conduct a binary classification in the second stage. The main contributions lie in Steps 1, 3 and 5.We use the classification of the CIFAR-10 dataset as an example to demonstrate the effectiveness of the above-mentioned key components of E-PixelHop.
Federated learning is an emerging research paradigm for enabling collaboratively training deep learning models without sharing patient data. However, the data from different institutions are usually heterogeneous across institutions, which may reduce the performance of models trained using federated learning. In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning. Unlike previous federated methods that require complex heuristic training or hyper parameter tuning, our SplitAVG leverages the simple network split and feature map concatenation strategies to encourage the federated model training an unbiased estimator of the target data distribution. We compare SplitAVG with seven state-of-the-art federated learning methods, using centrally hosted training data as the baseline on a suite of both synthetic and real-world federated datasets. We find that the performance of models trained using all the comparison federated learning methods degraded significantly with the increasing degrees of data heterogeneity. In contrast, SplitAVG method achieves comparable results to the baseline method under all heterogeneous settings, that it achieves 96.2% of the accuracy and 110.4% of the mean absolute error obtained by the baseline in a diabetic retinopathy binary classification dataset and a bone age prediction dataset, respectively, on highly heterogeneous data partitions. We conclude that SplitAVG method can effectively overcome the performance drops from variability in data distributions across institutions. Experimental results also show that SplitAVG can be adapted to different base networks and generalized to various types of medical imaging tasks.
Receiver Operating Characteristic (ROC) curves are plots of true positive rate versus false positive rate which are useful for evaluating binary classification models, but difficult to use for learning since the Area Under the Curve (AUC) is non-convex. ROC curves can also be used in other problems that have false positive and true positive rates such as changepoint detection. We show that in this more general context, the ROC curve can have loops, points with highly sub-optimal error rates, and AUC greater than one. This observation motivates a new optimization objective: rather than maximizing the AUC, we would like a monotonic ROC curve with AUC=1 that avoids points with large values for Min(FP,FN). We propose a convex relaxation of this objective that results in a new surrogate loss function called the AUM, short for Area Under Min(FP, FN). Whereas previous loss functions are based on summing over all labeled examples or pairs, the AUM requires a sort and a sum over the sequence of points on the ROC curve. We show that AUM directional derivatives can be efficiently computed and used in a gradient descent learning algorithm. In our empirical study of supervised binary classification and changepoint detection problems, we show that our new AUM minimization learning algorithm results in improved AUC and comparable speed relative to previous baselines.
The vast majority of statistical theory on binary classification characterizes performance in terms of accuracy. However, accuracy is known in many cases to poorly reflect the practical consequences of classification error, most famously in imbalanced binary classification, where data are dominated by samples from one of two classes. The first part of this paper derives a novel generalization of the Bayes-optimal classifier from accuracy to any performance metric computed from the confusion matrix. Specifically, this result (a) demonstrates that stochastic classifiers sometimes outperform the best possible deterministic classifier and (b) removes an empirically unverifiable absolute continuity assumption that is poorly understood but pervades existing results. We then demonstrate how to use this generalized Bayes classifier to obtain regret bounds in terms of the error of estimating regression functions under uniform loss. Finally, we use these results to develop some of the first finite-sample statistical guarantees specific to imbalanced binary classification. Specifically, we demonstrate that optimal classification performance depends on properties of class imbalance, such as a novel notion called Uniform Class Imbalance, that have not previously been formalized. We further illustrate these contributions numerically in the case of $k$-nearest neighbor classification
This note proposes a way of making probability forecasting rules less sensitive to changes in data distribution, concentrating on the simple case of binary classification. This is important in applications of machine learning, where the quality of a trained predictor may drop significantly in the process of its exploitation. Our techniques are based on recent work on conformal test martingales and older work on prediction with expert advice, namely tracking the best expert.
In recent years, machine learning has begun automating decision making in fields as varied as college admissions, credit lending, and criminal sentencing. The socially sensitive nature of some of these applications together with increasing regulatory constraints has necessitated the need for algorithms that are both fair and interpretable. In this paper we consider the problem of building Boolean rule sets in disjunctive normal form (DNF), an interpretable model for binary classification, subject to fairness constraints. We formulate the problem as an integer program that maximizes classification accuracy with explicit constraints on two different measures of classification parity: equality of opportunity and equalized odds. Column generation framework, with a novel formulation, is used to efficiently search over exponentially many possible rules. When combined with faster heuristics, our method can deal with large data-sets. Compared to other fair and interpretable classifiers, our method is able to find rule sets that meet stricter notions of fairness with a modest trade-off in accuracy.
