M-LINKX: Multiview Graph Learning for Brain Cognitive Disease Detection

An Phan; Yufei Jin; Xingquan Zhu

cs.LGAug 14, 2026

M-LINKX: Multiview Graph Learning for Brain Cognitive Disease Detection

Authors: An Phan, Yufei Jin, Xingquan Zhu

Organizations: Dept. of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA

Abstract

Electroencephalogram (EEG) is a non-invasive and relatively low-cost procedure that measures brain electricity for the detection of cognitive diseases. EEG-based classification of dementia-related conditions, including Alzheimer's disease (AD), mild cognitive impairment (MCI), and frontotemporal dementia (FTD), remains challenging because EEG signals are noisy, non-stationary, and vary across subjects. Segment-based learning provides a practical way to model long EEG recordings by converting them into fixed-length inputs. For each segment, discriminative information may be explored by using signals within each channel (i.e. electrode), as well as interactions between EEG channels. In this paper, we propose M-LINKX, a multi-view graph learning framework for EEG-based dementia classification. For each segment, we extract channel-level node features and construct multiple functional-connectivity (FC) graph views, where each view is defined by a specific combination of connectivity metric, frequency band, and topology filter, respectively. Instead of relying on message passing over the constructed graphs, M-LINKX follows a simple design in modeling node features and adjacency-based connectivity representations. The graph-view representations are fused using global trainable view weights, and subject-level prediction is obtained by averaging segment-level probabilities. Experiments on two three-class EEG datasets with different diagnostic groups, CAUEEG (HC/MCI/Dementia) and AHEAP (HC/AD/FTD), show that M-LINKX achieves the best subject-level performance under the main experimental settings. Our study suggests that multi-view functional connectivity can improve EEG-based dementia classification when integrated with an appropriate graph-learning architecture. Code and data are available at https://github.com/anphantt/MLINKX.

Figures & tables

Fig. 1 : Overview of the proposed M-LINKX framework. For readability, block ① should be read from top to bottom, whereas blocks ② and ③ should be read from left to right. Block ① shows the subject-level classification pipeline: each EEG recording is divided into fixed-length overlapping segments, segment-level probabilities are predicted, and subject-level prediction is obtained by averaging probabilities across segments. Block ② shows feature extraction and graph construction for a segment, where “segment 2” is represented by channel-level node features and multiple FC graph views from different connectivity metrics, frequency bands, and topology filters. Block ③ shows the M-LINKX encoder, which learns node-feature and graph-view embeddings, fuses graph-view embeddings using global trainable view weights, and produces segment-level predictions.

Fig. 2 : Topology-specific graph representations of alpha-band coherence from three consecutive EEG segments of the same subject recording. Nodes denote EEG channels arranged by approximate 10–20 scalp locations, and weighted edges denote retained coherence connections. Rows show the four topology filters: complete , domain , top- $k$ , and hybrid ; columns show consecutive EEG segments. Edge thickness and color indicate coherence weight, with thicker and darker blue edges representing larger weights and thinner gray edges representing smaller weights.

Property	AHEAP	CAUEEG
# of Subjects	36 AD, 23 FTD, 29 HC	291 Dementia, 395 MCI, 436 HC
# of Channels	19	19
Condition	Eyes closed	Eyes closed and eyes open
Sampling Rate	500 Hz	200 Hz
Avg. Duration	13.21 $\pm$ 2.32 min	12.80 $\pm$ 2.65 min

TABLE I : Summary of the EEG datasets used in this study.

Model	RawEEG	Node features	Balanced Acc.	Macro-F1	Balanced Acc.	Macro-F1
			CAUEEG (10-second window)		AHEAP (4-second window)
			35 HC, 33 MCI, 22 Dementia		29 HC, 23 FTD, 36 AD
1D ResNet	✓		0.6146 $\pm$ 0.0135	0.6224 $\pm$ 0.0141	0.5221 $\pm$ 0.0432	0.4815 $\pm$ 0.0511
CNN-LSTM	✓		0.5700 $\pm$ 0.0133	0.5585 $\pm$ 0.0049	0.5697 $\pm$ 0.0527	0.5494 $\pm$ 0.0438
MLP-node		✓	0.5949 $\pm$ 0.0233	0.5961 $\pm$ 0.0199	0.5740 $\pm$ 0.0477	0.5550 $\pm$ 0.0446
Ensemble	✓	✓	0.6084 $\pm$ 0.0285	0.6048 $\pm$ 0.0303	0.5791 $\pm$ 0.0258	0.5528 $\pm$ 0.0273

