LLM-Based Multi-Agent Systems are Scalable Graph Generative Models

• URL: http://arxiv.org/abs/2410.09824v6
• Date: Mon, 06 Jan 2025 02:16:37 GMT
• Title: LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
• Authors: Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei, Xu Chen, Yankai Lin, Xuchen Pan, Yaliang Li, Bolin Ding,
• Abstract summary: GraphAgent-Generator (GAG) is a novel simulation-based framework for dynamic, text-attributed social graph generation. GAG simulates the temporal node and edge generation processes for zero-shot social graph generation. The resulting graphs exhibit adherence to seven key macroscopic network properties, achieving an 11% improvement in microscopic graph structure metrics.
• Score: 73.28294528654885
• License:
• Abstract: The structural properties of naturally arising social graphs are extensively studied to understand their evolution. Prior approaches for modeling network dynamics typically rely on rule-based models, which lack realism and generalizability, or deep learning-based models, which require large-scale training datasets. Social graphs, as abstract graph representations of entity-wise interactions, present an opportunity to explore network evolution mechanisms through realistic simulations of human-item interactions. Leveraging the pre-trained social consensus knowledge embedded in large language models (LLMs), we present GraphAgent-Generator (GAG), a novel simulation-based framework for dynamic, text-attributed social graph generation. GAG simulates the temporal node and edge generation processes for zero-shot social graph generation. The resulting graphs exhibit adherence to seven key macroscopic network properties, achieving an 11% improvement in microscopic graph structure metrics. Through the node classification benchmarking task, we validate GAG effectively captures the intricate text-structure correlations in graph generation. Furthermore, GAG supports generating graphs with up to nearly 100,000 nodes or 10 million edges through large-scale LLM-based agent simulation with parallel acceleration, achieving a minimum speed-up of 90.4%. The source code is available at https://github.com/Ji-Cather/GraphAgent.

Related papers

• Neural Graph Pattern Machine [50.78679002846741]
  We propose the Neural Graph Pattern Machine (GPM), a framework designed to learn directly from graph patterns. GPM efficiently extracts and encodes substructures while identifying the most relevant ones for downstream tasks.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks [53.10674067060148]
  Shapley Interactions (SIs) quantify node contributions and interactions among multiple nodes. By exploiting the GNN architecture, we show that the structure of interactions in node embeddings are preserved for graph prediction. We introduce GraphSHAP-IQ, an efficient approach to compute any-order SIs exactly.
  arXiv  Detail & Related papers  (2025-01-28T13:37:44Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs) This framework provides a standardized setting to evaluate GNNs across diverse datasets. We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks [25.720233631885726]
  integration of Graph Neural Networks (GNNs) and Large Language Models (LLMs) has emerged as a promising technological paradigm. We leverage graph description texts with rich semantic context to fundamentally enhance Data quality. This work serves as a foundational reference for researchers and practitioners looking to advance graph learning methodologies.
  arXiv  Detail & Related papers  (2024-12-17T01:41:17Z)
• Tensor-Fused Multi-View Graph Contrastive Learning [12.412040359604163]
  Graph contrastive learning (GCL) has emerged as a promising approach to enhance graph neural networks' (GNNs) ability to learn rich representations from unlabeled graph-structured data. Current GCL models face challenges with computational demands and limited feature utilization. We propose TensorMV-GCL, a novel framework that integrates extended persistent homology with GCL representations and facilitates multi-scale feature extraction.
  arXiv  Detail & Related papers  (2024-10-20T01:40:12Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• GraphMaker: Can Diffusion Models Generate Large Attributed Graphs? [7.330479039715941]
  Large-scale graphs with node attributes are increasingly common in various real-world applications. Traditional graph generation methods are limited in their capacity to handle these complex structures. This paper introduces a novel diffusion model, GraphMaker, specifically designed for generating large attributed graphs.
  arXiv  Detail & Related papers  (2023-10-20T22:12:46Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Learning Attribute-Structure Co-Evolutions in Dynamic Graphs [28.848851822725933]
  We present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence. It preserves the impact of earlier graphs on the current graph by embedding generation through the sequence. It has a temporal self-attention mechanism to model long-range dependencies in the evolution.
  arXiv  Detail & Related papers  (2020-07-25T20:07:28Z)

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.