The Experts below are selected from a list of 25809 Experts worldwide ranked by ideXlab platform

Adele A. Rescigno - One of the best experts on this subject based on the ideXlab platform.

Magnus Jonsson - One of the best experts on this subject based on the ideXlab platform.

  • time deterministic wdm Star Network for massively parallel computing in radar systems
    Proceedings of Massively Parallel Processing Using Optical Interconnections, 1996
    Co-Authors: Magnus Jonsson, Anders Ahlander, Mikael Taveniku, Bertil Svensson
    Abstract:

    In massively parallel computer systems for embedded real-time applications there are normally very high bandwidth demands on the interconnection Network. Other important properties are time-deterministic latency and services to guarantee that deadlines are met. In this paper we analyze how these properties vary with the design parameters for a passive optical Star Network, specifically when used in a massively parallel radar signal processing system. The aggregated bandwidth and computational power of the radar system are approximately 45 Gb/s and 100 GOPS, respectively. The analysis is focused on the medium access control protocol, called TD-TWDMA, for the time and wavelength multiplexed Network. It is concluded that the proposed Network is very well suited to this kind of signal-processing applications. We also present a new distributed slot-allocation algorithm with real-time properties.

  • RTS - Dynamic time-deterministic traffic in a fiber-optic WDM Star Network
    Proceedings Ninth Euromicro Workshop on Real Time Systems, 1
    Co-Authors: Magnus Jonsson, K. Borjesson, M. Legardt
    Abstract:

    A number of protocols for WDM (Wavelength Division Multiplexing) Star Networks have been proposed. However, the area of real-time protocols for these Networks is quite unexplored. In this paper, a real-time protocol, based on TDM (Time Division Multiplexing), for a fiber-optic Star Network is presented. By the use of WDM, multiple Gb/s channels are achieved. Services for both guarantee-seeking messages and best-effort messages are supported for single destination, multicast, and broadcast transmission. Slot reservation can be used to increase the time-deterministic bandwidth, while still having an efficient bandwidth utilization due to a simple slot release method. The deterministic properties of the protocol are analyzed and simulation results presented.

Aura Ganz - One of the best experts on this subject based on the ideXlab platform.

  • INFOCOM - A time-wavelength assignment algorithm for a WDM Star Network
    [Proceedings] IEEE INFOCOM '92: The Conference on Computer Communications, 1992
    Co-Authors: Aura Ganz
    Abstract:

    The first time-wavelength assignment algorithm for wavelength division multiplexing (WDM) Star-based local and metropolitan area Networks is presented. The algorithm incorporates the unique aspects of WDM communication such as a number of tunable transmitters and receivers at each concentrator, the tuning time, and a limited number of wavelengths. The transmission duration is composed of two elements: the packet transmission time, and the overhead incurred due to the tunability of the system's transmitters and receivers. For a given traffic matrix, the algorithm obtains a TDM/WDM schedule with minimal packet transmission duration, while minimizing the tuning time. >

  • a time wavelength assignment algorithm for a wdm Star Network
    International Conference on Computer Communications, 1992
    Co-Authors: Aura Ganz, Y Gao
    Abstract:

    The first time-wavelength assignment algorithm for wavelength division multiplexing (WDM) Star-based local and metropolitan area Networks is presented. The algorithm incorporates the unique aspects of WDM communication such as a number of tunable transmitters and receivers at each concentrator, the tuning time, and a limited number of wavelengths. The transmission duration is composed of two elements: the packet transmission time, and the overhead incurred due to the tunability of the system's transmitters and receivers. For a given traffic matrix, the algorithm obtains a TDM/WDM schedule with minimal packet transmission duration, while minimizing the tuning time. >

Jia Wei Han - One of the best experts on this subject based on the ideXlab platform.

