Metraipolis › archive › dc_d92eee270eb8
LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models — arXiv:2609.05955
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05955
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:56:27.987Z
- SHA-256 of the archived text
0ee92bedcf2dcac72aba933406ee67ab84bbcd217a7644ee41b2a336eb499b4e- Stable URL of this page
https://metraipolis.com/documento/dc_d92eee270eb8
How to cite
LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models — arXiv:2609.05955 — arXiv (en), https://arxiv.org/abs/2609.05955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d92eee270eb8 (Metraipolis archive dc_d92eee270eb8, sha256 0ee92bedcf2dcac72aba933406ee67ab84bbcd217a7644ee41b2a336eb499b4e)
BibTeX
@misc{dcd92eee270eb8,
title = {LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models — arXiv:2609.05955},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05955},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d92eee270eb8; sha256 0ee92bedcf2dcac72aba933406ee67ab84bbcd217a7644ee41b2a336eb499b4e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tabular foundation models have become powerful graph learners. Systems such as G2T-FM and GraphPFN encode each node as a feature row and make predictions through in-context learning (ICL), with labeled rows serving as the prompt. Current protocols employ the complete training table as context, causing attention to scale quadratically with the labeled pool and introducing preprocessing and memory bottlenecks. We investigate context construction for node-level graph ICL: which labeled nodes and auxiliary unlabeled nodes should constitute the prompt for specified queries. We formulate this allocation in terms of two resources: a labeled-context budget for predictive evidence and an unlabeled-halo budget for adapter message passing without using label capacity. We present LoGIC, which retrieves labeled nodes via structural, feature-based, and coverage channels, shares each context across the queries in a graph-local cluster, incorporates an unlabeled halo for adapter backbones, and chooses the channel and context budget without test labels. Across three backbone configurations drawn from two model families on GraphLand, budgeted contexts maintain locally runnable full-context performance, stay competitive with published large-dataset results, and markedly lower peak memory requirements compared with full-context and whole-graph inference. They further permit frozen graph ICL on million-node graphs without retraining. Our analysis identifies when retrieval channels work best and connects their behavior with graph properties. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.05955 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:39:42.827Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).