Research map / Graph learning / GNN architectures
Graph-Time Convolutional Neural Networks: Architecture and Theoretical Analysis
Mohammad Sabbaqi, Elvin Isufi
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 |
|---|---|---|---|
| GTCNN vs Graph WaveNet at short horizon | GTCNN · METR-LA 3-step | MAE: 2.69 -> 2.68 | Improved |
| GTCNN vs Graph WaveNet at long horizon | GTCNN · METR-LA 12-step | MAE: 3.53 -> 3.55 | Hurt |
| GTCNN vs Graph WaveNet at 3-step | GTCNN · PEMS-BAY 3-step | MAE: 1.30 -> 1.25 | Improved |
| GTCNN vs Graph WaveNet at 12-step | GTCNN · PEMS-BAY 12-step | MAE: 1.95 -> 2.27 | Hurt |
| GTCNN vs G-VARMA on small Molene data | GTCNN · Molene 1-step | MAE: 2.09 -> 3.55 | Hurt |
| GTCNN vs LSTM at 3-step | GTCNN · NOAA 3-step | MAE: 0.66 -> 0.63 | Improved |
| GTCNN vs LSTM at 5-step | GTCNN · NOAA 5-step | MAE: 1.39 -> 1.53 | Hurt |
Closest papers by meaning
- L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks (CVPR 2020 · similarity 0.92)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.91)
- Simplifying Graph Convolutional Networks (ICML 2019 · similarity 0.91)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.91)
- Space-Time Graph Neural Networks (ICLR 2022 · similarity 0.91)
- Over-squashing in Spatiotemporal Graph Neural Networks (NeurIPS 2025 · similarity 0.90)
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.
