Zobrazeno 1 - 10
of 99
pro vyhledávání: '"Yu, Jianxiang"'
Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, GNNs lack the inherent semantic understanding capability of rich textual nodesattributes, limiting their effectiveness in applications. On
Externí odkaz:
http://arxiv.org/abs/2410.16822
The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approac
Externí odkaz:
http://arxiv.org/abs/2408.03195
Graph foundation models have recently attracted significant attention due to its strong generalizability. Although existing methods resort to language models to learn unified semantic representations across domains, they disregard the unique structur
Externí odkaz:
http://arxiv.org/abs/2407.19941
Existing methods for graph out-of-distribution (OOD) generalization primarily rely on empirical studies on synthetic datasets. Such approaches tend to overemphasize the causal relationships between invariant sub-graphs and labels, thereby neglecting
Externí odkaz:
http://arxiv.org/abs/2407.10204
Autor:
Yu, Jianxiang, Ding, Zichen, Tan, Jiaqi, Luo, Kangyang, Weng, Zhenmin, Gong, Chenghua, Zeng, Long, Cui, Renjing, Han, Chengcheng, Sun, Qiushi, Wu, Zhiyong, Lan, Yunshi, Li, Xiang
In recent years, the rapid increase in scientific papers has overwhelmed traditional review mechanisms, resulting in varying quality of publications. Although existing methods have explored the capabilities of Large Language Models (LLMs) for automat
Externí odkaz:
http://arxiv.org/abs/2407.12857
Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many r
Externí odkaz:
http://arxiv.org/abs/2401.09769
Autor:
Zhao, Yige, Yu, Jianxiang, Cheng, Yao, Yu, Chengcheng, Liu, Yiding, Li, Xiang, Wang, Shuaiqiang
Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently demonstrated excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) ignore the problems of
Externí odkaz:
http://arxiv.org/abs/2311.07929
While robust graph neural networks (GNNs) have been widely studied for graph perturbation and attack, those for label noise have received significantly less attention. Most existing methods heavily rely on the label smoothness assumption to correct n
Externí odkaz:
http://arxiv.org/abs/2311.02116
Graphs have become an important modeling tool for web applications, and Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, the performance of traditional GNNs heavily relies on a large amount of superv
Externí odkaz:
http://arxiv.org/abs/2310.10362
Text-attributed graphs have recently garnered significant attention due to their wide range of applications in web domains. Existing methodologies employ word embedding models for acquiring text representations as node features, which are subsequentl
Externí odkaz:
http://arxiv.org/abs/2310.09872