Zobrazeno 1 - 10
of 36 444
pro vyhledávání: '"Structure learning"'
Autor:
Yuan, Haonan, Sun, Qingyun, Wang, Zhaonan, Fu, Xingcheng, Ji, Cheng, Wang, Yongjian, Jin, Bo, Li, Jianxin
Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks (DGNNs). Dynami
Externí odkaz:
http://arxiv.org/abs/2412.08160
Autor:
Yin, Nan
Currently, most Graph Structure Learning (GSL) methods, as a means of learning graph structure, improve the robustness of GNN merely from a local view by considering the local information related to each edge and indiscriminately applying the mechani
Externí odkaz:
http://arxiv.org/abs/2411.17062
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 11, pp. 5695-5708, Nov. 2024
Next point-of-interest (POI) recommendation aims to predict a user's next destination based on sequential check-in history and a set of POI candidates. Graph neural networks (GNNs) have demonstrated a remarkable capability in this endeavor by exploit
Externí odkaz:
http://arxiv.org/abs/2411.01169
Recent advances in differentiable structure learning have framed the combinatorial problem of learning directed acyclic graphs as a continuous optimization problem. Various aspects, including data standardization, have been studied to identify factor
Externí odkaz:
http://arxiv.org/abs/2410.18396
Graph representation learning, involving both node features and graph structures, is crucial for real-world applications but often encounters pervasive noise. State-of-the-art methods typically address noise by focusing separately on node features wi
Externí odkaz:
http://arxiv.org/abs/2410.12096
Existing approaches to differentiable structure learning of directed acyclic graphs (DAGs) rely on strong identifiability assumptions in order to guarantee that global minimizers of the acyclicity-constrained optimization problem identifies the true
Externí odkaz:
http://arxiv.org/abs/2410.06163
Causal discovery is a crucial initial step in establishing causality from empirical data and background knowledge. Numerous algorithms have been developed for this purpose. Among them, the score-matching method has demonstrated superior performance a
Externí odkaz:
http://arxiv.org/abs/2412.07469
Model-based reinforcement learning refers to a set of approaches capable of sample-efficient decision making, which create an explicit model of the environment. This model can subsequently be used for learning optimal policies. In this paper, we prop
Externí odkaz:
http://arxiv.org/abs/2411.11511
Autor:
Zheng, Yilun, Zhang, Zhuofan, Wang, Ziming, Li, Xiang, Luan, Sitao, Peng, Xiaojiang, Chen, Lihui
To improve the performance of Graph Neural Networks (GNNs), Graph Structure Learning (GSL) has been extensively applied to reconstruct or refine original graph structures, effectively addressing issues like heterophily, over-squashing, and noisy stru
Externí odkaz:
http://arxiv.org/abs/2411.07672