Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Yu, Xingtong"'
Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based applications, but their performance heavily relies on abundant labeled dat
Externí odkaz:
http://arxiv.org/abs/2408.12594
Dynamic graphs capture evolving interactions between entities, such as in social networks, online learning platforms, and crowdsourcing projects. For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream technique
Externí odkaz:
http://arxiv.org/abs/2405.13937
Given the ubiquity of graph data, it is intriguing to ask: Is it possible to train a graph foundation model on a broad range of graph data across diverse domains? A major hurdle toward this goal lies in the fact that graphs from different domains oft
Externí odkaz:
http://arxiv.org/abs/2405.13934
Autor:
Yu, Xingtong, Fang, Yuan, Liu, Zemin, Wu, Yuxia, Wen, Zhihao, Bo, Jianyuan, Zhang, Xinming, Hoi, Steven C. H.
Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily rely on the availability of ample labeled data. This constraint has spu
Externí odkaz:
http://arxiv.org/abs/2402.01440
Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised framework greatly depends on the
Externí odkaz:
http://arxiv.org/abs/2312.01878
Graphs can inherently model interconnected objects on the Web, thereby facilitating a series of Web applications, such as web analyzing and content recommendation. Recently, Graph Neural Networks (GNNs) have emerged as a mainstream technique for grap
Externí odkaz:
http://arxiv.org/abs/2312.03731
Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce labeling requirement, the "pre-train, prompt" paradigms have become increas
Externí odkaz:
http://arxiv.org/abs/2311.15317
Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in complex sc
Externí odkaz:
http://arxiv.org/abs/2311.14064
Autor:
Zhang, Wenyu, Deng, Xin, Jia, Baojun, Yu, Xingtong, Chen, Yifan, Ma, jin, Ding, Qing, Zhang, Xinming
Publikováno v:
ACM Multimedia 2023
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in t
Externí odkaz:
http://arxiv.org/abs/2309.08919
Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks(GNNs) have emerged as a powerful tool for graph representa
Externí odkaz:
http://arxiv.org/abs/2302.08043