标签
本文提出了MS-WDRO,一个多源Wasserstein分布鲁棒图学习框架,通过Wasserstein重心融合异构源数据,并最小化最坏情况风险以实现鲁棒的图拓扑推断,在图恢复和诊断效用方面优于基线方法。
This paper applies graph signal processing to analyze how LLMs internally represent numerical sequences during in-context learning, finding that attention-induced token graphs and hidden-state signals show systematic, context-dependent signatures related to input complexity.
本文提出了一种统一的去噪扩散框架,用于条件生成图信号,引入了一种新颖的U-GNN架构,将U-Net扩展到图结构数据。该方法在股票价格预测和无线资源分配任务中得到了验证。