Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links. The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph. Recently, one of the most exciting advancements in deep learning is the attention mechanism, whose great potential has been well demonstrated in various areas. In this paper, we first propose a novel heterogeneous graph neural network based on the hierarchical attention, including node-level and semantic-level attentions. Specifically, the node-level attention aims to learn the importance between a node and its metapath based neighbors, while the semantic-level attention is able to learn the importance of different meta-paths. With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered. Then the proposed model can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner. Extensive experimental results on three real-world heterogeneous graphs not only show the superior performance of our proposed model over the state-of-the-arts, but also demonstrate its potentially good interpretability for graph analysis.

No abstract

No abstract

Mass spectrometry has become a powerful tool in the field of biomedicine. The combination of ambient ionization and miniature mass spectrometry systems could most likely fulfill a significant need in medical diagnostics, providing highly specific molecular information in real time for clinical and even point-of-care analysis. In this review, we discuss the recent development of ambient ionization and miniature mass spectrometers as well as their potential in disease diagnosis and therapeutic monitoring, with an emphasis on their capability in analysis of biofluids and tissues. We also speculate the future development of the integrated, miniature MS systems and provide our perspectives on the challenges in technical development as well as possible solutions for path forward.

No abstract

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. This work provides a solution to hardening DNNs under adversarial attacks through defensive dropout. Besides using dropout during training for the best test accuracy, we propose to use dropout also at test time to achieve strong defense effects. We consider the problem of building robust DNNs as an attacker-defender two-player game, where the attacker and the defender know each others' strategies and try to optimize their own strategies towards an equilibrium. Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker's strategy for generating adversarial examples. We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout. Comparing with stochastic activation pruning (SAP), another defense method through introducing randomness into the DNN model, we find that our defensive dropout achieves much larger variances of the gradients, which is the key for the improved defense effects (much lower attack success rate). For example, our defensive dropout can reduce the attack success rate from 100% to 13.89% under the currently strongest attack i.e., C&W attack on MNIST dataset. arXiv:1809.05165v1 [cs.CR]

Abstract-Nonnegative matrix factorization (NMF), a method for finding parts-based representation of nonnegative data, has shown remarkable competitiveness in data analysis. Given that real-world datasets are often comprised of multiple features or views which describe data from various perspectives, it is important to exploit diversity from multiple views for comprehensive and accurate data representations. Moreover, real-world datasets often come with high-dimensional features, which demands the efficiency of low-dimensional representation learning approaches. To address these needs, we propose a Diverse Nonnegative Matrix Factorization (DiNMF) approach. It enhances the diversity, reduces the redundancy among multi-view representations with a novel defined diversity term and enables the learning process in linear execution time. We further propose a Locality Preserved DiNMF (LP-DiNMF) for more accurate learning, which ensures diversity from multiple views while preserving the local geometry structure of data in each view. Efficient iterative updating algorithms are derived for both DiNMF and LP-DiNMF, along with proofs of convergence. Experiments on synthetic and realworld datasets have demonstrated the efficiency and accuracy of the proposed methods against the state-of-the-art approaches, proving the advantages of incorporating the proposed diversity term into NMF.

Abstract. Network coordinate (NC) system allows efficient Internet distance prediction with scalable measurements. Most of the NC systems are based on embedding hosts into a low dimensional Euclidean space. Unfortunately, the accuracy of predicted distances is largely hurt by the persistent occurrence of Triangle Inequality Violation (TIV) in measured Internet distances. IDES is a dot product based NC system which can tolerate the constraints of TIVs. However, it cannot guarantee the predicted distance non-negative and its prediction accuracy is close to the Euclidean distance based NC systems. In this paper, we propose Phoenix, an accurate, practical and decentralized NC system. It adopts a weighted model adjustment to achieve better prediction accuracy while it ensures the predicted distances to be positive and usable. Our extensive Internet trace based simulation shows that Phoenix can achieve higher prediction accuracy than other representative NC systems. Furthermore, Phoenix has fast convergence and robustness over measurement anomalies.