Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Rex Ying"'
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
Graph structured data is ubiquitous in daily life and scientific areas and has attracted increasing attention. Graph Neural Networks (GNNs) have been proved to be effective in modeling graph structured data and many variants of GNN architectures have
Externí odkaz:
https://doaj.org/article/2475712d67f94864b76d1017c58d82b9
Autor:
Tailin Wu, Qinchen Wang, Yinan Zhang, Rex Ying, Kaidi Cao, Rok Sosic, Ridwan Jalali, Hassan Hamam, Marko Maucec, Jure Leskovec
Subsurface simulations use computational models to predict the flow of fluids (e.g., oil, water, gas) through porous media. These simulations are pivotal in industrial applications such as petroleum production, where fast and accurate models are need
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65398413aaf3e1d6718cc016dba895be
http://arxiv.org/abs/2206.07680
http://arxiv.org/abs/2206.07680
Publikováno v:
KDD
Abusive behavior in online retail websites and communities threatens the experience of regular community members. Such behavior often takes place within a complex, dynamic, and large-scale network of users interacting with items. Detecting abuse is c
Publikováno v:
IJCAI
Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art performance on many graph representation learning tasks. Currently, at every layer, attention is computed between connected pairs of nodes and depends solely on the repr
Publikováno v:
NAACL-HLT
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks(GNN), but these approaches are usually vulnerable to parsing errors. To bette
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac21e3d8a5b7fba70b9d7cd765c11063
http://arxiv.org/abs/2103.11794
http://arxiv.org/abs/2103.11794
Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::813ccc8ee385c1eed8bef57e10b8d38c
http://arxiv.org/abs/2101.10320
http://arxiv.org/abs/2101.10320
Autor:
Jiaqing Xie, Rex Ying
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030937355
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93210de16d3983519245e26156d8a60c
https://doi.org/10.1007/978-3-030-93736-2_19
https://doi.org/10.1007/978-3-030-93736-2_19
Publikováno v:
KDD
Graph Neural Networks (GNNs) are based on repeated aggregations of information from nodes' neighbors in a graph. However, because nodes share many neighbors, a naive implementation leads to repeated and inefficient aggregations and represents signifi
Publikováno v:
KDD
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42448ae06e26c65bcdc583b22c3547b3
Publikováno v:
SIGSPATIAL/GIS
Dynamic time warping (DTW) is a widely used curve similarity measure. We present a simple and efficient (1 + e)- approximation algorithm for DTW between a pair of point sequences, say, P and Q, each of which is sampled from a curve. We prove that the