Research map / Graph learning / Graph self-supervised learning
AffinityNet: Semi-Supervised Few-Shot Learning for Disease Type Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use feature attention and kNN attention pooling instead of a plain neural network | AffinityNet vs NeuralNet · Synthetic data, 1% training | test accuracy: 46.9% -> 98.2% | Helped |
| Use feature attention and kNN attention pooling instead of NeuralNet | Kidney cancer classification · Kidney cancer, 0.01 train portion | AMI: 0.70 -> 0.84 | Helped |
| Use AffinityNet instead of SVM | Uterus cancer classification · Uterus cancer, 0.01 train portion | AMI: 0.43 -> 0.62 | Helped |
| Use AffinityNet instead of the covariate-based Cox model | Kidney cancer survival prediction · Kidney cancer, 10% train portion | concordance index: 0.601 -> 0.694 | Helped |
| Use kNN attention pooling with unlabeled patients during representation learning | AffinityNet vs NeuralNet · Kidney cancer, semi-supervised clustering with 1% training | AMI: p=0.008 | Helped |
| Vary the number of nearest neighbors k (ablation) | AffinityNet · Kidney and uterus cancer classification | AMI | No clear effect |
Closest papers by meaning
- Affinity Graph Supervision for Visual Recognition (CVPR 2020 · similarity 0.86)
- Mutual CRF-GNN for Few-Shot Learning (CVPR 2021 · similarity 0.85)
- Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks (ICML 2024 · similarity 0.84)
- Diet Networks: Thin Parameters for Fat Genomics (ICLR 2017 · similarity 0.84)
- SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis (ICML 2021 · similarity 0.84)
- LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching (NeurIPS 2023 · similarity 0.84)
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.