Papers09:51
Chinese content共识伪标签学习新方法：通过类内结构调整构建差异化决策源这篇论文说伪标签共识想有效，得让模型看不同的证据。他们在 Cora、CiteSeer、PubMed 上把伪标签精度最多提了 4.39 个百分点，做图学习可以看看。
#Cora
2 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "Cora", newest first.
Oct 9
Aug 29
Cone Extended Rayleigh Quotients for Directed Graph Learning
The method improves spectral control in directed graphs while preserving predictive information, outperforming symmetrization approaches that lose directional insights.