GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better
Xu Chu, Hanlin Xue, Zhijie Tan, Bingce Wang, Tong Mo, Weiping Li

TL;DR
GraphSOS enhances LLMs' understanding of graphs by optimizing node/edge order and sampling subgraphs, leading to improved performance in graph reasoning tasks.
Contribution
The paper introduces GraphSOS, a framework with order selection and subgraph sampling modules, improving LLMs' reasoning on graph data through novel serialization and sampling strategies.
Findings
Improved node classification accuracy.
Enhanced graph question-answering performance.
Better generalization across datasets.
Abstract
The success of Large Language Models (LLMs) in various domains has led researchers to apply them to graph-related problems by converting graph data into natural language text. However, unlike graph data, natural language inherently has sequential order. We observe a counter-intuitive fact that when the order of nodes or edges in the natural language description of a graph is shuffled, despite describing the same graph, model performance fluctuates between high performance and random guessing. Additionally, due to LLMs' limited input context length, current methods typically randomly sample neighbors of target nodes as representatives of their neighborhood, which may not always be effective for accurate reasoning. To address these gaps, we introduce GraphSOS (Graph Sampling and Order Selection). This novel model framework features an Order Selector Module to ensure proper serialization…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGraph Theory and Algorithms · Advanced Graph Neural Networks · Semantic Web and Ontologies
