There were two strategies for the data forwarding in the content-centric networking(CCN): forwarding strategy and routing strategy. Forwarding strategy only considered a separated node rather than the whole network pe...There were two strategies for the data forwarding in the content-centric networking(CCN): forwarding strategy and routing strategy. Forwarding strategy only considered a separated node rather than the whole network performance, and Interest flooding led to the network overhead and redundancy as well. As for routing strategy in CCN, each node was required to run the protocol. It was a waste of routing cost and unfit for large-scale deployment.This paper presents the super node routing strategy in CCN. Some super nodes selected from the peer nodes in CCN were used to receive the routing information from their slave nodes and compute the face-to-path to establish forwarding information base(FIB). Then FIB was sent to slave nodes to control and manage the slave nodes. The theoretical analysis showed that the super node routing strategy possessed robustness and scalability, achieved load balancing,reduced the redundancy and improved the network performance. In three topologies, three experiments were carried out to test the super node routing strategy. Network performance results showed that the proposed strategy had a shorter delay, lower CPU utilization and less redundancy compared with CCN.展开更多
Graph neural networks(GNNs)have demonstrated excellent performance in graph representation learning.However,as the volume of graph data grows,issues related to cost and efficiency become increasingly prominent.Graph d...Graph neural networks(GNNs)have demonstrated excellent performance in graph representation learning.However,as the volume of graph data grows,issues related to cost and efficiency become increasingly prominent.Graph distillation methods address this challenge by extracting a smaller,reduced graph,ensuring that GNNs trained on both the original and reduced graphs show similar performance.Existing methods,however,primarily optimize the feature matrix of the reduced graph and rely on correlation information from GNNs,while neglecting the original graph’s structure and redundant nodes.This often results in a loss of critical information within the reduced graph.To overcome this limitation,we propose a graph distillation method guided by network symmetry.Specifically,we identify symmetric nodes with equivalent neighborhood structures and merge them into“super nodes”,thereby simplifying the network structure,reducing redundant parameter optimization and enhancing training efficiency.At the same time,instead of relying on the original node features,we employ gradient descent to match optimal features that align with the original features,thus improving downstream task performance.Theoretically,our method guarantees that the reduced graph retains the key information present in the original graph.Extensive experiments demonstrate that our approach achieves significant improvements in graph distillation,exhibiting strong generalization capability and outperforming existing graph reduction methods.展开更多
基金Supported by the National Basic Research Program of China("973"Program,No.2013CB329100)Beijing Higher Education Young Elite Teacher Project(No.YETP0534)
文摘There were two strategies for the data forwarding in the content-centric networking(CCN): forwarding strategy and routing strategy. Forwarding strategy only considered a separated node rather than the whole network performance, and Interest flooding led to the network overhead and redundancy as well. As for routing strategy in CCN, each node was required to run the protocol. It was a waste of routing cost and unfit for large-scale deployment.This paper presents the super node routing strategy in CCN. Some super nodes selected from the peer nodes in CCN were used to receive the routing information from their slave nodes and compute the face-to-path to establish forwarding information base(FIB). Then FIB was sent to slave nodes to control and manage the slave nodes. The theoretical analysis showed that the super node routing strategy possessed robustness and scalability, achieved load balancing,reduced the redundancy and improved the network performance. In three topologies, three experiments were carried out to test the super node routing strategy. Network performance results showed that the proposed strategy had a shorter delay, lower CPU utilization and less redundancy compared with CCN.
基金Project supported by the National Natural Science Foundation of China(Grant No.62176217)the Program from the Sichuan Provincial Science and Technology,China(Grant No.2018RZ0081)the Fundamental Research Funds of China West Normal University(Grant No.17E063).
文摘Graph neural networks(GNNs)have demonstrated excellent performance in graph representation learning.However,as the volume of graph data grows,issues related to cost and efficiency become increasingly prominent.Graph distillation methods address this challenge by extracting a smaller,reduced graph,ensuring that GNNs trained on both the original and reduced graphs show similar performance.Existing methods,however,primarily optimize the feature matrix of the reduced graph and rely on correlation information from GNNs,while neglecting the original graph’s structure and redundant nodes.This often results in a loss of critical information within the reduced graph.To overcome this limitation,we propose a graph distillation method guided by network symmetry.Specifically,we identify symmetric nodes with equivalent neighborhood structures and merge them into“super nodes”,thereby simplifying the network structure,reducing redundant parameter optimization and enhancing training efficiency.At the same time,instead of relying on the original node features,we employ gradient descent to match optimal features that align with the original features,thus improving downstream task performance.Theoretically,our method guarantees that the reduced graph retains the key information present in the original graph.Extensive experiments demonstrate that our approach achieves significant improvements in graph distillation,exhibiting strong generalization capability and outperforming existing graph reduction methods.
文摘智慧城市中使用导航系统的车辆在逐渐增加。为了避免中出现密集规划而导致的某些道路负载过高而拥堵的情况,大规模路径规划近来成为了研究热点。从含有宏观连续模型中Lighthill-Whitham-Richards(LWR)模型的宏观基本图(Macroscopic Fundamental Diagram,MFD)推导得出,在城市路网环境中,使用道路负载率作为优化对象的大规模路径规划具有相较其它方案最低的时间成本。因此以LWR作为理论基础,设计负载均衡路径规划算法(Load Balancing Algorithm,LBA)。该算法以边的负载率作为评价指标,为单源查询批次Q中的每个查询找到一个最短路树。LBA构造超源节点将多源问题转化为单源问题。LBA使用网络扩张方法为可能出现的超负荷运转情况确定无拥堵路径,并使用Rtree索引的路网任意两点间最短路缓存加快算法运行速度。实验得出,与最先进算法相比在全局通行时延中减少了5.33%,CPU时间减少了54.58%。LBA在大规模路径规划场景中显著具有优越性。
