Research map / Learning theory and algorithms / Clustering
Gated Variational Graph Autoencoders as Experts with Competition and Consensus for Multi-view Clustering
Zhaoliang Chen, William K. Cheung, Hong-Ning Dai, Byron Choi, Jiming Liu
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 structure-aware quality evaluation to the gating network (ablation) | GVGAE-C2 · Wafer | ACC (%): 63.02 -> 68.29 | Improved |
| add structure-aware quality evaluation to the gating network (ablation) | GVGAE-C2 · LP1 | ACC (%): 66.81 -> 75.91 | Improved |
| add the gating network on top of quality scores (ablation) | GVGAE-C2 · Wafer | ACC (%): 64.55 -> 68.29 | Improved |
| add the gating network on top of quality scores (ablation) | GVGAE-C2 · LP1 | ACC (%): 69.09 -> 75.91 | Improved |
| add sample-level gating module instead of trainable view-level weights (ablation) | GVGAE-C2 · LP1 | ACC (%): 59.09 -> 75.91 | Improved |
| add sample-level gating module instead of trainable view-level weights (ablation) | GVGAE-C2 · Wafer | ACC (%): 62.95 -> 68.29 | Improved |
| keep the lowest-quality expert E3 rather than removing it (ablation) | GVGAE-C2 · Wafer | ACC (%): 62.24 -> 68.29 | Improved |
| keep expert E5 rather than removing it (ablation) | GVGAE-C2 · LP1 | ACC (%): 74.55 -> 75.91 | Improved |
| keep all six experts rather than removing E1 (ablation) | GVGAE-C2 · LP1 | ACC (%): 71.36 -> 75.91 | Improved |
| use very large lambda and gamma loss weights (ablation) | GVGAE-C2 · ALOI, Caltech101-20, WebKB, LP1 | ACC (%) | Hurt |
| add expert allocation loss to prevent collapse onto few experts (ablation) | GVGAE-C2 · Wafer, LP1 | ACC (%) | Improved |
| use GVGAE-C2 instead of MoE-based DMVC-CE | DMVC-CE · ALOI | ACC (%): 90.44 -> 91.99 | Improved |
Closest papers by meaning
- Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering Structures (AAAI 2024 · similarity 0.89)
- Dirichlet Graph Variational Autoencoder (NeurIPS 2020 · similarity 0.89)
- SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View Clustering (AAAI 2024 · similarity 0.88)
- Multi-View Graph Clustering via Node-Guided Contrastive Encoding (ICML 2025 · similarity 0.87)
- Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (AAAI 2025 · similarity 0.87)
- Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs (ICLR 2025 · similarity 0.87)
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.
