Signaling proteins are an important topic in drug development due to the increased importance of finding fast, accurate and cheap methods to evaluate new molecular targets involved in specific diseases. The complexity of the protein structure hinders the direct association of the signaling activity with the molecular structure. Therefore, the proposed solution involves the use of protein star graphs for the peptide sequence information encoding into specific topological indices calculated with S2SNet tool. The Quantitative Structure - Activity Relationship classification model obtained with Machine Learning techniques is able to predict new signaling peptides. The best classification model is the first signaling prediction model, which is based on eleven descriptors and it was obtained using the Support Vector Machines - Recursive Feature Elimination (SVM-RFE) technique with the Laplacian kernel (RFE-LAP) and an AUROC of 0.961. Testing a set of 3114 proteins of unknown function from the PDB database assessed the prediction performance of the model. Important signaling pathways are presented for three UniprotIDs (34 PDBs) with a signaling prediction greater than 98.0%.

Cluster analysis or clustering is the task of dividing a set of objects in such a way that elements in the same group or cluster are more similar, according to some dissimilarity measure, than elements in different groups. To achieve this task there are two main types of algorithms: partitioning algorithms, which try to split the data into k groups that usually minimize some optimality criteria, or agglomerative algorithms, which start with single observations and merge them into clusters according to some dissimilarity measure. Such methods have been investigated in a large amount of literature, hence we refer to [12] and references therein for an overview. Clustering techniques used as unsupervised classification procedures are increasingly more influential in people's life since they are used in credit scoring, article recommendation, risk assessment, spam filtering or sentencing recommendations in courts of law, among others. Hence controlling the outcome of such procedures, in particular ensuring that some variables which should not be taken into account due to moral or legal issues are not playing a role in the classification of the observations, has become an important field of research known as fair learning. We refer to [15], [3], [1] or [9] for an overview of such legal issues and mathematical solutions to address them. For instance avoiding discrimination against sensitive characteristics such as sex, race or age can not only be achieved using the naive solution of simply ignoring such protected attribute. Indeed, if the the data at hand reflects a real world bias, machine learning algorithms can pick on this behaviour and emulate it. More precisely, suppose we have data that includes information about attributes that we know or suspect that are biased with respect to the protected class.

Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images. As we witness the wide spread adoption of these systems, it is imperative to consider the problem of unintended leakage of information from an image representation, which might compromise the privacy of the data owner. This paper investigates the problem of learning an image representation that minimizes such leakage of user information. We formulate the problem as an adversarial non-zero sum game of finding a good embedding function with two competing goals: to retain as much task dependent discriminative image information as possible, while simultaneously minimizing the amount of information, as measured by entropy, about other sensitive attributes of the user. We analyze the stability and convergence dynamics of the proposed formulation using tools from non-linear systems theory and compare to that of the corresponding adversarial zero-sum game formulation that optimizes likelihood as a measure of information content. Numerical experiments on UCI, Extended Yale B, CIFAR-10 and CIFAR-100 datasets indicate that our proposed approach is able to learn image representations that exhibit high task performance while mitigating leakage of predefined sensitive information.

Unsupervised part of speech (POS) tagging is often framed as a clustering problem, but practical taggers need to ground their clusters as well. Grounding generally requires reference labeled data, a luxury a low-resource language might not have. In this work, we describe an approach for low-resource unsupervised POS tagging that yields fully grounded output and requires no labeled training data. We find the classic method of Brown et al. (1992) clusters well in our use case and employ a decipherment-based approach to grounding. This approach presumes a sequence of cluster IDs is a'ciphertext' and seeks a POS tag-tocluster ID mapping that will reveal the POS sequence. We show intrinsically that, despite the difficulty of the task, we obtain reasonable performance across a variety of languages. We also show extrinsically that incorporating our POS tagger into a name tagger leads to stateof-the-art tagging performance in Sinhalese and Kinyarwanda, two languages with nearly no labeled POS data available. We further demonstrate our tagger's utility by incorporating Figure 1: Overview of our approach to grounded POS it into a true'zero-resource' variant of the tagging. We use an unsupervised clustering method MALOPA(Ammar et al., 2016) dependency (Section 3.2) then reduce and ground the clusters using parser model that removes the current reliance a decipherment approach informed by POS tag sequence on multilingual resources and gold POS tags data from many languages (Section 3.3).

The quest of `can machines think' and `can machines do what human do' are quests that drive the development of artificial intelligence. Although recent artificial intelligence succeeds in many data intensive applications, it still lacks the ability of learning from limited exemplars and fast generalizing to new tasks. To tackle this problem, one has to turn to machine learning, which supports the scientific study of artificial intelligence. Particularly, a machine learning problem called Few-Shot Learning (FSL) targets at this case. It can rapidly generalize to new tasks of limited supervised experience by turning to prior knowledge, which mimics human's ability to acquire knowledge from few examples through generalization and analogy. It has been seen as a test-bed for real artificial intelligence, a way to reduce laborious data gathering and computationally costly training, and antidote for rare cases learning. With extensive works on FSL emerging, we give a comprehensive survey for it. We first give the formal definition for FSL. Then we point out the core issues of FSL, which turns the problem from "how to solve FSL" to "how to deal with the core issues". Accordingly, existing works from the birth of FSL to the most recent published ones are categorized in a unified taxonomy, with thorough discussion of the pros and cons for different categories. Finally, we envision possible future directions for FSL in terms of problem setup, techniques, applications and theory, hoping to provide insights to both beginners and experienced researchers.

