亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Graph Neural Networks (GNNs) are powerful tools for graph representation learning. Despite their rapid development, GNNs also face some challenges, such as over-fitting, over-smoothing, and non-robustness. Previous works indicate that these problems can be alleviated by random dropping methods, which integrate augmented data into models by randomly masking parts of the input. However, some open problems of random dropping on GNNs remain to be solved. First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models. Second, augmented data introduced to GNNs causes the incomplete coverage of parameters and unstable training process. Third, there is no theoretical analysis on the effectiveness of random dropping methods on GNNs. In this paper, we propose a novel random dropping method called DropMessage, which performs dropping operations directly on the propagated messages during the message-passing process. More importantly, we find that DropMessage provides a unified framework for most existing random dropping methods, based on which we give theoretical analysis of their effectiveness. Furthermore, we elaborate the superiority of DropMessage: it stabilizes the training process by reducing sample variance; it keeps information diversity from the perspective of information theory, enabling it become a theoretical upper bound of other methods. To evaluate our proposed method, we conduct experiments that aims for multiple tasks on five public datasets and two industrial datasets with various backbone models. The experimental results show that DropMessage has the advantages of both effectiveness and generalization, and can significantly alleviate the problems mentioned above.

Safety has been recognized as the central obstacle to preventing the use of reinforcement learning (RL) for real-world applications. Different methods have been developed to deal with safety concerns in RL. However, learning reliable RL-based solutions usually require a large number of interactions with the environment. Likewise, how to improve the learning efficiency, specifically, how to utilize transfer learning for safe reinforcement learning, has not been well studied. In this work, we propose an adaptive aggregation framework for safety-critical control. Our method comprises two key techniques: 1) we learn to transfer the safety knowledge by aggregating the multiple source tasks and a target task through the attention network; 2) we separate the goal of improving task performance and reducing constraint violations by utilizing a safeguard. Experiment results demonstrate that our algorithm can achieve fewer safety violations while showing better data efficiency compared with several baselines.

The pandemic COVID-19 disease has had a dramatic impact on almost all countries around the world so that many hospitals have been overwhelmed with Covid-19 cases. As medical resources are limited, deciding on the proper allocation of these resources is a very crucial issue. Besides, uncertainty is a major factor that can affect decisions, especially in medical fields. To cope with this issue, we use fuzzy logic (FL) as one of the most suitable methods in modeling systems with high uncertainty and complexity. We intend to make use of the advantages of FL in decisions on cases that need to treat in ICU. In this study, an interval type-2 fuzzy expert system is proposed for prediction of ICU admission in COVID-19 patients. For this prediction task, we also developed an adaptive neuro-fuzzy inference system (ANFIS). Finally, the results of these fuzzy systems are compared to some well-known classification methods such as Naive Bayes (NB), Case-Based Reasoning (CBR), Decision Tree (DT), and K Nearest Neighbor (KNN). The results show that the type-2 fuzzy expert system and ANFIS models perform competitively in terms of accuracy and F-measure compared to the other system modeling techniques.

Generalized mutual information (GMI) is used to compute achievable rates for fading channels with various types of channel state information at the transmitter (CSIT) and receiver (CSIR). The GMI is based on variations of auxiliary channels with additive white Gaussian noise (AWGN). One variation is for receivers unaware of the CSIT where adaptive codewords, or Shannon strategies, achieve capacity. The GMI is then based on auxiliary channels with inputs that are linear functions of the adaptive codewords' symbols. For scalar channels, the input that maximizes the GMI is shown to give a conventional codebook but where the amplitude and phase of each symbol is modified based on the CSIT. A second variation partitions the channel output alphabet and has a different auxiliary channel for each subset of the partition. The partitioning helps to determine the capacity scaling at high signal to noise ratios. A class of power control policies is described for partial CSIR, including a truncated minimum mean square error policy for full CSIT and quadratic waterfilling if the CSIT is known at the receiver. Several examples for fading channels with AWGN illustrate the theory, with a focus on on-off fading and Rayleigh fading. The capacity results are generalized to block fading channels with in-block feedback, including capacity expressions based on mutual information and directed information.

We consider the problem of optimizing the decisions of a preemptively capable transmitter to minimize the Age of Incorrect Information (AoII) when the communication channel has a random delay. In the system, a transmitter observes a Markovian source and makes decisions based on the system status. Time is slotted and normalized. In each time slot, the transmitter decides whether to preempt or skip when the channel is busy. When the channel is idle, the transmitter decides whether to send a new update. At the other end of the channel is a receiver that estimates the state of the Markovian source based on the update it receives. We consider a generic transmission delay and assume that the transmission delay is independent and identically distributed for each update. This paper aims to optimize the transmitter's decision in each time slot to minimize the AoII with generic time penalty functions. To this end, we first use the Markov decision process to formulate the optimization problem and derive the analytical expressions of the expected AoIIs achieved by two canonical preemptive policies. Then, we prove the existence of the optimal policy and provide a feasible value iteration algorithm to approximate the optimal policy. However, the value iteration algorithm will be computationally expensive if we want considerable confidence in the approximation. Therefore, we analyze the system characteristics under two canonical delay distributions and theoretically obtain the corresponding optimal policies using the policy improvement theorem. Finally, numerical results are presented to illustrate the performance improvements brought about by the preemption capability.

