Graph neural networks denote a group of neural network models introduced for the representation learning tasks on graph data specifically. Graph neural networks have been demonstrated to be effective for capturing network structure information, and the learned representations can achieve the state-of-the-art performance on node and graph classification tasks. Besides the different application scenarios, the architectures of graph neural network models also depend on the studied graph types a lot. Graph data studied in research can be generally categorized into two main types, i.e., small graphs vs. giant networks, which differ from each other a lot in the size, instance number and label annotation. Several different types of graph neural network models have been introduced for learning the representations from such different types of graphs already. In this paper, for these two different types of graph data, we will introduce the graph neural networks introduced in recent years. To be more specific, the graph neural networks introduced in this paper include IsoNN, SDBN, LF&ER, GCN, GAT, DifNN, GNL, GraphSage and seGEN. Among these graph neural network models, IsoNN, SDBN and LF&ER are initially proposed for small graphs and the remaining ones are initially proposed for giant networks instead. The readers are also suggested to refer to these papers for detailed information when reading this tutorial paper.

Gradients to activations get involved in most of the calculations during back propagation procedure of Convolution Neural Networks (CNNs) training. However, an important known observation is that the majority of these gradients are close to zero, imposing little impact on weights update. These gradients can be then pruned to achieve high gradient sparsity during CNNs training and reduce the computational cost. In particular, we randomly change a gradient to zero or a threshold value if the gradient is below the threshold which is determined by the statistical distribution of activation gradients. We also theoretically proved that the training convergence of the CNN model can be guaranteed when the above activation gradient sparsification method is applied. We evaluated our method on AlexNet, MobileNet, ResNet-{18, 34, 50, 101, 152} with CIFAR-{10, 100} and ImageNet datasets. Experimental results show that our method can substantially reduce the computational cost with negligible accuracy loss or even accuracy improvement. Finally, we analyzed the benefits that the sparsity of activation gradients introduced in detail.

The existence of adversarial examples has led to considerable uncertainty regarding the trust one can justifiably put in predictions produced by automated systems. This uncertainty has, in turn, lead to considerable research effort in understanding adversarial robustness. In this work, we take first steps towards separating robustness analysis from the choice of robustness threshold and norm. We propose robustness curves as a more general view of the robustness behavior of a model and investigate under which circumstances they can qualitatively depend on the chosen norm.

Devices comprising the Internet of Things, such as sensors and small cameras, usually have small memories and limited computational power. The proliferation of such resource-constrained devices in recent years has led to the generation of large quantities of data. These data-producing devices are appealing targets for machine learning applications but struggle to run machine learning algorithms due to their limited computing capability. They typically offload input data to external computing systems (such as cloud servers) for further processing. The results of the machine learning computations are communicated back to the resource-scarce devices, but this worsens latency, leads to increased communication costs, and adds to privacy concerns. Therefore, efforts have been made to place additional computing devices at the edge of the network, i.e close to the IoT devices where the data is generated. Deploying machine learning systems on such edge devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning has been deployed at the edge of computer networks.

Drug-Drug Interactions (DDIs) Extraction refers to the efforts to generate hand-made or automatic tools to extract embedded information from text and literature in the biomedical domain. Because of restrictions in hand-made efforts and their lower speed, Machine-Learning, or Deep-Learning approaches have become more popular for extracting DDIs. In this study, we propose a novel and generic Deep-Learning model which wraps Hierarchical Bidirectional LSTMs with two Attention Mechanisms that outperforms state-of-the-art models for DDIs Extraction, based on the DDIExtraction-2013 corpora. This model has obtained the macro F1-score of 0.785, and the precision of 0.80.

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques used to dupe classifiers in supervised learning. In contrast, this paper investigates the problem of devising optimal attacks, depending on a well-defined attacker's objective, e.g., to minimize the main agent average reward. When the policy and the system dynamics, as well as rewards, are known to the attacker, a scenario referred to as a white-box attack, designing optimal attacks amounts to solving a Markov Decision Process. For what we call black-box attacks, where neither the policy nor the system is known, optimal attacks can be trained using Reinforcement Learning techniques. Through numerical experiments, we demonstrate the efficiency of our attacks compared to existing attacks (usually based on Gradient methods). We further quantify the potential impact of attacks and establish its connection to the smoothness of the policy under attack. Smooth policies are naturally less prone to attacks (this explains why Lipschitz policies, with respect to the state, are more resilient). Finally, we show that from the main agent perspective, the system uncertainties and the attacker can be modeled as a Partially Observable Markov Decision Process. We actually demonstrate that using Reinforcement Learning techniques tailored to POMDP (e.g. using Recurrent Neural Networks) leads to more resilient policies.

