TACO-Graph: Automated Construction of Text-Atributed Graphs

Amiri Hayes; Kristina Wicke

cs.LGOct 27, 2026

TACO-Graph: Automated Construction of Text-Atributed Graphs

Authors: Amiri Hayes, Kristina Wicke

Organizations: MIT CSAIL · New Jersey Institute of Technology

Abstract

Graph-structured representations of text data have become foundational across machine learning, yet it remains unclear how to systematically construct a graph from a given dataset for a target task. Choices about which entities become nodes, which relationships become edges, and what text each node contains can substantially affect downstream performance. In practice, finding optimal constructions often requires expert knowledge or manual trial and error. We introduce TACO-Graph, a decision tree framework for learning which graph construction choices are most effective for a given dataset and task. Specifically, we focus on text-attributed graphs (TAGs) constructed from multi-attribute tabular data. TACO-Graph enumerates valid TAG representations, scores each using fast proxy evaluation on small representative subsets, and trains an interpretable decision tree on those scores. Across five datasets spanning citation networks, product reviews, and bibliographic relationships, our decision trees predict construction quality on separately drawn evaluation samples with mean Spearman $ρ$ above $0.9$ for node classification and above $0.8$ for GraphRAG retrieval. Our trees systematically identify which constructions perform better across both GNN and GraphRAG tasks, and the full pipeline is released as an open-source library to support evaluation on new tasks and datasets at https://github.com/AmiriHayes/text_attributed_graphs. TACO-Graph provides a systematic and interpretable guide for determining how to convert tabular data to text-attributed graphs for downstream tasks.

Figures & tables

Figure 1: Overview of TACO-Graph. (1) A relational dataset’s columns are mapped to a generalized schema and characterized using automated statistical and validity checks. These dataset level properties are stored for each dataset, and train/test subsets are sampled. (2) For a specified downstream task, TACO-Graph enumerates the space of potential TAG constructions (variants) by defining node, edge, and text-fidelity choices. (3) Each construction is evaluated on representative subsamples by scoring (via lightweight GNN or small-sample GraphRAG), yielding

\mathrm{Score}(\mathrm{variant},\mathrm{subsample})

. (4) A decision tree is fit to variant construction scores and validated on separately drawn data using Spearman correlation and tree edit distance. (5) The interpretable ranking from the tree reveals optimal and suboptimal graph construction choices, informing the practitioner.

Tasks (M)	Nodes (N)
1. Node Classification : predict the category labels of nodes. — e.g. paper subject classification text 2. GraphRAG Retrieval : answer questions over graph-structured context. — e.g. author queries	N1 Primary Entity: the fundamental unit of information with core textual content. — e.g. Paper N2 Secondary Entity: hub node connecting primary entities through shared participation. — e.g. Author N3 Aggregate Entity: a higher-order grouping of primary entities by category or family. — e.g. Journal
Edges (E)	Text (T)
Ground Truth Metrics: E4a Categorical edges — e.g. same category E4b Scalar edges — e.g. similar citation count E4c Participation edges — e.g. coauthorship Calculated Similarity Metrics: E5a Semantic edges — e.g. similar abstract E5b Structural edges — e.g. similar degree	T6a Contextual: node text including both primary content and its surrounding semantic context — e.g. title + abstract T6b Standard: primary content only with no surrounding context — e.g. title T6e Baseline: no text features, serving as a structure-only control. — e.g. no text

Table 1: TAG construction search space

\Omega_{\mathcal{M}}

with citation network examples .

Architecture	2-layer GraphSAGE
Aggregation	Mean
Node features	SBERT all-MiniLM-L6-v2 (384-d)
Hidden dim	256
Output dim	Dataset- and task-specific
Epochs	100
Early stopping	Patience 30 (on validation)

Table 2: Fixed Scoring configurations.

Figure 2: Construction performance results for Sports. We visualize 6 of 26 variants, revealing a clear performance split between N2 and N1/N3 for the GNN task (top row). The bottom row has less extreme scoring differences, but similar superiority among variants. The thick lines represent means; thin lines are subsets (top) and question orderings (bottom). On the right, heatmaps show the final scores for each variant and subsample or question bucket. T6e represents the no text control.

$\rho$	Hist	Sports	ArXiv	Elec	Toys
Hist	+0.97*	+0.72*	+0.75*	+0.65*	+0.68*
Sports	+0.86*	+0.98*	+0.48	+0.92*	+0.92*
ArXiv	+0.86*	+0.50*	+0.97*	+0.48	+0.48
Elec	+0.48	+0.95*	+0.50	+0.98*	+0.94*
Toys	+0.65	+0.93*	+0.47	+0.93*	+0.95*

Table 3: Decision Tree Structural Consistency Checks

Figure 4: Construction ranking stability versus evaluation budget for GNN and GraphRAG. Left: GNN Spearman

\rho

against

n

train-pool subsets across five datasets. Right: GraphRAG stability against question counts with 20 random seeds. Both pipelines show increasing ranking stability with larger evaluation budgets, with GNN starting high and GraphRAG climbing gradually.