We revisit the family of goodness-of-fit tests for exponentiality based on the mean residual life time proposed by Baringhaus & Henze (2008). We motivate the test statistic by a characterisation of Shanbhag (1970) and provide an alternative representation, which leads to simple and short proofs for the known theory and an easy to access covariance structure of the limiting Gaussian process under the null hypothesis. Explicit formulas for the eigenvalues and eigenfunctions of the operator associated with the limit covariance are derived using results on weighted Brownian bridges. In addition we provide further asymptotic theory under fixed alternatives and derive approximate Bahadur efficiencies, which provide an insight into the choice of the tuning parameter with regard to the power performance of the tests.

In this paper, we investigate the problem of system identification for autonomous Markov jump linear systems (MJS) with complete state observations. We propose switched least squares method for identification of MJS, show that this method is strongly consistent, and derive data-dependent and data-independent rates of convergence. In particular, our data-independent rate of convergence shows that, almost surely, the system identification error is $\mathcal{O}\big(\sqrt{\log(T)/T} \big)$ where $T$ is the time horizon. These results show that switched least squares method for MJS has the same rate of convergence as least squares method for autonomous linear systems. We derive our results by imposing a general stability assumption on the model called stability in the average sense. We show that stability in the average sense is a weaker form of stability compared to the stability assumptions commonly imposed in the literature. We present numerical examples to illustrate the performance of the proposed method.

A set $S$ of vertices of a digraph $D$ is called an open neighbourhood locating dominating set if every vertex in $D$ has an in-neighbour in $S$, and for every pair $u,v$ of vertices of $D$, there is a vertex in $S$ that is an in-neighbour of exactly one of $u$ and $v$. The smallest size of an open neighbourhood locating-dominating set of a digraph $D$ is denoted by $\gamma_{OL}(D)$. We study the class of digraphs $D$ whose only open neighbourhood locating dominating set consists of the whole set of vertices, in other words, $\gamma_{OL}(D)$ is equal to the order of $D$, which we call \emph{extremal}. By considering digraphs with loops allowed, our definition also applies to the related (and more widely studied) concept of identifying codes. Extending some previous studies from the literature for both open neighbourhood locating-dominating sets and identifying codes of both undirected and directed graphs (which all correspond to studying special classes of digraphs), we prove general structural properties of such extremal digraphs, and we describe how they can all be constructed. We then use these properties to give new proofs of several known results from the literature. We also give a recursive and constructive characterization of the extremal digraphs whose underlying undirected graph is a tree.

This paper proposes a reconciliation of two different theories of information. The first, originally proposed in a lesser-known work by Claude Shannon, describes how the information content of channels can be described qualitatively, but still abstractly, in terms of information elements, i.e. equivalence relations over the data source domain. Shannon showed that these elements form a complete lattice, with the order expressing when one element is more informative than another. In the context of security and information flow this structure has been independently rediscovered several times, and used as a foundation for reasoning about information flow. The second theory of information is Dana Scott's domain theory, a mathematical framework for giving meaning to programs as continuous functions over a particular topology. Scott's partial ordering also represents when one element is more informative than another, but in the sense of computational progress, i.e. when one element is a more defined or evolved version of another. To give a satisfactory account of information flow in programs it is necessary to consider both theories together, to understand what information is conveyed by a program viewed as a channel (\`a la Shannon) but also by the definedness of its encoding (\`a la Scott). We combine these theories by defining the Lattice of Computable Information (LoCI), a lattice of preorders rather than equivalence relations. LoCI retains the rich lattice structure of Shannon's theory, filters out elements that do not make computational sense, and refines the remaining information elements to reflect how Scott's ordering captures the way that information is presented. We show how the new theory facilitates the first general definition of termination-insensitive information flow properties, a weakened form of information flow property commonly targeted by static program analyses.

While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples. Examples involved in the consistency regularization are adaptively selected according to their potential contributions to the target task. We conduct extensive experiments on several popular benchmarks including CUB-200-2011, MIT Indoor-67, MURA, by fine-tuning the ImageNet pre-trained ResNet-50 model. Results show that our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and MixMatch. Moreover, our algorithm is orthogonal to existing methods and thus able to gain additional improvements on top of MixMatch and FixMatch. Our code is available at //github.com/SHI-Labs/Semi-Supervised-Transfer-Learning.