• Publications
  • Influence
Simplifying Graph Convolutional Networks
TLDR
This paper successively removes nonlinearities and collapsing weight matrices between consecutive layers, and theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier.
Efficient algorithms for Web services selection with end-to-end QoS constraints
TLDR
A broker-based architecture is designed to facilitate the selection of QoS-based services and efficient heuristic algorithms for service processes of different composition structures are presented.
Service Selection Algorithms for Composing Complex Services with Multiple QoS Constraints
TLDR
The service selection problem for complex services with only one QoS constraint is extended to multiple QoS constraints and can be modelled in two ways: the combinatorial model and the graph model.
Service Selection Algorithms for Web Services with End-to-End QoS Constraints
TLDR
This paper studies the end-to-end QoS issues of composite service by utilizing a QoS broker that is responsible for coordinating the individual service component to meet the quality constraint by modeling the problem as the multiple choice knapsack problem (MCKP) and providing efficient solutions.
Service selection algorithms for Web services with end-to-end QoS constraints
  • Tao Yu, Kwei-Jay Lin
  • Computer Science
    Proceedings. IEEE International Conference on e…
  • 1 July 2005
TLDR
This paper studies the end-to-end QoS issues of composite services by utilizing a QoS broker that is responsible for selecting and coordinating the individual service component, and proposes two solution approaches to the service selection problem: the combinatorial approach, by modeling the problem as the Multiple Choice Knapsack Problem (MCKP), and the graph approach, as the constrained shortest path problem in the graph theory.
A reputation and trust management broker framework for Web applications
This paper presents a distributed reputation and trust management framework that addresses the challenges of eliciting, evaluating and propagating reputation for Web applications. We propose a broker
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction
TLDR
In the PaMIR-based reconstruction framework, a novel deep neural network is proposed to regularize the free-form deep implicit function using the semantic features of the parametric model, which improves the generalization ability under the scenarios of challenging poses and various clothing topologies.
Exosomal circSHKBP1 promotes gastric cancer progression via regulating the miR-582-3p/HUR/VEGF axis and suppressing HSP90 degradation
TLDR
It is demonstrated that exosomal circSHKBP1 regulates the miR-582-3p/HUR/VEGF pathway, suppresses HSP90 degradation, and promotes GC progression, and is a promising circulating biomarker for GC diagnosis and prognosis and an exceptional candidate for further therapeutic exploration.
The Design of QoS Broker Algorithms for QoS-Capable Web Services
TLDR
A QoS-capable Web service architecture, QCWS, is presented by introducing a QoS broker module between service clients and providers, and studying two resource allocation algorithms used by QoS brokers acting as the front-end of servers.
Adaptive algorithms for finding replacement services in autonomic distributed business processes
  • Tao Yu, Kwei-Jay Lin
  • Computer Science
    Proceedings Autonomous Decentralized Systems…
  • 4 April 2005
TLDR
The simulation result shows that, when producing the information needed for dynamic adaptation, the running time of business process composition increases only by a constant factor regardless of the system size.
...
1
2
3
4
5
...