Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or fifinance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.

Contemporary machine learning applications often involve classification tasks with many classes. Despite their extensive use, a precise understanding of the statistical properties and behavior of classification algorithms is still missing, especially in modern regimes where the number of classes is rather large. In this paper, we take a step in this direction by providing the first asymptotically precise analysis of linear multiclass classification. Our theoretical analysis allows us to precisely characterize how the test error varies over different training algorithms, data distributions, problem dimensions as well as number of classes, inter/intra class correlations and class priors. Specifically, our analysis reveals that the classification accuracy is highly distribution-dependent with different algorithms achieving optimal performance for different data distributions and/or training/features sizes. Unlike linear regression/binary classification, the test error in multiclass classification relies on intricate functions of the trained model (e.g., correlation between some of the trained weights) whose asymptotic behavior is difficult to characterize. This challenge is already present in simple classifiers, such as those minimizing a square loss. Our novel theoretical techniques allow us to overcome some of these challenges. The insights gained may pave the way for a precise understanding of other classification algorithms beyond those studied in this paper.

Link prediction -- the process of uncovering missing links in a complex network -- is an important problem in information sciences, with applications ranging from social sciences to molecular biology. Recent advances in neural graph embeddings have proposed an end-to-end way of learning latent vector representations of nodes, with successful application in link prediction tasks. Yet, our understanding of the internal mechanisms of such approaches has been rather limited, and only very recently we have witnessed the development of a very compelling connection to the mature matrix factorization theory. In this work, we make an important contribution to our understanding of the interplay between the skip-gram powered neural graph embedding algorithms and the matrix factorization via SVD. In particular, we show that the link prediction accuracy of graph embeddings strongly depends on the transformations of the original graph co-occurrence matrix that they decompose, sometimes resulting in staggering boosts of accuracy performance on link prediction tasks. Our improved approach to learning low-rank factorization embeddings that incorporate information from unlikely pairs of nodes yields results on par with the state-of-the-art link prediction performance achieved by a complex neural graph embedding model

In this paper, we propose a rule-based engine composed of high quality and interpretable regular expressions for medical text classification. The regular expressions are auto generated by a constructive heuristic method and optimized using a Pool-based Simulated Annealing (PSA) approach. Although existing Deep Neural Network (DNN) methods present high quality performance in most Natural Language Processing (NLP) applications, the solutions are regarded as uninterpretable black boxes to humans. Therefore, rule-based methods are often introduced when interpretable solutions are needed, especially in the medical field. However, the construction of regular expressions can be extremely labor-intensive for large data sets. This research aims to reduce the manual efforts while maintaining high-quality solutions

A major challenge in the Deep RL (DRL) community is to train agents able to generalize their control policy over situations never seen in training. Training on diverse tasks has been identified as a key ingredient for good generalization, which pushed researchers towards using rich procedural task generation systems controlled through complex continuous parameter spaces. In such complex task spaces, it is essential to rely on some form of Automatic Curriculum Learning (ACL) to adapt the task sampling distribution to a given learning agent, instead of randomly sampling tasks, as many could end up being either trivial or unfeasible. Since it is hard to get prior knowledge on such task spaces, many ACL algorithms explore the task space to detect progress niches over time, a costly tabula-rasa process that needs to be performed for each new learning agents, although they might have similarities in their capabilities profiles. To address this limitation, we introduce the concept of Meta-ACL, and formalize it in the context of black-box RL learners, i.e. algorithms seeking to generalize curriculum generation to an (unknown) distribution of learners. In this work, we present AGAIN, a first instantiation of Meta-ACL, and showcase its benefits for curriculum generation over classical ACL in multiple simulated environments including procedurally generated parkour environments with learners of varying morphologies. Videos and code are available at https://sites.google.com/view/meta-acl .

