Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs

2025-02-19

AI Summary

Existing graph data augmentation methods often neglect contextual information, while mainstream large language model (LLM)-empowered graph learning approaches rely on white-box access—requiring model weights or intermediate features—making them incompatible with proprietary, black-box LLMs. To address this, we propose DemoGraph, the first black-box, context-driven graph data augmentation framework. DemoGraph requires no internal model parameters; instead, it leverages granularity-aware prompting and instruction tuning to guide closed-source LLMs in generating implicit knowledge graphs, which are then dynamically fused into the original graph structure. This approach effectively mitigates graph data scarcity and noise. Extensive experiments demonstrate significant performance gains across diverse graph learning tasks—including node classification, link prediction, and graph classification—with particularly notable improvements in electronic health record (EHR) analytics, where it simultaneously enhances both predictive accuracy and model interpretability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Reasoning under Uncertainty: Graphical Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Data augmentation is necessary for graph representation learning due to the scarcity and noise present in graph data. Most of the existing augmentation methods overlook the context information inherited from the dataset as they rely solely on the graph structure for augmentation. Despite the success of some large language model-based (LLM) graph learning methods, they are mostly white-box which require access to the weights or latent features from the open-access LLMs, making them difficult to be democratized for everyone as existing LLMs are mostly closed-source for commercial considerations. To overcome these limitations, we propose a black-box context-driven graph data augmentation approach, with the guidance of LLMs -- DemoGraph. Leveraging the text prompt as context-related information, we task the LLM with generating knowledge graphs (KGs), which allow us to capture the structural interactions from the text outputs. We then design a dynamic merging schema to stochastically integrate the LLM-generated KGs into the original graph during training. To control the sparsity of the augmented graph, we further devise a granularity-aware prompting strategy and an instruction fine-tuning module, which seamlessly generates text prompts according to different granularity levels of the dataset. Extensive experiments on various graph learning tasks validate the effectiveness of our method over existing graph data augmentation methods. Notably, our approach excels in scenarios involving electronic health records (EHRs), which validates its maximal utilization of contextual knowledge, leading to enhanced predictive performance and interpretability.

Problem

• Addresses graph data scarcity and noise issues
• Proposes black-box context-driven graph augmentation
• Enhances predictive performance and interpretability

Innovation

• Black-box LLM-driven graph augmentation
• Dynamic merging of knowledge graphs
• Granularity-aware prompting strategy