We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with homophily. However, it is a significant challenge to set personalized neighborhood sizes for different nodes. Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation. To address these problems, we propose two models GloGNN and GloGNN++, which generate a node's embedding by aggregating information from global nodes in the graph. In each layer, both models learn a coefficient matrix to capture the correlations between nodes, based on which neighborhood aggregation is performed. The coefficient matrix allows signed values and is derived from an optimization problem that has a closed-form solution. We further accelerate neighborhood aggregation and derive a linear time complexity. We theoretically explain the models' effectiveness by proving that both the coefficient matrix and the generated node embedding matrix have the desired grouping effect. We conduct extensive experiments to compare our models against 11 other competitors on 15 benchmark datasets in a wide range of domains, scales and graph heterophilies. Experimental results show that our methods achieve superior performance and are also very efficient.

In this paper, we study knowledge tracing in the domain of programming education and make two important contributions. First, we harvest and publish so far the most comprehensive dataset, namely BePKT, which covers various online behaviors in an OJ system, including programming text problems, knowledge annotations, user-submitted code and system-logged events. Second, we propose a new model PDKT to exploit the enriched context for accurate student behavior prediction. More specifically, we construct a bipartite graph for programming problem embedding, and design an improved pre-training model PLCodeBERT for code embedding, as well as a double-sequence RNN model with exponential decay attention for effective feature fusion. Experimental results on the new dataset BePKT show that our proposed model establishes state-of-the-art performance in programming knowledge tracing. In addition, we verify that our code embedding strategy based on PLCodeBERT is complementary to existing knowledge tracing models to further enhance their accuracy. As a side product, PLCodeBERT also results in better performance in other programming-related tasks such as code clone detection.

No abstract

Downburst is the main source of extreme wind speed in non-typhoon areas, which has caused a large amount of transmission line damage all over the world. In order to reveal the wind-induced vibration response characteristics of a transmission tower-line system under downburst, the nonlinear dynamic analysis of a single tower and tower-line system is carried out, and the amplification effect of tower-line coupling and fluctuating wind on the dynamic response is studied. Then, the effects of three wind field parameters closely related to the average wind profile on the wind-induced response of the tower-line system are studied. The results show that under the action of the downburst, the tower-line coupling weakens the dynamic response to a certain extent, and the dynamic amplification factor of a single tower and tower-line system is 1.1 ~ 1.3; for the self-supporting tower, when the height of the peak wind speed is close to the height of tower, the responses of the structure are more unfavorable. When the vector superposition method is used, the storm moving speed (Vt) has little effect on the wind-induced response of the tower-line system. For large-span structures such as tower-line systems, to ensure the safety of the structural design, the value of the characteristic radius (Rc) should not be too small.