DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
Jiasheng Zhang, Jialin Chen, Menglin Yang, Aosong Feng, Shuang Liang,, Jie Shao, and Rex Ying

TL;DR
The paper introduces DTGB, a large-scale benchmark dataset for dynamic text-attributed graphs, enabling evaluation of models that understand evolving graph structures and associated natural language descriptions.
Contribution
It provides the first comprehensive benchmark for DyTAGs, including datasets, evaluation procedures, and extensive experiments with existing models and LLMs.
Findings
Existing models struggle with DyTAGs.
DTGB reveals limitations in current dynamic graph algorithms.
Incorporating text attributes enhances understanding of graph evolution.
Abstract
Dynamic text-attributed graphs (DyTAGs) are prevalent in various real-world scenarios, where each node and edge are associated with text descriptions, and both the graph structure and text descriptions evolve over time. Despite their broad applicability, there is a notable scarcity of benchmark datasets tailored to DyTAGs, which hinders the potential advancement in many research fields. To address this gap, we introduce Dynamic Text-attributed Graph Benchmark (DTGB), a collection of large-scale, time-evolving graphs from diverse domains, with nodes and edges enriched by dynamically changing text attributes and categories. To facilitate the use of DTGB, we design standardized evaluation procedures based on four real-world use cases: future link prediction, destination node retrieval, edge classification, and textual relation generation. These tasks require models to understand both…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsSemantic Web and Ontologies · Advanced Graph Neural Networks · Logic, Reasoning, and Knowledge
