Zobrazeno 1 - 10
of 670
pro vyhledávání: '"Huang, Edward"'
Autor:
Basu, Sabyasachi, Paul-Pena, Daniel, Qian, Kun, Seshadhri, C., Huang, Edward W, Subbian, Karthik
Graphs are a fundamental data structure used to represent relationships in domains as diverse as the social sciences, bioinformatics, cybersecurity, the Internet, and more. One of the central observations in network science is that real-world graphs
Externí odkaz:
http://arxiv.org/abs/2407.16850
Autor:
Jaiswal, Ajay, Choudhary, Nurendra, Adkathimar, Ravinarayana, Alagappan, Muthu P., Hiranandani, Gaurush, Ding, Ying, Wang, Zhangyang, Huang, Edward W, Subbian, Karthik
Graph Neural Networks (GNNs) have attracted immense attention in the past decade due to their numerous real-world applications built around graph-structured data. On the other hand, Large Language Models (LLMs) with extensive pretrained knowledge and
Externí odkaz:
http://arxiv.org/abs/2407.14996
Autor:
Tzeng, Jing-Tong, Li, Jeng-Lin, Chen, Huan-Yu, Huang, Chun-Hsiang, Chen, Chi-Hsin, Fan, Cheng-Yi, Huang, Edward Pei-Chuan, Lee, Chi-Chun
Deep learning techniques have shown promising results in the automatic classification of respiratory sounds. However, accurately distinguishing these sounds in real-world noisy conditions poses challenges for clinical deployment. Additionally, predic
Externí odkaz:
http://arxiv.org/abs/2407.13895
The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been
Externí odkaz:
http://arxiv.org/abs/2403.00923
Training Graph Neural Networks (GNNs) on real-world graphs consisting of billions of nodes and edges is quite challenging, primarily due to the substantial memory needed to store the graph and its intermediate node and edge features, and there is a p
Externí odkaz:
http://arxiv.org/abs/2308.03209
Autor:
Zhu, Jiong, Reganti, Aishwarya, Huang, Edward, Dickens, Charles, Rao, Nikhil, Subbian, Karthik, Koutra, Danai
Distributed training of GNNs enables learning on massive graphs (e.g., social and e-commerce networks) that exceed the storage and computational capacity of a single machine. To reach performance comparable to centralized training, distributed framew
Externí odkaz:
http://arxiv.org/abs/2305.09887
Link prediction is central to many real-world applications, but its performance may be hampered when the graph of interest is sparse. To alleviate issues caused by sparsity, we investigate a previously overlooked phenomenon: in many cases, a densely
Externí odkaz:
http://arxiv.org/abs/2302.14189
Although the bipartite shopping graphs are straightforward to model search behavior, they suffer from two challenges: 1) The majority of items are sporadically searched and hence have noisy/sparse query associations, leading to a \textit{long-tail} d
Externí odkaz:
http://arxiv.org/abs/2211.13328
Autor:
Hu, Weihua, Cao, Kaidi, Huang, Kexin, Huang, Edward W, Subbian, Karthik, Kawaguchi, Kenji, Leskovec, Jure
Despite recent advances in Graph Neural Networks (GNNs), their training strategies remain largely under-explored. The conventional training strategy learns over all nodes in the original graph(s) equally, which can be sub-optimal as certain nodes are
Externí odkaz:
http://arxiv.org/abs/2210.14843
Autor:
Xie, Yaochen, Katariya, Sumeet, Tang, Xianfeng, Huang, Edward, Rao, Nikhil, Subbian, Karthik, Ji, Shuiwang
Graph Neural Networks (GNNs) have emerged as powerful tools to encode graph-structured data. Due to their broad applications, there is an increasing need to develop tools to explain how GNNs make decisions given graph-structured data. Existing learni
Externí odkaz:
http://arxiv.org/abs/2202.08335