Nowadays, Graph Neural Networks (GNNs) following the Message Passing paradigm become the dominant way to learn on graphic data. Models in this paradigm have to spend extra space to look up adjacent nodes with adjacency matrices and extra time to aggregate multiple messages from adjacent nodes. To address this issue, we develop a method called LinkDist that distils self-knowledge from connected node pairs into a Multi-Layer Perceptron (MLP) without the need to aggregate messages. Experiment with 8 real-world datasets shows the MLP derived from LinkDist can predict the label of a node without knowing its adjacencies but achieve comparable accuracy against GNNs in the contexts of semi-and fullsupervised node classification. Moreover, LinkDist benefits from its Non-Message Passing paradigm that we can also distil self-knowledge from arbitrarily sampled node pairs in a contrastive way to further boost the performance of LinkDist.

Following the application of Deep Learning to graphic data, Graph Neural Networks (GNNs) have become the dominant method for Node Classification on graphs in recent years. To assign nodes with preset labels, most GNNs inherit the end-to-end way of Deep Learning in which node features are input to models while labels of pre-classified nodes are used for supervised learning. However, while these methods can make full use of node features and their associations, they treat labels separately and ignore the structural information of those labels. To utilize information on label structures, this paper proposes a method called 3ference that infers from references with differences. Specifically, 3ference predicts what label a node has according to the features of that node in concatenation with both features and labels of its relevant nodes. With the additional information on labels of relevant nodes, 3ference captures the transition pattern of labels between nodes, as subsequent analysis and visualization revealed. Experiments on a synthetic graph and seven real-world graphs proved that this knowledge about label associations helps 3ference to predict accurately with fewer parameters, fewer pre-classified nodes, and varying label patterns compared with GNNs.

Work function (WF) modulation is a crucial descriptor for carbon-based electrodes in optoelectronic, catalytic, and energy storage applications. The boron-doped graphene is envisioned as a highly promising anode material for...

CAN field-bus is a technology of serial communication network effectively supporting distributed or real time control system. This paper presents a method to design a kind of distributed control system based on CAN bus, narrates application of CAN field-bus in supervision and control system of Production Line of Power Battery, and presents the structure of the system and of the intelligent control unit. The software of the supervision and control system is based on VS2010. In addition, it introduces in particular the design of identifier in CAN field-bus and the flow of communication software.Index Terms -Production Line of Power Battery, CAN bus, distributed control system, VS2010, design of identifier.

Microgrid is profitable to mitigate the expansion pressure of transmission grid and achieve higher reliability at the same time. It also provides an ideal platform for the application of renewable energy. Network characteristics analysis is the basic element in reliability assessment of microgrid. This paper discusses two methods of microgrid construction according to China's distribution system, and constructs a microgrid based on typical 10kV distribution network. In order to analyze the topology characteristics of a microgrid, two typical kinds of matrices are used to describe the topology of microgrid, and a more common microgrid based on RBTS Bus4 System is established to illustrate four kinds of sub-network type under different conditions. Issues analyzed in this paper clear the structure difference between the microgrid and distribution network. Accordingly, the algorithms suitable to identify the characteristics of network structure in reliability analysis of microgrid are offered. The work in this paper lays a foundation for further reliability assessment of microgrid.