Graph convolution (GConv) is a widely used technique that has been demonstrated to be extremely effective for graph learning applications, most notably node categorization. On the other hand, many GConv-based models do not quantify the effect of graph topology and node features on performance, and are even surpassed by some models that do not consider graph structure or node properties. We quantify the information overlap between graph topology, node features, and labels in order to determine graph convolution's representation power in the node classification task. In this work, we first determine the linear separability of graph convoluted features using analysis of variance. Mutual information is used to acquire a better understanding of the possible non-linear relationship between graph topology, node features, and labels. Our theoretical analysis demonstrates that a simple and efficient graph operation that concatenates only graph topology and node properties consistently outperforms conventional graph convolution, especially in the heterophily case. Extensive empirical research utilizing a synthetic dataset and real-world benchmarks demonstrates that graph concatenation is a simple but more flexible alternative to graph convolution.

Federated Learning has been recently proposed for distributed model training at the edge. The principle of this approach is to aggregate models learned on distributed clients to obtain a new more general "average" model (FedAvg). The resulting model is then redistributed to clients for further training. To date, the most popular federated learning algorithm uses coordinate-wise averaging of the model parameters for aggregation. In this paper, we carry out a complete general mathematical convergence analysis to evaluate aggregation strategies in a federated learning framework. From this, we derive novel aggregation algorithms which are able to modify their model architecture by differentiating client contributions according to the value of their losses. Moreover, we go beyond the assumptions introduced in theory, by evaluating the performance of these strategies and by comparing them with the one of FedAvg in classification tasks in both the IID and the Non-IID framework without additional hypothesis.

There is recent interest in using model hubs, a collection of pre-trained models, in computer vision tasks. To utilize the model hub, we first select a source model and then adapt the model for the target to compensate for differences. While there is yet limited research on model selection and adaption for computer vision tasks, this holds even more for the field of renewable power. At the same time, it is a crucial challenge to provide forecasts for the increasing demand for power forecasts based on weather features from a numerical weather prediction. We close these gaps by conducting the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast, adopting recent results from the field of computer vision on 667 wind and photovoltaic parks. To the best of our knowledge, this makes it the most extensive study for transfer learning in renewable power forecasts reducing the computational effort and improving the forecast error. Therefore, we adopt source models based on target data from different seasons and limit the amount of training data. As an extension of the current state of the art, we utilize a Bayesian linear regression for forecasting the response based on features extracted from a neural network. This approach outperforms the baseline with only seven days of training data. We further show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach.

This report presents the open-source package which implements the series of our boosting works in the past years. In particular, the package includes mainly three lines of techniques, among which the following two are already the standard implementations in popular boosted tree platforms: (i) The histogram-based (feature-binning) approach makes the tree implementation convenient and efficient. In Li et al (2007), a simple fixed-length adaptive binning algorithm was developed. In this report, we demonstrate that such a simple algorithm is still surprisingly effective compared to more sophisticated variants in popular tree platforms. (ii) The explicit gain formula in Li (20010) for tree splitting based on second-order derivatives of the loss function typically improves, often considerably, over the first-order methods. Although the gain formula in Li (2010) was derived for logistic regression loss, it is a generic formula for loss functions with second-derivatives. For example, the open-source package also includes $L_p$ regression for $p\geq 1$. The main contribution of this package is the ABC-Boost (adaptive base class boosting) for multi-class classification. The initial work in Li (2008) derived a new set of derivatives of the classical multi-class logistic regression by specifying a "base class". The accuracy can be substantially improved if the base class is chosen properly. The major technical challenge is to design a search strategy to select the base class. The prior published works implemented an exhaustive search procedure to find the base class which is computationally too expensive. Recently, a new report (Li and Zhao, 20022) presents a unified framework of "Fast ABC-Boost" which allows users to efficiently choose the proper search space for the base class. The package provides interfaces for linux, windows, mac, matlab, R, python.