Subtype Discovery consists in finding interpretable and consistent sub-parts of a dataset, which are also relevant to a certain supervised task. From a mathematical point of view, this can be defined as a clustering task driven by supervised learning in order to uncover subgroups in line with the supervised prediction. In this paper, we propose a general Expectation-Maximization ensemble framework entitled UCSL (Unsupervised Clustering driven by Supervised Learning). Our method is generic, it can integrate any clustering method and can be driven by both binary classification and regression. We propose to construct a non-linear model by merging multiple linear estimators, one per cluster. Each hyperplane is estimated so that it correctly discriminates - or predict - only one cluster. We use SVC or Logistic Regression for classification and SVR for regression. Furthermore, to perform cluster analysis within a more suitable space, we also propose a dimension-reduction algorithm that projects the data onto an orthonormal space relevant to the supervised task. We analyze the robustness and generalization capability of our algorithm using synthetic and experimental datasets. In particular, we validate its ability to identify suitable consistent sub-types by conducting a psychiatric-diseases cluster analysis with known ground-truth labels. The gain of the proposed method over previous state-of-the-art techniques is about +1.9 points in terms of balanced accuracy. Finally, we make codes and examples available in a scikit-learn-compatible Python package at https://github.com/neurospin-projects/2021_rlouiset_ucsl
In this paper, we propose a novel graph kernel method for the wireless link scheduling problem in device-to-device (D2D) networks on Riemannian manifold. The link scheduling problem can be considered as a binary classification problem since each D2D pair can only hold the state active or inactive. Our goal is to learn a novel metric that facilitates the design of an efficient but less computationally demanding machine learning (ML) solution for the binary classification task of link scheduling problem that requires no channel state information (CSI) and a fewer number of training samples as opposed to other benchmark ML algorithms. To this aim, we first represent the wireless D2D network as a graph and model the features of each D2D pair, including its communication and interference links, as regularized (i.e., positively-shifted) Laplacian matrices which are symmetric positive definite (SPD) one. By doing so, we represent the feature information of each D2D pair as a point on the SPD manifold, and we analyze the topology through Riemannian geometry. We compute the Riemannian metric, e.g., Log-Euclidean metric (LEM), which are suitable distance measures between the regularized Laplacian matrices. The LEM is then utilized to define a positive definite graph kernel for the binary classification of the link scheduling decisions. Simulation results demonstrate that the proposed graph Kernel-based method is computationally less demanding and achieves a sum rate of more than 95% of benchmark algorithm FPLinQ [1] for 10 D2D pairs without using CSI and less than a hundred training network layouts.
We consider a binary classification problem when the data comes from a mixture of two rotationally symmetric distributions satisfying concentration and anti-concentration properties enjoyed by log-concave distributions among others. We show that there exists a universal constant $C_{\mathrm{err}}>0$ such that if a pseudolabeler $\boldsymbol{\beta}_{\mathrm{pl}}$ can achieve classification error at most $C_{\mathrm{err}}$, then for any $\varepsilon>0$, an iterative self-training algorithm initialized at $\boldsymbol{\beta}_0 := \boldsymbol{\beta}_{\mathrm{pl}}$ using pseudolabels $\hat y = \mathrm{sgn}(\langle \boldsymbol{\beta}_t, \mathbf{x}\rangle)$ and using at most $\tilde O(d/\varepsilon^2)$ unlabeled examples suffices to learn the Bayes-optimal classifier up to $\varepsilon$ error, where $d$ is the ambient dimension. That is, self-training converts weak learners to strong learners using only unlabeled examples. We additionally show that by running gradient descent on the logistic loss one can obtain a pseudolabeler $\boldsymbol{\beta}_{\mathrm{pl}}$ with classification error $C_{\mathrm{err}}$ using only $O(d)$ labeled examples (i.e., independent of $\varepsilon$). Together our results imply that mixture models can be learned to within $\varepsilon$ of the Bayes-optimal accuracy using at most $O(d)$ labeled examples and $\tilde O(d/\varepsilon^2)$ unlabeled examples by way of a semi-supervised self-training algorithm.
