Community-Aware Graph Transformer for Brain Disorder Identification

Authors: Shengbing Pei, Jiajun Ma, Zhao Lv, Chao Zhang, Jihong Guan

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results indicate that our proposed method significantly improves performance on both large and small datasets, and can reliably capture the interactions between sub-networks, demonstrating its generalization and interpretability.
Researcher Affiliation Academia 1Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University 2School of Computer Science and Technology, Tongji University EMAIL, EMAIL, EMAIL, iiphci EMAIL, EMAIL
Pseudocode No The paper describes methods through text and diagrams (Figure 2 shows the overall framework) but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes All codes are implemented using the Py Torch and Py G libraries. Experiments are conducted on a Windows server equipped with an Intel Core i7-10700 CPU (2.90 GHz), a Ge Force GTX 3080 Ti GPU and 32 GB of RAM. The code is available at https://github.com/null-cks/CAGT.
Open Datasets Yes ABIDE I is an open-source ASD diseases database comprising data from 17 international sites, available at https: //fcon 1000.projects.nitrc.org/indi/abide. The Preprocessed Connectomes Project (PCP) has preprocessed the f MRI data for each subject, resulting in rs-f MRI data for 1,035 subjects, including 505 ASD patients and 530 normal controls (NC). REST-MDD is a publicly available MDD diseases database comprising 25 study cohorts, accessible at http: //rfmri.org/REST-meta-MDD. The data were preprocessed using the Data Processing Assistant for Resting-State f MRI (DPARSF) toolbox [Yan et al., 2016]. Following the official recommendation to exclude overlapping data from site S4, the refined dataset consists of 2,380 rs-f MRI scans, including 1,276 MDD patients and 1,104 NC. Tao Wu and Neurocon datasets are among the earliest image datasets available for Parkinson s research. We followed the preprocessing steps outlined in [Liu et al., 2024b] using the DPARSF toolbox.
Dataset Splits Yes We evaluate the model s performance using ten-fold crossvalidation.
Hardware Specification Yes Experiments are conducted on a Windows server equipped with an Intel Core i7-10700 CPU (2.90 GHz), a Ge Force GTX 3080 Ti GPU and 32 GB of RAM.
Software Dependencies No All codes are implemented using the Py Torch and Py G libraries. The paper mentions the use of PyTorch and PyG libraries but does not specify their version numbers.
Experiment Setup Yes Key parameters included a batch size of 64, a total of 70 epochs, an initial learning rate of 1 10 4, and a weight decay of 1 10 6. The top-k connections for each node are retained as edges, with their values fixed at 30. The RWPE dimension S is set to 30. The Transformer architecture is configured with 2 layers and 8 heads. A dropout rate of 0.2 is applied to the GINE, Transformer, and the final fully connected classification layer.