Research map / Graph learning / GNN architectures
Dual Low-Rank Graph Autoencoder for Semantic and Topological Networks
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 shared low-rank factor reconstruction across semantic and topological graphs rather than AMGCN | DLR-GAE · Citeseer | accuracy: 0.719 -> 0.724 | Helped |
| Use shared low-rank factor reconstruction across semantic and topological graphs rather than AMGCN | DLR-GAE · CoraFull | accuracy: 0.584 -> 0.590 | Helped |
| Use shared low-rank factor reconstruction across semantic and topological graphs rather than AMGCN | DLR-GAE · BlogCatalog | accuracy: 0.858 -> 0.901 | Helped |
| Use shared low-rank factor reconstruction across semantic and topological graphs rather than AMGCN | DLR-GAE · ACM | accuracy: 0.899 -> 0.924 | Helped |
| Use shared low-rank factor reconstruction across semantic and topological graphs rather than AMGCN | DLR-GAE · Flickr | accuracy: 0.756 -> 0.810 | Helped |
| Use shared low-rank factor reconstruction across semantic and topological graphs rather than AMGCN | DLR-GAE · UAI | accuracy: 0.643 -> 0.658 | Helped |
| Add a shared latent factor matrix Us (ablation) | DLR-GAE · Flickr | accuracy: 0.741 -> 0.810 | Helped |
| Add a shared latent factor matrix Us (ablation) | DLR-GAE · UAI | accuracy: 0.630 -> 0.658 | Helped |
| Add the Schatten-p low-rank loss Lsp(Us) (ablation) | DLR-GAE · Flickr | accuracy: 0.783 -> 0.810 | Helped |
| Add the Schatten-p low-rank loss Lsp(Us) (ablation) | DLR-GAE · UAI | accuracy: 0.636 -> 0.658 | Helped |
| Enforce the constraints on Us in Eq. (25) (ablation) | DLR-GAE · Flickr | accuracy: 0.562 -> 0.810 | Helped |
| Enforce the constraints on Us in Eq. (25) (ablation) | DLR-GAE · UAI | accuracy: 0.632 -> 0.658 | Helped |
Closest papers by meaning
- HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning (NeurIPS 2024 · similarity 0.90)
- Beyond Graph Convolutional Network: An Interpretable Regularizer-Centered Optimization Framework (AAAI 2023 · similarity 0.89)
- Graph Representation Learning via Ladder Gamma Variational Autoencoders (AAAI 2020 · similarity 0.89)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.89)
- Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness (ICML 2024 · similarity 0.88)
- Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach (AAAI 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.