Research map / Graph learning / Graph self-supervised learning
A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning
Check 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 |
|---|---|---|---|
| Add a graph-reconstruction pathway to D-DAE | D-DAE · YaleB test | mAP: 82.61 -> 83.73 | Helped |
| Add a graph-reconstruction pathway to D-DAE | D-DAE · COIL20 test | mAP: 77.61 -> 82.23 | Helped |
| Add a graph-reconstruction pathway to D-DAE | D-DAE · MNIST test | mAP: 75.82 -> 79.15 | Helped |
| Add a graph-reconstruction pathway to D-DAE | D-DAE · MNIST2 test | mAP: 75.71 -> 77.43 | Helped |
| Use an overly small or overly large graph-loss weight η (ablation) | GR-DNN · MNIST | mAP@1k | Hurt |
| Increase code dimension (ablation) | GR-DNN(D-DAE) · MNIST | mAP@1k | Hurt |
| Increase the number of layers in the data and graph pathways (ablation) | GR-DNN · MNIST | clustering performance | Helped |
| Increase the number of layers in the graph decoder (ablation) | GR-DNN · MNIST | clustering performance | Helped |
| Use too few or too many anchor points (ablation) | GR-DNN with anchor graph · MNIST | mAP | Hurt |
| Increase graph neighborhood size K (ablation) | GR-DNN with anchor graph · MNIST | mAP@10 | Hurt |
| Increase graph neighborhood size K (ablation) | GR-DNN with anchor graph · MNIST | mAP@2k | Helped |
Closest papers by meaning
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.90)
- Rethinking Graph Regularization for Graph Neural Networks (AAAI 2021 · similarity 0.88)
- Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings (NeurIPS 2020 · similarity 0.88)
- Beyond Graph Convolutional Network: An Interpretable Regularizer-Centered Optimization Framework (AAAI 2023 · similarity 0.87)
- LDMNet: Low Dimensional Manifold Regularized Neural Networks (CVPR 2018 · similarity 0.87)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.86)
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.