Machine Learning is one of the most sought after skills these days. If you are a data scientist, then you need to be good at Machine Learning – no two ways about it. As part of DataFest 2017, we organized various skill tests so that data scientists can assess themselves on these critical skills. These tests included Machine Learning, Deep Learning, Time Series problems and Probability. This article will lay out the solutions to the machine learning skill test. If you missed out on any of the above skill tests, you can still check out the questions and answers through the articles linked above. In Machine Learning skill test, more than 1350 people registered for the test.

Knowledge graphs (KGs) model facts about the world, they consist of nodes (entities such as companies and people) that are connected by edges (relations such as founderOf). Facts encoded in KGs are frequently used by search applications to augment result pages. When presenting a KG fact to the user, providing other facts that are pertinent to that main fact can enrich the user experience and support exploratory information needs. KG fact contextualization is the task of augmenting a given KG fact with additional and useful KG facts. The task is challenging because of the large size of KGs, discovering other relevant facts even in a small neighborhood of the given fact results in an enormous amount of candidates. We introduce a neural fact contextualization method (NFCM) to address the KG fact contextualization task. NFCM first generates a set of candidate facts in the neighborhood of a given fact and then ranks the candidate facts using a supervised learning to rank model. The ranking model combines features that we automatically learn from data and that represent the query-candidate facts with a set of hand-crafted features we devised or adjusted for this task. In order to obtain the annotations required to train the learning to rank model at scale, we generate training data automatically using distant supervision on a large entity-tagged text corpus. We show that ranking functions learned on this data are effective at contextualizing KG facts. Evaluation using human assessors shows that it significantly outperforms several competitive baselines.

We analyze Gradient Descent applied to learning a bounded target function on $n$ real-valued inputs by training a neural network with a single hidden layer of nonlinear gates. Our main finding is that GD starting from a randomly initialized network converges in mean squared loss to the minimum error (in 2-norm) of the best approximation of the target function using a polynomial of degree at most $k$. Moreover, the size of the network and number of iterations needed are both bounded by $n^{O(k)}$. The core of our analysis is the following existence theorem, which is of independent interest: for any $\epsilon > 0$, any bounded function that has a degree-$k$ polynomial approximation with error $\epsilon_0$ (in 2-norm), can be approximated to within error $\epsilon_0 + \epsilon$ as a linear combination of $n^{O(k)} \mbox{poly}(1/\epsilon)$ randomly chosen gates from any class of gates whose corresponding activation function has nonzero coefficients in its harmonic expansion for degrees up to $k$. In particular, this applies to training networks of unbiased sigmoids and ReLUs.

We study the problem of efficient PAC active learning of homogeneous linear classifiers (halfspaces) in $\mathbb{R}^d$, where the goal is to learn a halfspace with low error, using as few label queries as possible. Given the extra assumption that there is a $t$-sparse halfspace that performs well on the data ($t \ll d$), we would like our active learning algorithm to be {\em attribute efficient}, i.e. to have label requirements sublinear in $d$. In this paper, we provide a computationally efficient algorithm that achieves this goal. Under certain distributional assumptions on the data, our algorithm achieves a label complexity of $O(t \mathrm{polylog}(d, \frac 1 \epsilon))$. In contrast, existing algorithms in this setting are either computationally inefficient, or subject to label requirements polynomial in $d$ or $\frac 1 \epsilon$.

Region-based classification of PolSAR data can be effectively performed by seeking for the assignment that minimizes a distance between prototypes and segments. Silva et al (2013) used stochastic distances between complex multivariate Wishart models which, differently from other measures, are computationally tractable. In this work we assess the robustness of such approach with respect to errors in the training stage, and propose an extension that alleviates such problems. We introduce robustness in the process by incorporating a combination of radial basis kernel functions and stochastic distances with Support Vector Machines (SVM). We consider several stochastic distances between Wishart: Bhatacharyya, Kullback-Leibler, Chi-Square, R\'{e}nyi, and Hellinger. We perform two case studies with PolSAR images, both simulated and from actual sensors, and different classification scenarios to compare the performance of Minimum Distance and SVM classification frameworks. With this, we model the situation of imperfect training samples. We show that SVM with the proposed kernel functions achieves better performance with respect to Minimum Distance, at the expense of more computational resources and the need of parameter tuning. Code and data are provided for reproducibility.

In online question-and-answer (QA) websites like Quora, one central issue is to find (invite) users who are able to provide answers to a given question and at the same time would be unlikely to say "no" to the invitation. The challenge is how to trade off the matching degree between users' expertise and the question topic, and the likelihood of positive response from the invited users. In this paper, we formally formulate the problem and develop a weakly supervised factor graph (WeakFG) model to address the problem. The model explicitly captures expertise matching degree between questions and users. To model the likelihood that an invited user is willing to answer a specific question, we incorporate a set of correlations based on social identity theory into the WeakFG model. We use two different genres of datasets: QA-Expert and Paper-Reviewer, to validate the proposed model. Our experimental results show that the proposed model can significantly outperform (+1.5-10.7% by MAP) the state-of-the-art algorithms for matching users (experts) with community questions. We have also developed an online system to further demonstrate the advantages of the proposed method.

Complex networks are often categorized according to the underlying phenomena that they represent such as molecular interactions, re-tweets, and brain activity. In this work, we investigate the problem of predicting the category (domain) of arbitrary networks. This includes complex networks from different domains as well as synthetically generated graphs from five different network models. A classification accuracy of $96.6\%$ is achieved using a random forest classifier with both real and synthetic networks. This work makes two important findings. First, our results indicate that complex networks from various domains have distinct structural properties that allow us to predict with high accuracy the category of a new previously unseen network. Second, synthetic graphs are trivial to classify as the classification model can predict with near-certainty the network model used to generate it. Overall, the results demonstrate that networks drawn from different domains (and network models) are trivial to distinguish using only a handful of simple structural properties.

In this paper we introduce a significant improvement to the popular tree-based Stochastic Gradient Boosting algorithm using a wavelet decomposition of the trees. This approach is based on harmonic analysis and approximation theoretical elements, and as we show through extensive experimentation, our wavelet based method generally outperforms existing methods, particularly in difficult scenarios of class unbalance and mislabeling in the training data.

Network embedding has attracted considerable research attention recently. However, the existing methods are incapable of handling billion-scale networks, because they are computationally expensive and, at the same time, difficult to be accelerated by distributed computing schemes. To address these problems, we propose RandNE, a novel and simple billion-scale network embedding method. Specifically, we propose a Gaussian random projection approach to map the network into a low-dimensional embedding space while preserving the high-order proximities between nodes. To reduce the time complexity, we design an iterative projection procedure to avoid the explicit calculation of the high-order proximities. Theoretical analysis shows that our method is extremely efficient, and friendly to distributed computing schemes without any communication cost in the calculation. We demonstrate the efficacy of RandNE over state-of-the-art methods in network reconstruction and link prediction tasks on multiple datasets with different scales, ranging from thousands to billions of nodes and edges.

We discuss the development of novel deep learning algorithms to enable real-time regression analysis for time series data. We showcase the application of this new method with a timely case study, and then discuss the applicability of this approach to tackle similar challenges across science domains.