LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models
This work investigates context construction for node-level graph ICL: which labeled nodes and auxiliary unlabeled nodes should constitute the prompt for specified queries, and identifies when retrieval channels work best and connects their behavior with graph properties.
Ming-Qi Yang, Zi-Dong-Wei-Zhi-Yuan-He-Tongtang Guo, Ji-Hui Yang et al.
· 0 citations