  • curriculum learning for heterogeneous Star Network embedding via deep reinforcement learning
    Web Search and Data Mining, 2018
    Co-Authors: Jian Tang, Jia Wei Han
    Abstract:

    Learning node representations for Networks has attracted much attention recently due to its effectiveness in a variety of applications. This paper focuses on learning node representations for heterogeneous Star Networks, which have a center node type linked with multiple attribute node types through different types of edges. In heterogeneous Star Networks, we observe that the training order of different types of edges affects the learning performance significantly. Therefore we study learning curricula for node representation learning in heterogeneous Star Networks, i.e., learning an optimal sequence of edges of different types for the node representation learning process. We formulate the problem as a Markov decision process, with the action as selecting a specific type of edges for learning or terminating the training process, and the state as the sequence of edge types selected so far. The reward is calculated as the performance on external tasks with node representations as features, and the goal is to take a series of actions to maximize the cumulative rewards. We propose an approach based on deep reinforcement learning for this problem. Our approach leverages LSTM models to encode states and further estimate the expected cumulative reward of each state-action pair, which essentially measures the long-term performance of different actions at each state. Experimental results on real-world heterogeneous Star Networks demonstrate the effectiveness and efficiency of our approach over competitive baseline approaches.

  • WSDM - Curriculum Learning for Heterogeneous Star Network Embedding via Deep Reinforcement Learning
    Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining - WSDM '18, 2018
    Co-Authors: Jian Tang, Jia Wei Han
    Abstract:

    Learning node representations for Networks has attracted much attention recently due to its effectiveness in a variety of applications. This paper focuses on learning node representations for heterogeneous Star Networks, which have a center node type linked with multiple attribute node types through different types of edges. In heterogeneous Star Networks, we observe that the training order of different types of edges affects the learning performance significantly. Therefore we study learning curricula for node representation learning in heterogeneous Star Networks, i.e., learning an optimal sequence of edges of different types for the node representation learning process. We formulate the problem as a Markov decision process, with the action as selecting a specific type of edges for learning or terminating the training process, and the state as the sequence of edge types selected so far. The reward is calculated as the performance on external tasks with node representations as features, and the goal is to take a series of actions to maximize the cumulative rewards. We propose an approach based on deep reinforcement learning for this problem. Our approach leverages LSTM models to encode states and further estimate the expected cumulative reward of each state-action pair, which essentially measures the long-term performance of different actions at each state. Experimental results on real-world heterogeneous Star Networks demonstrate the effectiveness and efficiency of our approach over competitive baseline approaches.

  • Ranking-based clustering of heterogeneous information Networks with Star Network schema
    Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09, 2009
    Co-Authors: Yizhou Sun, Yintao Yu, Jia Wei Han
    Abstract:

    A heterogeneous information Network is an information Network composed of multiple types of objects. Clustering on such a Network may lead to better understanding of both hidden structures of the Network and the individual role played by every object in each cluster. However, although clustering on homogeneous Networks has been studied over decades, clustering on heterogeneous Networks has not been addressed until recently. A recent study proposed a new algorithm, RankClus, for clustering on bi-typed heterogeneous Networks. However, a real-world Network may consist of more than two types, and the interactions among multi-typed objects play a key role at disclosing the rich semantics that a Network carries. In this paper, we study clustering of multi-typed heterogeneous Networks with a Star Network schema and propose a novel algorithm, NetClus, that utilizes links across multityped objects to generate high-quality net-clusters. An iterative enhancement method is developed that leads to effective ranking-based clustering in such heterogeneous Networks. Our experiments on DBLP data show that NetClus generates more accurate clustering results than the baseline topic model algorithm PLSA and the recently proposed algorithm, RankClus. Further, NetClus generates informative clusters, presenting good ranking and cluster membership information for each attribute object in each net-cluster.

Bertil Svensson - One of the best experts on this subject based on the ideXlab platform.

  • time deterministic wdm Star Network for massively parallel computing in radar systems
    Proceedings of Massively Parallel Processing Using Optical Interconnections, 1996
    Co-Authors: Magnus Jonsson, Anders Ahlander, Mikael Taveniku, Bertil Svensson
    Abstract:

    In massively parallel computer systems for embedded real-time applications there are normally very high bandwidth demands on the interconnection Network. Other important properties are time-deterministic latency and services to guarantee that deadlines are met. In this paper we analyze how these properties vary with the design parameters for a passive optical Star Network, specifically when used in a massively parallel radar signal processing system. The aggregated bandwidth and computational power of the radar system are approximately 45 Gb/s and 100 GOPS, respectively. The analysis is focused on the medium access control protocol, called TD-TWDMA, for the time and wavelength multiplexed Network. It is concluded that the proposed Network is very well suited to this kind of signal-processing applications. We also present a new distributed slot-allocation algorithm with real-time properties.