Recent years have seen an increased focus into the tasks of predicting hospital inpatient risk of deterioration and trajectory evolution due to the availability of electronic patient data. A common approach to these problems involves clustering patients time-series information such as vital sign observations) to determine dissimilar subgroups of the patient population. Most clustering methods assume time-invariance of vital-signs and are unable to provide interpretability in clusters that is clinically relevant, for instance, event or outcome information. In this work, we evaluate three different clustering models on a large hospital dataset of vital-sign observations from patients suffering from Chronic Obstructive Pulmonary Disease. We further propose novel modifications to deal with unevenly sampled time-series data and unbalanced class distribution to improve phenotype separation. Lastly, we discuss further avenues of investigation for models to learn patient subgroups with distinct behaviour and phenotype.

Particle physics experiments often require the reconstruction of decay patterns through a hierarchical clustering of the observed final-state particles. We show that this task can be phrased as a Markov Decision Process and adapt reinforcement learning algorithms to solve it. In particular, we show that Monte-Carlo Tree Search guided by a neural policy can construct high-quality hierarchical clusterings and outperform established greedy and beam search baselines.

As a promising step, the performance of data analysis and feature learning are able to be improved if certain pattern matching mechanism is available. One of the feasible solutions can refer to the importance estimation of instances, and consequently, kernel mean matching (KMM) has become an important method for knowledge discovery and novelty detection in kernel machines. Furthermore, the existing KMM methods have focused on concrete learning frameworks. In this work, a novel approach to adaptive matching of kernel means is proposed, and selected data with high importance are adopted to achieve calculation efficiency with optimization. In addition, scalable learning can be conducted in proposed method as a generalized solution to matching of appended data. The experimental results on a wide variety of real-world data sets demonstrate the proposed method is able to give outstanding performance compared with several state-of-the-art methods, while calculation efficiency can be preserved.

Knowledge graphs have been demonstrated to be an effective tool for numerous intelligent applications. However, a large amount of valuable knowledge still exists implicitly in the knowledge graphs. To enrich the existing knowledge graphs, recent years witness that many algorithms for link prediction and knowledge graphs embedding have been designed to infer new facts. But most of these studies focus on the static knowledge graphs and ignore the temporal information that reflects the validity of knowledge. Developing the model for temporal knowledge graphs completion is an increasingly important task. In this paper, we build a new tensor decomposition model for temporal knowledge graphs completion inspired by the Tucker decomposition of order 4 tensor. We demonstrate that the proposed model is fully expressive and report state-of-the-art results for several public benchmarks. Additionally, we present several regularization schemes to improve the strategy and study their impact on the proposed model. Experimental studies on three temporal datasets (i.e. ICEWS2014, ICEWS2005-15, GDELT) justify our design and demonstrate that our model outperforms baselines with an explicit margin on link prediction task.

This work addresses the inverse identification of apparent elastic properties of random heterogeneous materials using machine learning based on artificial neural networks. The proposed neural network-based identification method requires the construction of a database from which an artificial neural network can be trained to learn the nonlinear relationship between the hyperparameters of a prior stochastic model of the random compliance field and some relevant quantities of interest of an ad hoc multiscale computational model. An initial database made up with input and target data is first generated from the computational model, from which a processed database is deduced by conditioning the input data with respect to the target data using the nonparametric statistics. Two-and three-layer feedforward artificial neural networks are then trained from each of the initial and processed databases to construct an algebraic representation of the nonlinear mapping between the hyperparameters (network outputs) and the quantities of interest (network inputs). The performances of the trained artificial neural networks are analyzed in terms of mean squared error, linear regression fit and probability distribution between network outputs and targets for both databases. An ad hoc probabilistic model of the input random vector is finally proposed in order to take into account uncertainties on the network input and to perform a robustness analysis of the network output with respect to the input uncertainties level. The capability of the proposed neural network-based identification method to efficiently solve the underlying statistical inverse problem is illustrated through two numerical examples developed within the framework of 2D plane stress linear elasticity, namely a first validation example on synthetic data obtained through computational simulations and a second application example on real experimental data obtained through a physical experiment monitored by digital image correlation on a real heterogeneous biological material (beef cortical bone).