In this paper, we present a new method for few-sample supervised feature selection (FS). Our method first learns the manifold of the feature space of each class using kernels capturing multi-feature associations. Then, based on Riemannian geometry, a composite kernel is computed, extracting the differences between the learned feature associations. Finally, a FS score based on spectral analysis is proposed. Considering multi-feature associations makes our method multivariate by design. This in turn allows for the extraction of the hidden manifold underlying the features and avoids overfitting, facilitating few-sample FS. We showcase the efficacy of our method on illustrative examples and several benchmarks, where our method demonstrates higher accuracy in selecting the informative features compared to competing methods. In addition, we show that our FS leads to improved classification and better generalization when applied to test data.

In this work, we demonstrate the advantage of the pGMM (``powered generalized min-max'') kernel in the context of (ridge) regression. In recent prior studies, the pGMM kernel has been extensively evaluated for classification tasks, for logistic regression, support vector machines, as well as deep neural networks. In this paper, we provide an experimental study on ridge regression, to compare the pGMM kernel regression with the ordinary ridge linear regression as well as the RBF kernel ridge regression. Perhaps surprisingly, even without a tuning parameter (i.e., $p=1$ for the power parameter of the pGMM kernel), the pGMM kernel already performs well. Furthermore, by tuning the parameter $p$, this (deceptively simple) pGMM kernel even performs quite comparably to boosted trees. Boosting and boosted trees are very popular in machine learning practice. For regression tasks, typically, practitioners use $L_2$ boost, i.e., for minimizing the $L_2$ loss. Sometimes for the purpose of robustness, the $L_1$ boost might be a choice. In this study, we implement $L_p$ boost for $p\geq 1$ and include it in the package of ``Fast ABC-Boost''. Perhaps also surprisingly, the best performance (in terms of $L_2$ regression loss) is often attained at $p>2$, in some cases at $p\gg 2$. This phenomenon has already been demonstrated by Li et al (UAI 2010) in the context of k-nearest neighbor classification using $L_p$ distances. In summary, the implementation of $L_p$ boost provides practitioners the additional flexibility of tuning boosting algorithms for potentially achieving better accuracy in regression applications.

PyOD is one such library to detect outliers in your data. It provides access to more than 20 different algorithms to detect outliers and is compatible with both Python 2 and 3. In the case of outlier detection, the algorithm is used differently. Since we do not know the outliers in advance, KNN is used in an unsupervised learning manner. In this scenario, the algorithm finds the closest K nearest neighbors for every data point and measures the average distance.

Is artificial intelligence blurring the line between reality and fantasy? The science fantasy is becoming the science reality, "the improbable made possible" while "the impossible made probable".

We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resulting path-gradient estimators are straightforward to implement, have lower variance, and lead not only to faster convergence of training but also to better overall approximation results compared to standard total gradient estimators. We also demonstrate that path-gradient training is less susceptible to mode-collapse. In light of our results, we expect that path-gradient estimators will become the new standard method to train normalizing flows for variational inference.

Over the last decade, Neural Networks (NNs) have been widely used in numerous applications including safety-critical ones such as autonomous systems. Despite their emerging adoption, it is well known that NNs are susceptible to Adversarial Attacks. Hence, it is highly important to provide guarantees that such systems work correctly. To remedy these issues we introduce a framework for repairing unsafe NNs w.r.t. safety specification, that is by utilizing satisfiability modulo theories (SMT) solvers. Our method is able to search for a new, safe NN representation, by modifying only a few of its weight values. In addition, our technique attempts to maximize the similarity to original network with regard to its decision boundaries. We perform extensive experiments which demonstrate the capability of our proposed framework to yield safe NNs w.r.t. the Adversarial Robustness property, with only a mild loss of accuracy (in terms of similarity). Moreover, we compare our method with a naive baseline to empirically prove its effectiveness. To conclude, we provide an algorithm to automatically repair NNs given safety properties, and suggest a few heuristics to improve its computational performance. Currently, by following this approach we are capable of producing small-sized (i.e., with up to few hundreds of parameters) correct NNs, composed of the piecewise linear ReLU activation function. Nevertheless, our framework is general in the sense that it can synthesize NNs w.r.t. any decidable fragment of first-order logic specification.