Graph Neural Networks(GNNs) are useful deep learning models to deal with the non-Euclid data. However, recent works show that GNNs are vulnerable to adversarial attacks. Small perturbations can lead to poor performance in many GNNs, such as Graph attention networks(GATs). Therefore, enhancing the robustness of GNNs is a critical problem. Robust GAT(RoGAT) is proposed to improve the robustness of GNNs in this paper, . Note that the original GAT uses the attention mechanism for different edges but is still sensitive to the perturbation, RoGAT adjusts the edges' weight to adjust the attention scores progressively. Firstly, RoGAT tunes the edges weight based on the assumption that the adjacent nodes should have similar nodes. Secondly, RoGAT further tunes the features to eliminate feature's noises since even for the clean graph, there exists some unreasonable data. Then, we trained the adjusted GAT model to defense the adversarial attacks. Different experiments against targeted and untargeted attacks demonstrate that RoGAT outperforms significantly than most the state-of-the-art defense methods. The implementation of RoGAT based on the DeepRobust repository for adversarial attacks.

Our visual steering interface purposed to guide analysts in the task of constructing the best performing deep neural network architecture for a given application using a one-shot search algorithm. The first section is the Lego View where the analyst can create and edit different components of a large neural network with simple drag and drop operations. An initial large neural network is treated as a super graph (shown in the Graph View) and the problem of finding the best performing neural network architecture is framed as searching for the respective subgraph in this super graph. The Graph View visualizes the super graph where each node is a block (sequence of neural network components). The One-Shot Search algorithm evaluates the subgraphs of this super graph iteratively, gauges their accuracy with regards to a test dataset and provides a fitness score for each node in the graph (Block Information view). The subgraphs are then projected as points into the scatterplot in the Search Space view and colored based on their evaluation accuracy. Analysts can filter and analyze a specific region in the subgraph search space with zoom and pan operations in the Search Space View. Finally, all blocks with high fitness scores are combined to create the best performing candidate neural network architecture. Abstract--Recent advancements in the area of deep learning have shown the effectiveness of very large neural networks in several applications. However, as these deep neural networks continue to grow in size, it becomes more and more difficult to configure their many parameters to obtain good results. Presently, analysts must experiment with many different configurations and parameter settings, which is labor-intensive and time-consuming. On the other hand, the capacity of fully automated techniques for neural network architecture search is limited without the domain knowledge of human experts.

Efficient construction of checkpoints/snapshots is a critical tool for training and diagnosing deep learning models. In this paper, we propose a lossy compression scheme for checkpoint constructions (called LC-Checkpoint). LC-Checkpoint simultaneously maximizes the compression rate and optimizes the recovery speed, under the assumption that SGD is used to train the model. LC-Checkpointuses quantization and priority promotion to store the most crucial information for SGD to recover, and then uses a Huffman coding to leverage the non-uniform distribution of the gradient scales. Our extensive experiments show that LC-Checkpoint achieves a compression rate up to $28\times$ and recovery speedup up to $5.77\times$ over a state-of-the-art algorithm (SCAR).

Semantic image segmentation is one of fastest growing areas in computer vision with a variety of applications. In many areas, such as robotics and autonomous vehicles, semantic image segmentation is crucial, since it provides the necessary context for actions to be taken based on a scene understanding at the pixel level. Moreover, the success of medical diagnosis and treatment relies on the extremely accurate understanding of the data under consideration and semantic image segmentation is one of the important tools in many cases. Recent developments in deep learning have provided a host of tools to tackle this problem efficiently and with increased accuracy. This work provides a comprehensive analysis of state-of-the-art deep learning architectures in image segmentation and, more importantly, an extensive list of techniques to achieve fast inference and computational efficiency. The origins of these techniques as well as their strengths and trade-offs are discussed with an in-depth analysis of their impact in the area. The best-performing architectures are summarized with a list of methods used to achieve these state-of-the-art results.

Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications. This paper reviews and comments on the past, present and future of normalization methods in the context of DNN training. We provide a unified picture of the main motivation behind different approaches from the perspective of optimization, and present a taxonomy for understanding the similarities and differences between them. Specifically, we decompose the pipeline of the most representative normalizing activation methods into three components: the normalization area partitioning, normalization operation and normalization representation recovery. In doing so, we provide insight for designing new normalization technique. Finally, we discuss the current progress in understanding normalization methods, and provide a comprehensive review of the applications of normalization for particular tasks, in which it can effectively solve the key issues.

