all AI news
Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks. (arXiv:2008.08844v4 [cs.LG] UPDATED)
Nov. 4, 2022, 1:12 a.m. | Sitao Luan, Mingde Zhao, Chenqing Hua, Xiao-Wen Chang, Doina Precup
cs.LG updates on arXiv.org arxiv.org
The core operation of current Graph Neural Networks (GNNs) is the aggregation
enabled by the graph Laplacian or message passing, which filters the
neighborhood node information. Though effective for various tasks, in this
paper, we show that they are potentially a problematic factor underlying all
GNN methods for learning on certain datasets, as they force the node
representations similar, making the nodes gradually lose their identity and
become indistinguishable. Hence, we augment the aggregation operations with
their dual, i.e. diversification …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Vice President, AI Product Manager
@ JPMorgan Chase & Co. | New York City, United States
Binance Accelerator Program - Data Engineer
@ Binance | Asia