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

• URL: http://arxiv.org/abs/2609.05955v1
• Date: Sat, 05 Sep 2026 07:43:30 GMT
• Title: LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models
• Abstract summary: Current protocols employ the complete training table as context, causing attention to scale quadratically with the labeled pool and introducing preprocessing and memory bottlenecks.<n>We investigate context construction for node-level graph ICL: which labeled nodes and auxiliary unlabeled nodes should constitute the prompt for specified queries.<n>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.
• Score: 2.895347325484886
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation [10.08021023788401]
  SelfGraphRAG is a framework that generates question-answer pairs directly from knowledge graph structure and uses them to train a query-conditioned graph retriever.<n>We show that SelfGraphRAG improves retrieval precision and downstream reasoning performance over embedding-based baselines.
  arXiv  Detail & Related papers  (2026-08-25T20:18:05Z)
• COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models [19.591073105733567]
  We propose COMBA to tackle large graph learning using state space models.<n>Two key innovations: graph context gating and cross batch aggregation.<n> Experiments on benchmark networks demonstrate significant performance gains compared to baseline approaches.
  arXiv  Detail & Related papers  (2026-02-19T23:14:32Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning [47.674647127050186]
  Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data but often struggle on heterophilous graphs.<n>We propose GLANCE, a novel framework that integrates logic-guided reasoning, dynamic graph refinement, and adaptive clustering to enhance graph representation learning.
  arXiv  Detail & Related papers  (2025-07-24T15:45:26Z)
• From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs [6.0757501646966965]
  We introduce auGraph, a unified framework for task-aware graph augmentation.<n> auGraph enhances base graph structures by selectively promoting attributes into nodes.<n>It preserves the original data schema while injecting task-relevant structural signal.
  arXiv  Detail & Related papers  (2025-06-02T20:42:53Z)
• GraphGPT: Graph Instruction Tuning for Large Language Models [27.036935149004726]
  Graph Neural Networks (GNNs) have evolved to understand graph structures. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Our research tackles this by advancing graph model generalization in zero-shot learning environments.
  arXiv  Detail & Related papers  (2023-10-19T06:17:46Z)
• A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features [61.92791503017341]
  Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data. The best models for such data types in most standard supervised learning settings with IID (non-graph) data are not easily incorporated into a GNN. Here we propose a robust stacking framework that fuses graph-aware propagation with arbitrary models intended for IID data.
  arXiv  Detail & Related papers  (2022-06-16T22:46:33Z)
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels? [89.13567439679709]
  Graph Identification (GI) has long been researched in graph learning and is essential in certain applications. This paper defines a novel problem dubbed Inverse Graph Identification (IGI) We propose a simple yet effective method that makes the node-level message passing process using Graph Attention Network (GAT) under the protocol of GI.
  arXiv  Detail & Related papers  (2020-07-12T12:06:17Z)
• Iterative Context-Aware Graph Inference for Visual Dialog [126.016187323249]
  We propose a novel Context-Aware Graph (CAG) neural network. Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations.
  arXiv  Detail & Related papers  (2020-04-05T13:09:37Z)
• Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
  We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification. For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes. Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-17T02:52:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.