Dataset	GNN	RAG	GNN	RAG	GNN	RAG	GNN	RAG
	Variants		Total scoring (hr)		Full-scale run (hr)		Whole-space cost
ArXiv	24	16	0.14	2.8	0.05	0.11	$\mathbf{2.7\times}$	$\mathbf{26.4\times}$
Sports	39	26	0.16	3.4	0.05	0.12	$\mathbf{3.0\times}$	$\mathbf{27.5\times}$
History	12	8	0.04	0.8	0.02	0.10	$\mathbf{2.5\times}$	$\mathbf{8.0\times}$
Electronics	39	26	0.16	2.8	0.02	0.11	$\mathbf{6.9\times}$	$\mathbf{24.5\times}$
Toys	39	26	0.16	2.8	0.02	0.10	$\mathbf{9.3\times}$	$\mathbf{26.8\times}$

Table 4: Construction space evaluation cost.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 5 — Figure 5: Construction performance for the four datasets not shown in the main body. Rows are datasets; the left column is node classification and the right column is GraphRAG retrieval. Within each panel, scores accumulate over evaluation on the left and final per-variant scores appear as a heatmap on the right.

Graph Construction

See all 18 papers

Jun 30, 2026

TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning

Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and graphs use the language model mainly as a text encoder and delegate structure learning to a separate graph module. We propose method that unifies textual reasoning and graph message passing within a masked diffusion language model, a language model with bidirectional attention and generative decoding. For each graph instance, method linearises a sampled local neighbourhood into a token sequence and injects graph structure through a topology attention mask, which realises message passing over the graph. Because the diffusion language model can both interpret and generate text, the method adapts to different tasks simply by changing the prompt, supporting node classification, link prediction, and cross-dataset transfer with no target-specific fine-tuning. Experiments show that method outperforms graph neural networks, graph transformers, and LLM-based baselines on all three TAG benchmarks across two tasks, improving over the strongest baseline by up to 3.9 points.

Lingjie Chen, Yuanchen Bei, Haobo Xu +3

UIUC · VISA

Masked Diffusion Models Link Prediction LLM Reasoning with Graphs Text-Attributed Graph Learning Diffusion Language Models Node Classification+1

Ask PDF

Jun 2, 2026

Text-attributed Graph Condensation via Text Selection and Attribute Matching

Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neural Network (GNN) and language model jointly, which leads to high space and time consumption, especially on large datasets. To mitigate this, we propose TAGSAM, a condensation method that compresses TAGs while preserving training accuracy. TAGSAM comes with two key designs, i.e., subgraph text Selection and Attribute similarity Matching, which compress the text description and graph topology of TAG, respectively. For the texts, subgraph text selection selects and merges representative text chunks from multiple related text descriptions by maximizing mutual information. For the graph topology, popular condensation methods based on Matching Training Trajectories (MTT) suffer from high variance, which hinders accuracy. Our attribute similarity matching mitigates this issue by aligning stable similarity matrices. We evaluate TAGSAM against six state-of-the-art baselines, where it showcases superior performance. For the same compressed size, TAGSAM improves upon the best-performing baseline by an average of 4.9% in accuracy. Furthermore, it maintains competitive training accuracy even when the TAG is condensed to just 1% size. Our code is available at https://github.com/SundayVHan/TAGSAM

Haowei Han, Yuxiang Wang, Guojia Wan +5

School of Computer Science Wuhan University Wuhan, China · Institute for Math & AI Wuhan University Wuhan, China

Graph Neural Networks Text-Attributed Graph Learning Dataset Condensation

Ask PDF

Jul 21, 2026

OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation

Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality issues arising from text, structure, and labels, and typically manifesting as sparsity, noise, and imbalance. These dimensions define nine representative degradation scenarios that can substantially affect TAG learning. Although prior studies have explored specific mitigation strategies, existing evidence remains fragmented across degradation types, datasets, tasks, and model families, leaving TAG robustness insufficiently understood. To address this gap, we present OpenRTAG, a robustness benchmark for text-attributed graph learning. OpenRTAG organizes TAG quality issues into a unified 3 * 3 taxonomy and supports standardized evaluation across nine TAG datasets and three downstream tasks. It systematically evaluates scenario validity and model sensitivity, compares traditional GNNs, LLM-GNNs, and a representative GFM, investigates the effectiveness, efficiency, and robustness of scenario-matched baselines, and further examines model behavior under composite degradation scenarios. OpenRTAG provides a standardized testbed for understanding robustness in TAG learning under realistic low-quality settings.

Yuze Dai, Zhihan Zhang, Yan Zhao +6

Beijing Institute of Technology

Text-Attributed Graph Learning Learning with Noisy Labels

Ask PDF

Abstract

Graph Construction

Explore similar work

TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning

Text-attributed Graph Condensation via Text Selection and Attribute Matching

OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation