Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-Layer Multi-View Classification for Alzheimer’s Disease Diagnosis
Changqing Zhang, Ehsan Adeli, Tao Zhou, Xiaobo Chen, Dinggang Shen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add low-rank tensor constraint on view kernels (alpha 0 -> 10) (ablation) | multi-layer multi-view kernel model · ADNI multi-modality | accuracy: 0.579 -> 0.625 | Improved |
| add low-rank tensor constraint (alpha 0 -> 100) (ablation) | multi-layer multi-view kernel model · ADNI RS-fMRI multi-feature | accuracy: 0.481 -> 0.502 | Improved |
| use two modalities instead of MRI alone (View1+View3) | SVM · ADNI multi-modality | accuracy: 0.517 -> 0.575 | Improved |
| concatenate all three modalities instead of single best view | SVM · ADNI multi-modality | accuracy: 0.542 -> 0.608 | Improved |
| concatenate all three feature types instead of single view | SVM · ADNI RS-fMRI multi-feature | accuracy: 0.471 -> 0.467 | No clear effect |
| add PET to MRI+SNP concatenation relative to pair | SVM · ADNI multi-modality | accuracy: 0.575 -> 0.608 | Mixed |
| use matrix completion with concatenated views | Matrix Completion · ADNI multi-modality | accuracy: 0.608 -> 0.514 | Hurt |
| use matrix completion with concatenated views | Matrix Completion · ADNI RS-fMRI multi-feature | accuracy: 0.467 -> 0.410 | Hurt |
| replace VMR-MVL with the proposed method without tensor (alpha=0) | multi-view model · ADNI multi-modality | accuracy: 0.579 -> 0.579 | No clear effect |
| full model versus best baseline multi-view method | Ours + Tensor · ADNI multi-modality | accuracy: 0.608 -> 0.625 | Improved |
| full model versus best baseline Multiview CCA | Ours + Tensor · ADNI RS-fMRI multi-feature | accuracy: 0.482 -> 0.502 | Improved |
| vary tradeoff hyperparameter alpha (ablation) | Ours + Tensor · ADNI both datasets | accuracy | No clear effect |
Closest papers by meaning
- Learning Multi-Modal Biomarker Representations via Globally Aligned Longitudinal Enrichments (AAAI 2020 · similarity 0.87)
- Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease Diagnosis (ICLR 2026 · similarity 0.87)
- Multi-Way Multi-Level Kernel Modeling for Neuroimaging Classification (CVPR 2017 · similarity 0.87)
- EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease (CVPR 2026 · similarity 0.83)
- Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization (ICML 2024 · similarity 0.83)
- CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
