Search

Graph Convolutional Networks (GCNs) have been widely used due to their outstanding performance in processing graph-structured data. However, the undirected graphs limit their application scope. In this paper, we extend spectral-based graph convolution to directed graphs by using first- and second-order proximity, which can not only retain the connection properties of the directed graph, but also expand the receptive field of the convolution operation. A new GCN model, called DGCN, is then designed to learn representations on the directed graph, leveraging both the first- and second-order proximity information. We empirically show the fact that GCNs working only with DGCNs can encode more useful information from graph and help achieve better performance when generalized to other models. Moreover, extensive experiments on citation networks and co-purchase datasets demonstrate the superiority of our model against the state-of-the-art methods.

Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations. We also show that local temporal dependencies can be retained and are globally consistent in the resulting interval network. Moreover, network structure can be learned from empirical data. A new dataset of complex hand activities has been constructed and made publicly available, which is much larger in size than any existing datasets. Empirical evaluations on benchmark datasets as well as our in-house dataset demonstrate the competitiveness of our approach.

There is increasing interest in having software systems execute and interoperate over the Internet. Execution and interoperation at this scale imply a degree of loose coupling and heterogeneity among the components from which such systems will be built. One common approach to designing distributed, loosely-coupled, heterogeneous software systems is a structure based on event generation, observation and notification. The technology to support this approach is well-developed for local area -networks, but it is ill-suited to networks on the scale of the Internet. Hence, new technologies are needed to suppoort the construction of large-scale, event-based software systems for the Internet. We have begun to design a new facility for event observation and notification that better serves the needs of Internet-scale applications. In this paper we present results from our first step in this design process, in which we defined a framework that captures many of the relevant design dimensions. Our framework comprises seven models - an object model, an event model, a naming model, an observation model, a time model, a notification model, and a resource model. The paper discusses each of these models in detail and illustrates them using an example involving an update to a Web page. The paper also evaluates three existing technologies with respect to the seven models.

The majority of existing probabilistic model checking case studies are based on well understood theoretical models and distributions. However, real-life probabilistic systems usually involve distribution parameters whose values are obtained by empirical measurements and thus are subject to small perturbations. In this paper, we consider perturbation analysis of reachability in the parametric models of these systems (i.e., parametric Markov chains) equipped with the norm of absolute distance. Our main contribution is a method to compute the asymptotic bounds in the form of condition numbers for constrained reachability probabilities against perturbations of the distribution parameters of the system. The adequacy of the method is demonstrated through experiments with the Zeroconf protocol and the hopping frog problem., Comment: This paper is a long version of the paper Asymptotic Bounds for Quantitative Verification of Perturbed Probabilistic Systems in the proceedings of 15th International Conference on Formal Engineering Methods

Components have increasingly become the unit of development of software. In industry, there has been considerable work in the development of standard component interoperability models, such as ActiveX, CORBA and JavaBeans. In academia, there has been intensive research in developing a notion of software architecture. Both of these efforts use software components as the basic building blocks, and both address concerns of structure and reuse. With component interoperability models, the focus is on specifying interfaces, binding mechanisms, packaging, inter-component communication protocols, and expectations regarding the runtime environment. With software architecture, the focus is on specifying systems of communicating components, analyzing system properties, and generating "glue" code that binds system components. Our research involves studying how standard component models can be extended to accommodate important issues of architecture, including a notion of architectural style and support for explicit connectors. For our initial effort in this work, we have enhanced the JavaBeans component model to support component composition according to the C2 architectural style. Our approach enables the design and development of applications in the C2 style using off-the-shelf Java components or "beans" that are available to the designer. In this paper, we describe the techniques underlying our approach, and we identify the important issues that surface when attempting this type of extension.

An increasing number of mission-critical software systems require dependability, robustness, adaptability, and continuous availability. Self-adaptive software strives to fulfill these requirements. Self-adaptive software requires the simultaneous management of two related processes—system evolution, the consistent and reasoned application of change over time, and system adaptation, the cycle of detecting changing circumstances, planning responsive modifications, and deploying those modifications to field sites. We indicate how these two processes can be combined and coordinated in an infrastructure that supports ongoing continuous system change without requiring any downtime, rebuilds, or system restarts—all the while guaranteeing system integrity. Central to our methodology is the dominant role of software architectures in planning, coordinating, monitoring, evaluating, and implementing software adaptation. We argue that explicit system structure and representation, the separation of architecture from implementation, and the separation of communication from computation are scalable abstractions suitable for domains and adaptations of all sizes.

Software architectures are software system models that represent the design of a system at a high level of abstraction. A software architecture typically focuses on the coarse-grained organization of functionality into components and on the explicit representation and specification of inter-component communication. A notable feature of many architectural models (and the languages used to express them) is their representation of communication concerns in explicit model elements, which are typically called connectors. However, there is little consensus yet in the software engineering community on the role of connectors in an architectural model, or even on the necessity of making them first-class model elements. In this paper we demonstrate the utility of explicit connectors in architectural models through a presentation and analysis of an architecture for a meeting scheduler system. We show how the functional abstraction provided by connectors contributes to the mobility, distribution and extensibility of the design, as well as its ability to sustain run time structural change. Furthermore, we demonstrate how connectors encapsulate important aspects of inter-component communication, including the number and identity of communication recipients, the policy used to select these recipients, the choice of implementation technology for the communications, and architectural constraints on component composition.

Software architecture descriptions are high-level models of software systems. Some researchers have proposed special-purpose architectural notations that have a great deal of expressive power but are not well integrated with common development methods. Others have used mainstream development methods that are accessible to developers, but lack semantics needed for extensive analysis. We describe an approach to combining the advantages of these two ways of modeling architectures. We present two examples of extending UML, an emerging standard design notation, for use with two architecture description languages, C2 and Wright. Our approach suggests a practical strategy for bringing architectural modeling into wider use, namely by incorporating substantial elements of architectural models into a standard design method.