MARK

PyTorch implementation for "MARK: Multi-agent Collaboration with Ranking Guidance for Text-attributed Graph Clustering", ACL Findings 2025

Overview

In this paper, we introduce a new perspective of leveraging large language models (LLMs) to enhance text-attributed graph clustering and develop a novel approach named Multi-agent Collaboration with Ranking Guidance (MARK).

Framework

Installation

Start by following this source codes:

git clone https://github.com/fuyw-aisw/MARK.git
cd MARK
pip install -r requirements.txt
## or install the following dependencies
## step1: install PyTorch’s CUDA support on Linux
pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu118
## step2: install pyg package
pip install torch_scatter torch_sparse torch_cluster torch_spline_conv torch_geometric -f https://data.pyg.org/whl/torch-2.0.0%2Bcu118.html ### GPU

Usage

Download preprocessed data from here.
And then put them into the folder MARK/preprocessed_data. Replace your own API url and API key in call_api.py

python main_magi.py