Policy gradient algorithms in reinforcement learning rely on efficiently sampling an environment. Most sampling procedures are based solely on sampling the agent's policy. However, other measures made available through these algorithms could be used in order to improve the sampling prior to each policy update. Following this line of thoughts, we propose a method where a transition is used in the gradient update if it meets a particular criterion, and rejected otherwise. This criterion is the fraction of variance explained ($\mathcal{V}^{ex}$), a measure of the discrepancy between a model and actual samples. $\mathcal{V}^{ex}$ can be used to evaluate the impact each transition will have on the learning. This criterion refines sampling and improves the policy gradient algorithm. In this paper: (1) We introduce and explore $\mathcal{V}^{ex}$, the selection criterion used to improve the sampling procedure. (2) We conduct experiments across a variety of standard benchmark environments, including continuous control problems. Our results show better performance than if we did not use the $\mathcal{V}^{ex}$ criterion for the policy gradient update. (3) We investigate why $\mathcal{V}^{ex}$ gives a good evaluation for the selection of samples that will positively impact the learning. (4) We show how this criterion can be interpreted as a dynamic way to adjust the ratio between exploration and exploitation.

The main approaches for node classification in graphs are information propagation and the association of the class of the node with external information. State of the art methods merge these approaches through Graph Convolutional Networks. We here use the association of topological features of the nodes with their class to predict this class. Moreover, combining topological information with information propagation improves classification accuracy on the standard CiteSeer and Cora paper classification task. Topological features and information propagation produce results almost as good as text-based classification, without no textual or content information. We propose to represent the topology and information propagation through a GCN with the neighboring training node classification as an input and the current node classification as output. Such a formalism outperforms state of the art methods.

Matrices satisfying the Restricted Isometry Property (RIP) play an important role in the areas of compressed sensing and statistical learning. RIP matrices with optimal parameters are mainly obtained via probabilistic arguments, as explicit constructions seem hard. It is therefore interesting to ask whether a fixed matrix can be incorporated into a construction of restricted isometries. In this paper, we construct a new broad ensemble of random matrices with dependent entries that satisfy the restricted isometry property. Our construction starts with a fixed (deterministic) matrix $X$ satisfying some simple stable rank condition, and we show that the matrix $XR$, where $R$ is a random matrix drawn from various popular probabilistic models (including, subgaussian, sparse, low-randomness, satisfying convex concentration property), satisfies the RIP with high probability. These theorems have various applications in signal recovery, random matrix theory, dimensionality reduction, etc. Additionally, motivated by an application for understanding the effectiveness of word vector embeddings popular in natural language processing and machine learning applications, we investigate the RIP of the matrix $XR^{(l)}$ where $R^{(l)}$ is formed by taking all possible (disregarding order) $l$-way entrywise products of the columns of a random matrix $R$.

Tree data are ubiquitous because they model a large variety of situations, e.g., the architecture of plants, the secondary structure of RNA, or the hierarchy of XML files. Nevertheless, the analysis of these non-Euclidean data is difficul per se. In this paper, we focus on the subtree kernel that is a convolution kernel for tree data introduced by Vishwanathan and Smola in the early 2000's. More precisely, we investigate the influence of the weight function from a theoretical perspective and in real data applications. We establish on a 2-classes stochastic model that the performance of the subtree kernel is improved when the weight of leaves vanishes, which motivates the definition of a new weight function, learned from the data and not fixed by the user as usually done. To this end, we define a unified framework for computing the subtree kernel from ordered or unordered trees, that is particularly suitable for tuning parameters. We show through two real data classification problems the great efficiency of our approach, in particular with respect to the ones considered in the literature, which also states the high importance of the weight function. Finally, a visualization tool of the significant features is derived.

A large portion of estimation procedures in high-dimensional statistics and machine learning have been designed based on principles and methods in continuous optimization. In this pursuit, incorporating prior knowledge on the target model, often presented as discrete and combinatorial descriptions, has been of interest in the past decade. Aside from many individual cases that have been studied in the literature, a number of general frameworks have been proposed. For example, [Bach et al., 2013, Obozinski and Bach, 2016] define sparsity-related norms and their associated optimization tools from support-based monotone set functions. On the other hand, several unifications have been proposed for the purpose of providing estimation and recovery guarantees. A et al., 2012] which connects the success ofwell-known example is the work of [Chandrasekaran norm minimization in model recovery given random linear measurements to the notion of Gaussian width [Gordon, 1988]. However, many of the final results of these frameworks (excluding discrete et al., 2013]) are quantities that are hard to compute; even evaluating theapproaches such as [Bach norm. Therefore, many a time computational aspects of these norms and their associated quantities are treated on a case by case basis. In fact, a unified framework for turning discrete descriptions into continuous tools for estimation, that 1) provides a computational suite of optimization tools, and 2) is amenable to statistical analysis, is largely underdeveloped.