The impressive performance exhibited by modern machine learning models hinges on the ability to train such models on a very large amounts of labeled data. However, since access to large volumes of labeled data is often limited or expensive, it is desirable to alleviate this bottleneck by carefully curating the training set. Optimal experimental design is a well-established paradigm for selecting data point to be labeled so to maximally inform the learning process. Unfortunately, classical theory on optimal experimental design focuses on selecting examples in order to learn underparameterized (and thus, non-interpolative) models, while modern machine learning models such as deep neural networks are overparameterized, and oftentimes are trained to be interpolative. As such, classical experimental design methods are not applicable in many modern learning setups. Indeed, the predictive performance of underparameterized models tends to be variance dominated, so classical experimental design focuses on variance reduction, while the predictive performance of overparameterized models can also be, as is shown in this paper, bias dominated or of mixed nature. In this paper we propose a design strategy that is well suited for overparameterized regression and interpolation, and we demonstrate the applicability of our method in the context of deep learning by proposing a new algorithm for single-shot deep active learning.

We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information about the targets, in a decoder-agnostic fashion. In machine learning, however, our goal is not compression but rather generalization, which is intimately linked to the predictive family or decoder of interest (e.g. linear classifier). We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. As a result, DIB gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees. Empirically, we show that the framework can be used to enforce a small generalization gap on downstream classifiers and to predict the generalization ability of neural networks.

Predicting the interaction between a compound and a target is crucial for rapid drug repurposing. Deep learning has been successfully applied in drug-target affinity (DTA) problem. However, previous deep learning-based methods ignore modeling the direct interactions between drug and protein residues. This would lead to inaccurate learning of target representation which may change due to the drug binding effects. In addition, previous DTA methods learn protein representation solely based on a small number of protein sequences in DTA datasets while neglecting the use of proteins outside of the DTA datasets. We propose GEFA (Graph Early Fusion Affinity), a novel graph-in-graph neural network with attention mechanism to address the changes in target representation because of the binding effects. Specifically, a drug is modeled as a graph of atoms, which then serves as a node in a larger graph of residues-drug complex. The resulting model is an expressive deep nested graph neural network. We also use pre-trained protein representation powered by the recent effort of learning contextualized protein representation. The experiments are conducted under different settings to evaluate scenarios such as novel drugs or targets. The results demonstrate the effectiveness of the pre-trained protein embedding and the advantages our GEFA in modeling the nested graph for drug-target interaction.

Deep learning has achieved notable success in various fields, including image and speech recognition. One of the factors in the successful performance of deep learning is its high feature extraction ability. In this study, we focus on the adaptivity of deep learning; consequently, we treat the variable exponent Besov space, which has a different smoothness depending on the input location $x$. In other words, the difficulty of the estimation is not uniform within the domain. We analyze the general approximation error of the variable exponent Besov space and the approximation and estimation errors of deep learning. We note that the improvement based on adaptivity is remarkable when the region upon which the target function has less smoothness is small and the dimension is large. Moreover, the superiority to linear estimators is shown with respect to the convergence rate of the estimation error.

Therefore, to mitigate such problems, researchers have developed state-of-the-art (SOTA) models to autodetect fake news on social media using sophisticated data science and machine learning techniques. In this work, then, we ask "what if adversaries attempt to attack such detection models?" and investigate related issues by (i) proposing a novel attack scenario against fake news detectors, in which adversaries can post malicious comments toward news articles to mislead SOTA fake news detectors, and (ii) developing Malcom, an end-to-end adversarial comment generation framework to achieve such an attack. Through a comprehensive evaluation, we demonstrate that about 94% and 93.5% of the time on average Malcom can successfully mislead five of the latest neural detection models to always output targeted real and fake news labels. Furthermore, Malcom can also fool black box fake news detectors to always output real news labels 90% of the time on average. We also compare Real Comment: admitting im not going to read this (...) our attack model with four baselines across two real-world Malcom: hes a conservative from a few months ago datasets, not only on attack performance but also on generated Prediction Change: Real News Fake News quality, coherency, transferability, and robustness. We release the source code of Malcom at https://github.com/lethaiq/MALCOM