一作NeurIPS 2026Poster
GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
Peyman Baghershahi · Fangxin Wang · Debmalya Mandal · Sourav Medya
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Peyman Baghershahi · Fangxin Wang · Debmalya Mandal · Sourav Medya
Peyman Baghershahi · Gregoire Fournier · Pranav Nyati · Sourav Medya
Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation m...
Angelo Zangari · Peyman Baghershahi · Sourav Medya
Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex relationships, creating a mismatch with the representations o...