# LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models

arXiv: https://arxiv.org/abs/2609.05955 · HTML: https://mlsanity.com/paper/2609.05955/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 43 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 30 of 38)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Combining Label Propagation and Simple Models Out-performs Graph Neural Networks](https://mlsanity.com/paper/2010.13993/) (2020)
- [Scaling Graph Neural Networks with Approximate PageRank](https://mlsanity.com/paper/2007.01570/) (2020)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Decoupling the Depth and Scope of Graph Neural Networks](https://mlsanity.com/paper/2201.07858/) (2022)
- [GFT: Graph Foundation Model with Transferable Tree Vocabulary](https://mlsanity.com/paper/2411.06070/) (2024)
- [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025)
- [Retrieval & Fine-Tuning for In-Context Tabular Models](https://mlsanity.com/paper/2406.05207/) (2024)
- [Active Learning for Graph Embedding](https://mlsanity.com/paper/1705.05085/) (2017)
- [Fully-inductive Node Classification on Arbitrary Graphs](https://mlsanity.com/paper/2405.20445/) (2024)
- [Active Learning for Graph Neural Networks via Node Feature Propagation](https://mlsanity.com/paper/1910.07567/) (2019)
- [Turning Tabular Foundation Models into Graph Foundation Models](https://mlsanity.com/paper/2508.20906/) (2025)
- [Mixture of In-Context Prompters for Tabular PFNs](https://mlsanity.com/paper/2405.16156/) (2024)
- [Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization](https://mlsanity.com/paper/2108.00219/) (2021)
- [RAGraph: A General Retrieval-Augmented Graph Learning Framework](https://mlsanity.com/paper/2410.23855/) (2024)
- [Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning](https://mlsanity.com/paper/2410.07074/) (2024)
- [GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design](https://mlsanity.com/paper/2501.15755/) (2025)
- [GraphPFN: A Prior-Data Fitted Graph Foundation Model](https://mlsanity.com/paper/2509.21489/) (2025)
- [GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data](https://mlsanity.com/paper/2409.14500/) (2024)
- [Bringing Graphs to the Table: Zero-shot Node Classification via Tabular Foundation Models](https://mlsanity.com/paper/2509.07143/) (2025)
- [Partition-Based Active Learning for Graph Neural Networks](https://mlsanity.com/paper/2201.09391/) (2022)

## Built on by (most cited first, 1 of 1)

- [Valid for Free: Homophily-Gated Conformal Prediction for Training-Free Node Classification with Tabular Foundation Models](https://mlsanity.com/paper/2610.08564/) (2026)

## Abstract (arXiv)

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.