When reasoning about strategic behavior in a machine learning context it is tempting to combine standard microfoundations of rational agents with the statistical decision theory underlying classification. In this work, we argue that a direct combination of these standard ingredients leads to brittle solution concepts of limited descriptive and prescriptive value. First, we show that rational agents with perfect information produce discontinuities in the aggregate response to a decision rule that we often do not observe empirically. Second, when any positive fraction of agents is not perfectly strategic, desirable stable points -- where the classifier is optimal for the data it entails -- cease to exist. Third, optimal decision rules under standard microfoundations maximize a measure of negative externality known as social burden within a broad class of possible assumptions about agent behavior. Recognizing these limitations we explore alternatives to standard microfoundations for binary classification. We start by describing a set of desiderata that help navigate the space of possible assumptions about how agents respond to a decision rule. In particular, we analyze a natural constraint on feature manipulations, and discuss properties that are sufficient to guarantee the robust existence of stable points. Building on these insights, we then propose the noisy response model. Inspired by smoothed analysis and empirical observations, noisy response incorporates imperfection in the agent responses, which we show mitigates the limitations of standard microfoundations. Our model retains analytical tractability, leads to more robust insights about stable points, and imposes a lower social burden at optimality.
With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video contents and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this paper, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and inter-frame inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively. The two components are designed using a novel long distance attention mechanism. The one component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves the state-of-the-art performance, and the proposed long distance attention method can effectively capture pivotal parts for face forgery.
A central goal of explainable artificial intelligence (XAI) is to improve the trust relationship in human-AI interaction. One assumption underlying research in transparent AI systems is that explanations help to better assess predictions of machine learning (ML) models, for instance by enabling humans to identify wrong predictions more efficiently. Recent empirical evidence however shows that explanations can have the opposite effect: When presenting explanations of ML predictions humans often tend to trust ML predictions even when these are wrong. Experimental evidence suggests that this effect can be attributed to how intuitive, or human, an AI or explanation appears. This effect challenges the very goal of XAI and implies that responsible usage of transparent AI methods has to consider the ability of humans to distinguish machine generated from human explanations. Here we propose a quantitative metric for XAI methods based on Turing's imitation game, a Turing Test for Transparency. A human interrogator is asked to judge whether an explanation was generated by a human or by an XAI method. Explanations of XAI methods that can not be detected by humans above chance performance in this binary classification task are passing the test. Detecting such explanations is a requirement for assessing and calibrating the trust relationship in human-AI interaction. We present experimental results on a crowd-sourced text classification task demonstrating that even for basic ML models and XAI approaches most participants were not able to differentiate human from machine generated explanations. We discuss ethical and practical implications of our results for applications of transparent ML.
With the rapid growth of renewable energy, lots of small photovoltaic (PV) prosumers emerge. Due to the uncertainty of solar power generation, there is a need for aggregated prosumers to predict solar power generation and whether solar power generation will be larger than load. This paper presents two interpretable neural networks to solve the problem: one binary classification neural network and one regression neural network. The neural networks are built using TensorFlow. The global feature importance and local feature contributions are examined by three gradient-based methods: Integrated Gradients, Expected Gradients, and DeepLIFT. Moreover, we detect abnormal cases when predictions might fail by estimating the prediction uncertainty using Bayesian neural networks. Neural networks, which are interpreted by gradient-based methods and complemented with uncertainty estimation, provide robust and explainable forecasting for decision-makers.
The literature on "benign overfitting" in overparameterized models has been mostly restricted to regression or binary classification; however, modern machine learning operates in the multiclass setting. Motivated by this discrepancy, we study benign overfitting in multiclass linear classification. Specifically, we consider the following training algorithms on separable data: (i) empirical risk minimization (ERM) with cross-entropy loss, which converges to the multiclass support vector machine (SVM) solution; (ii) ERM with least-squares loss, which converges to the min-norm interpolating (MNI) solution; and, (iii) the one-vs-all SVM classifier. First, we provide a simple sufficient deterministic condition under which all three algorithms lead to classifiers that interpolate the training data and have equal accuracy. When the data is generated from Gaussian mixtures or a multinomial logistic model, this condition holds under high enough effective overparameterization. We also show that this sufficient condition is satisfied under "neural collapse", a phenomenon that is observed in training deep neural networks. Second, we derive novel bounds on the accuracy of the MNI classifier, thereby showing that all three training algorithms lead to benign overfitting under sufficient overparameterization. Ultimately, our analysis shows that good generalization is possible for SVM solutions beyond the realm in which typical margin-based bounds apply.
