Research map / Graph learning / Graph self-supervised learning
Deep Clustering by Gaussian Mixture Variational Autoencoders With Graph Embedding
Linxiao Yang, Ngai-Man Cheung, Jiaying Li, Jun Fang
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 graph embedding (JS divergence between neighbor posteriors) to Gaussian mixture VAE | VaDE · MNIST | clustering accuracy: 94.46 -> 97.58 | Improved |
| add graph embedding to Gaussian mixture VAE | VaDE · STL-10 | clustering accuracy: 84.45 -> 90.59 | Improved |
| add graph embedding to Gaussian mixture VAE | VaDE · Reuters | clustering accuracy: 79.83 -> 82.3 | Improved |
| add graph embedding to Gaussian mixture VAE | VaDE · HHAR | clustering accuracy: 84.46 -> 89.04 | Improved |
| use jointly learned GMM clustering instead of two-stage spectral embedding then k-means | SpectralNet · MNIST | clustering accuracy: 97.1 -> 97.58 | Improved |
| use DGG instead of IMSAT | IMSAT · MNIST | clustering accuracy: 98.4 -> 97.58 | Hurt |
| use DGG instead of IMSAT | IMSAT · Reuters | clustering accuracy: 71.0 -> 82.3 | Improved |
| add 1 nearest neighbor of graph information (ablation) | DGG · MNIST | clustering accuracy: 94.82 -> 96.98 | Improved |
| increase neighbors from 1 to 20 (ablation) | DGG · MNIST | clustering accuracy: 96.98 -> 97.58 | Improved |
| increase neighbors from 20 to 30 (ablation) | DGG · MNIST | clustering accuracy: 97.58 -> 97.49 | Hurt |
Closest papers by meaning
- ManlyMM-VAE: Deep Clustering With Manly Transformation Mixture Latent Embeddings for High-Dimensional Skewed Data (TPAMI 2026 · similarity 0.89)
- Deep Spectral Clustering Using Dual Autoencoder Network (CVPR 2019 · similarity 0.89)
- Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (ICLR 2018 · similarity 0.89)
- Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization (ICCV 2017 · similarity 0.89)
- Clustering Diffusion Model With Frequency-Signal Modulation for Variational Graph Autoencoders (TPAMI 2025 · similarity 0.88)
- Multi-Facet Clustering Variational Autoencoders (NeurIPS 2021 · similarity 0.88)
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.
