Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Fu, Xingcheng"'
Autor:
Sun, Qingyun, Chen, Ziying, Yang, Beining, Ji, Cheng, Fu, Xingcheng, Zhou, Sheng, Peng, Hao, Li, Jianxin, Yu, Philip S.
Graph condensation (GC) has recently garnered considerable attention due to its ability to reduce large-scale graph datasets while preserving their essential properties. The core concept of GC is to create a smaller, more manageable graph that retain
Externí odkaz:
http://arxiv.org/abs/2407.00615
Autor:
Qin, Jiawen, Yuan, Haonan, Sun, Qingyun, Xu, Lyujin, Yuan, Jiaqi, Huang, Pengfeng, Wang, Zhaonan, Fu, Xingcheng, Peng, Hao, Li, Jianxin, Yu, Philip S.
Deep graph learning has gained grand popularity over the past years due to its versatility and success in representing graph data across a wide range of domains. However, the pervasive issue of imbalanced graph data distributions, where certain parts
Externí odkaz:
http://arxiv.org/abs/2406.09870
Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computat
Externí odkaz:
http://arxiv.org/abs/2405.03188
Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predictive abilities by exploiting th
Externí odkaz:
http://arxiv.org/abs/2402.06716
Autor:
Wei, Yuecen, Yuan, Haonan, Fu, Xingcheng, Sun, Qingyun, Peng, Hao, Li, Xianxian, Hu, Chunming
Hierarchy is an important and commonly observed topological property in real-world graphs that indicate the relationships between supervisors and subordinates or the organizational behavior of human groups. As hierarchy is introduced as a new inducti
Externí odkaz:
http://arxiv.org/abs/2312.12183
Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generati
Externí odkaz:
http://arxiv.org/abs/2311.11114
Autor:
Yang, Beining, Wang, Kai, Sun, Qingyun, Ji, Cheng, Fu, Xingcheng, Tang, Hao, You, Yang, Li, Jianxin
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns. Existing graph condensation methods primarily focus on optimizing the feature matrices of co
Externí odkaz:
http://arxiv.org/abs/2310.09192
Learning unbiased node representations for imbalanced samples in the graph has become a more remarkable and important topic. For the graph, a significant challenge is that the topological properties of the nodes (e.g., locations, roles) are unbalance
Externí odkaz:
http://arxiv.org/abs/2304.05059
Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been studied, which
Externí odkaz:
http://arxiv.org/abs/2301.12104
Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships. However, this fundamental assumption cannot always be satisfied, as real-world graphs are always incomplete,
Externí odkaz:
http://arxiv.org/abs/2301.00015