We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the learner observes a sample, the adversary decides whether to corrupt the label or not. First, we show that, in a benign corruption setting (which includes the misspecification setting as a special case), with a slight enlargement on the hypothesis elimination threshold, the classical RobustCAL framework can (surprisingly) achieve nearly the same label complexity guarantee as in the non-corrupted setting. However, this algorithm can fail in the general corruption setting. To resolve this drawback, we propose a new algorithm which is provably correct without any assumptions on the presence of corruptions. Furthermore, this algorithm enjoys the minimax label complexity in the non-corrupted setting (which is achieved by RobustCAL) and only requires $\tilde{\mathcal{O}}(C_{\mathrm{total}})$ additional labels in the corrupted setting to achieve $\mathcal{O}(\varepsilon + \frac{C_{\mathrm{total}}}{n})$, where $\varepsilon$ is the target accuracy, $C_{\mathrm{total}}$ is the total number of corruptions and $n$ is the total number of unlabeled samples.
Predicting gender by the first name is not a simple task. In many applications, especially in the natural language processing (NLP) field, this task may be necessary, mainly when considering foreign names. In this paper, we examined and implemented several machine learning algorithms, such as extra trees, KNN, Naive Bayes, SVM, random forest, gradient boosting, light GBM, logistic regression, ridge classifier, and deep neural network models, such as MLP, RNN, GRU, CNN, and BiLSTM, to classify gender through the first name. A dataset of Brazilian names is used to train and evaluate the models. We analyzed the accuracy, recall, precision, f1 score, and confusion matrix to measure the models' performances. The results indicate that the gender prediction can be performed from the feature extraction strategy looking at the names as a set of strings. Some models accurately predict gender in more than 95% of the cases. The recurrent models overcome the feedforward models in this binary classification problem.
Researchers have recently started to study how the emotional speech heard by young infants can affect their developmental outcomes. As a part of this research, hundreds of hours of daylong recordings from preterm infants' audio environments were collected from two hospitals in Finland and Estonia in the context of so-called APPLE study. In order to analyze the emotional content of speech in such a massive dataset, an automatic speech emotion recognition (SER) system is required. However, there are no emotion labels or existing indomain SER systems to be used for this purpose. In this paper, we introduce this initially unannotated large-scale real-world audio dataset and describe the development of a functional SER system for the Finnish subset of the data. We explore the effectiveness of alternative state-of-the-art techniques to deploy a SER system to a new domain, comparing cross-corpus generalization, WGAN-based domain adaptation, and active learning in the task. As a result, we show that the best-performing models are able to achieve a classification performance of 73.4% unweighted average recall (UAR) and 73.2% UAR for a binary classification for valence and arousal, respectively. The results also show that active learning achieves the most consistent performance compared to the two alternatives.
In a binary classification problem where the goal is to fit an accurate predictor, the presence of corrupted labels in the training data set may create an additional challenge. However, in settings where likelihood maximization is poorly behaved-for example, if positive and negative labels are perfectly separable-then a small fraction of corrupted labels can improve performance by ensuring robustness. In this work, we establish that in such settings, corruption acts as a form of regularization, and we compute precise upper bounds on estimation error in the presence of corruptions. Our results suggest that the presence of corrupted data points is beneficial only up to a small fraction of the total sample, scaling with the square root of the sample size.
Main characters in images are the most important humans that catch the viewer's attention upon first look, and they are emphasized by properties such as size, position, color saturation, and sharpness of focus. Identifying the main character in images plays an important role in traditional photographic studies and media analysis, but the task is performed manually and can be slow and laborious. Furthermore, selection of main characters can be sometimes subjective. In this paper, we analyze the feasibility of solving the main character recognition needed for photographic studies automatically and propose a method for identifying the main characters. The proposed method uses machine learning based human pose estimation along with traditional computer vision approaches for this task. We approach the task as a binary classification problem where each detected human is classified either as a main character or not. To evaluate both the subjectivity of the task and the performance of our method, we collected a dataset of 300 varying images from multiple sources and asked five people, a photographic researcher and four other persons, to annotate the main characters. Our analysis showed a relatively high agreement between different annotators. The proposed method achieved a promising F1 score of 0.83 on the full image set and 0.96 on a subset evaluated as most clear and important cases by the photographic researcher.