Many versions of cross-validation (CV) exist in the literature; and each version though has different variants. All are used interchangeably by many practitioners; yet, without explanation to the connection or difference among them. This article has three contributions. First, it starts by mathematical formalization of these different versions and variants that estimate the error rate and the Area Under the ROC Curve (AUC) of a classification rule, to show the connection and difference among them. Second, we prove some of their properties and prove that many variants are either redundant or "not smooth". Hence, we suggest to abandon all redundant versions and variants and only keep the leave-one-out, the $K$-fold, and the repeated $K$-fold. We show that the latter is the only among the three versions that is "smooth" and hence looks mathematically like estimating the mean performance of the classification rules. However, empirically, for the known phenomenon of "weak correlation", which we explain mathematically and experimentally, it estimates both conditional and mean performance almost with the same accuracy. Third, we conclude the article with suggesting two research points that may answer the remaining question of whether we can come up with a finalist among the three estimators: (1) a comparative study, that is much more comprehensive than those available in literature and conclude no overall winner, is needed to consider a wide range of distributions, datasets, and classifiers including complex ones obtained via the recent deep learning approach. (2) we sketch the path of deriving a rigorous method for estimating the variance of the only "smooth" version, repeated $K$-fold CV, rather than those ad-hoc methods available in the literature that ignore the covariance structure among the folds of CV.

Deep learning algorithms have achieved excellent performance lately in a wide range of fields (e.g., computer version). However, a severe challenge faced by deep learning is the high dependency on hyper-parameters. The algorithm results may fluctuate dramatically under the different configuration of hyper-parameters. Addressing the above issue, this paper presents an efficient Orthogonal Array Tuning Method (OATM) for deep learning hyper-parameter tuning. We describe the OATM approach in five detailed steps and elaborate on it using two widely used deep neural network structures (Recurrent Neural Networks and Convolutional Neural Networks). The proposed method is compared to the state-of-the-art hyper-parameter tuning methods including manually (e.g., grid search and random search) and automatically (e.g., Bayesian Optimization) ones. The experiment results state that OATM can significantly save the tuning time compared to the state-of-the-art methods while preserving the satisfying performance.

Confused about renovating your space? Choosing the perfect color for your walls is always a challenging task. One does rounds of color consultation and several patch tests. This paper proposes an AI tool to pitch paint based on attributes of your room and other furniture, and visualize it on your walls. It makes the color selection process a whole lot easier. It basically takes in images of a room, detects furniture objects using YOLO object detection. Once these objects have been detected, the tool picks out color of the object. Later this object specific information gets appended to the room attributes (room_type, room_size, preferred_tone, etc) and a deep neural net is trained to make predictions for color/texture/wallpaper for the walls. Finally, these predictions are visualized on the walls from the images provided. The idea is to take the knowledge of a color consultant and pitch colors that suit the walls and provide a good contrast with the furniture and harmonize with different colors in the room. Transfer learning for YOLO object detection from the COCO dataset was used as a starting point and the weights were later fine-tuned by training on additional images. The model was trained on 1000 records listing the room and furniture attributes, to predict colors. Given the room image, this method finds the best color scheme for the walls. These predictions are then visualized on the walls in the image using image segmentation. The results are visually appealing and automatically enhance the color look-and-feel.

This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios. Graph-level representations are critical in a variety of real-world applications such as predicting the properties of molecules and community analysis in social networks. Traditional graph kernel based methods are simple, yet effective for obtaining fixed-length representations for graphs but they suffer from poor generalization due to hand-crafted designs. There are also some recent methods based on language models (e.g. graph2vec) but they tend to only consider certain substructures (e.g. subtrees) as graph representatives. Inspired by recent progress of unsupervised representation learning, in this paper we proposed a novel method called InfoGraph for learning graph-level representations. We maximize the mutual information between the graph-level representation and the representations of substructures of different scales (e.g., nodes, edges, triangles). By doing so, the graph-level representations encode aspects of the data that are shared across different scales of substructures. Furthermore, we further propose InfoGraph*, an extension of InfoGraph for semi-supervised scenarios. InfoGraph* maximizes the mutual information between unsupervised graph representations learned by InfoGraph and the representations learned by existing supervised methods. As a result, the supervised encoder learns from unlabeled data while preserving the latent semantic space favored by the current supervised task. Experimental results on the tasks of graph classification and molecular property prediction show that InfoGraph is superior to state-of-the-art baselines and InfoGraph* can achieve performance competitive with state-of-the-art semi-supervised models.