实体
Sanjukta Krishnagopal
Sanjukta Krishnagopal
PulseAugur coverage of Sanjukta Krishnagopal — every cluster mentioning Sanjukta Krishnagopal across labs, papers, and developer communities, ranked by signal.
总计 · 30天
2
90 天内 2
发布 · 30天
0
90 天内 0
论文 · 30天
2
90 天内 2
层级分布 · 90 天
最近 · 第 1/1 页 · 共 2 条
-
New research shows spectral graph sparsification preserves GNN representation geometry
Researchers have demonstrated that spectral graph sparsification, a technique used to simplify graph neural networks (GNNs) for faster computation, also preserves the geometric structure of learned embeddings. Their the…
-
拓扑神经切线核通过高阶结构增强图神经网络
研究人员引入了拓扑神经切线核(TopoNTK),这是一种专为单纯形消息传递设计的、超越成对关系的新型核。与传统的图核不同,TopoNTK能够捕捉单纯形复形内的高阶交互作用,使其能够感知到基于图的方法无法察觉的拓扑结构。该方法通过分解边信号并分析不同组件如何基于谱属性进行学习,从而提供更具可解释性的学习几何。