June 6, 2024, 4:43 a.m. | Haoyu Han, Juanhui Li, Wei Huang, Xianfeng Tang, Hanqing Lu, Chen Luo, Hui Liu, Jiliang Tang

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.03464v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs and a high-pass filter for heterophilic graphs. However, real-world graphs often exhibit a complex mix of homophilic and heterophilic patterns, rendering a single global filter approach suboptimal. In this work, we theoretically demonstrate that a global filter optimized for one pattern can …

abstract arxiv classification cs.lg diverse experts filter filtering global gnns graph graph neural networks graphs however low mixture of experts networks neural networks node patterns tasks type uniform wise world

Senior Data Engineer

@ Displate | Warsaw

Solution Architect

@ Philips | Bothell - B2 - Bothell 22050

Senior Product Development Engineer - Datacenter Products

@ NVIDIA | US, CA, Santa Clara

Systems Engineer - 2nd Shift (Onsite)

@ RTX | PW715: Asheville Site W Asheville Greenfield Site TBD , Asheville, NC, 28803 USA

System Test Engineers (HW & SW)

@ Novanta | Barcelona, Spain

Senior Solutions Architect, Energy

@ NVIDIA | US, TX, Remote