TABLE II : Subject-level performance of M-LINKX and the baseline models, reported as mean

\pm

standard deviation over three random seeds. Best and second-best results are shown in bold and underlined italics , respectively. For methods involving different Functional connectivity (“FC Input”),

\mathcal{V}

denotes all four candidate graph views and

v^{\star}

denotes the best-performing view among the four candidate graph views

\mathcal{V}

Fig. 3 : Subject-level confusion matrices of M-LINKX on CAUEEG (10 $s$ ) and AHEAP (4 $s$ ). Cells show average subject counts and row-normalized percentages over three random seeds. For AHEAP, confusion matrices are first summed across folds within each seed.

Fig. 4 : Subject-level balanced accuracy comparisons between M-LINKX and baseline models w.r.t. different segment durations on CAUEEG and AHEAP. $y$ -axis denotes mean balanced accuracies over three random seeds, and error bars denote standard deviation.

Fig. 5 : M-LINKX trainable graph-view weights across segment durations. Bars denote the mean weight over three random seeds, and error bars denote standard deviation.

Electroencephalography

Electroencephalography (EEG) studies brain-generated electrical activity to understand cognition and support diagnosis, monitoring, and brain-computer interfaces.

See all 182 papers

EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning
Mar 3, 2026Fengcheng Wu, Zhenxi Song, Guoyang Xu +4Electroencephalography Dynamic Graph Learning
Harbin Institute of Technology, Shenzhen, China · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen, China
Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction
Apr 27, 2026Xiaoyu Zheng, Xu Tian, Bin Jiao +4Alzheimer's Disease Electroencephalography
Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University, Urumqi 830091, China. · Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, China. · Department of Neurology, Xiangya Hospital, Central South University, Changsha 410083, China. +1
Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networks
Oct 13, 2025Jun-En Ding, Anna Zilverstand, Shihao Yang +2Alzheimer's Disease Electroencephalography
Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ, USA · Department of Psychiatry and Behavioral Sciences, University of Minnesota, Minneapolis, MN, USA · Institute of Brain Science, College of Medicine, National Yang-Ming Chiao Tung University, Taipei City, Taiwan

Mar 3, 2026J/K move · Enter open · S save

EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning

Fengcheng Wu, Zhenxi Song, Guoyang Xu, Kaisong Hu+3

Harbin Institute of Technology, Shenzhen, China · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen, China

Electroencephalography Dynamic Graph Learning Functional Connectivity GNN Explainability

Open paper AskPDF arXiv

Robust and interpretable dementia diagnosis from noisy, non-stationary electroencephalography (EEG) is clinically essential yet remains challenging. To this end, we propose SeeGraph, a Sparse-Explanatory dynamic EEG-graph network that models time-evolving functional connectivity and employs a node-guided sparse edge mask to reveal the connections that drive diagnostic decisions, while remaining robust to noise and cross-site variability. SeeGraph comprises four components: (1) a dual-trajectory temporal encoder that models dynamic EEG with two streams, where node signals capture regional oscillations and edge signals capture interregional coupling; (2) a topology-aware positional encoder that derives graph-spectral Laplacian coordinates from the fused connectivity and augments node embeddings; (3) a node-guided sparse explanatory edge mask that gates the connectivity into a compact subgraph; and (4) a gated graph predictor that operates on the sparsified graph. The framework is trained using cross-entropy loss together with a sparsity regularizer on the mask, yielding noise-robust and interpretable diagnoses. The effectiveness of SeeGraph is validated on public and in-house EEG cohorts, including patients with neurodegenerative dementias and healthy controls, under both raw and noise-perturbed conditions. Its sparse, node-guided explanations highlight disease-relevant connections and align with established clinical findings on functional connectivity alterations, thereby offering transparent cues for neurological evaluation.

Abstract

Electroencephalography

Explore similar work

EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning

Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction

Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networks