基本信息
浏览量:74
职业迁徙
个人简介
Research summary
Graphs are ideal tools to depict relationships between discrete entities. Deep Learning on Graphs (DLG) enhances understanding of each entity by considering its interactions with other entities. As graph data continues to expand in scale and diversity, DLG algorithms are required to evolve under unprecedented constraints, such as privacy guarantees for end-users or different modalities for entities (e.g., text, images). My past and current research have focused on making DLG algorithms more :
Accurate (OSP, TPA, ANRank)
Automatic (AutoGM)
Scalable (PASS)
Privacy-enhanced (KTN, CGT)
to address this evolving data landscape. Going forward, my goal is to understand the interplay of different modalities toward developing unified approaches that can holistically address multimodal datasets with their relations.
Graphs are ideal tools to depict relationships between discrete entities. Deep Learning on Graphs (DLG) enhances understanding of each entity by considering its interactions with other entities. As graph data continues to expand in scale and diversity, DLG algorithms are required to evolve under unprecedented constraints, such as privacy guarantees for end-users or different modalities for entities (e.g., text, images). My past and current research have focused on making DLG algorithms more :
Accurate (OSP, TPA, ANRank)
Automatic (AutoGM)
Scalable (PASS)
Privacy-enhanced (KTN, CGT)
to address this evolving data landscape. Going forward, my goal is to understand the interplay of different modalities toward developing unified approaches that can holistically address multimodal datasets with their relations.
研究兴趣
论文共 21 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Rohan Kumar, Youngmin Kim, Sunitha Ravi,Haitian Sun,Christos Faloutsos,Ruslan Salakhutdinov,Minji Yoon
arxiv(2024)
引用0浏览0引用
0
0
引用1浏览0引用
1
0
CoRR (2023)
引用0浏览0EI引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn