Research map / Time series / Long-term forecasting
Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
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 |
|---|---|---|---|
| add zigzag persistence representation learning (ablation) | Z-GCNETs · PeMSD4 | RMSE: 31.94 -> 31.61 | Helped |
| add spatial graph convolution (ablation) | Z-GCNETs · PeMSD4 | RMSE: 31.96 -> 31.61 | Helped |
| add temporal graph convolution (ablation) | Z-GCNETs · PeMSD4 | RMSE: 33.18 -> 31.61 | Helped |
| add zigzag persistence representation learning (ablation) | Z-GCNETs · PeMSD8 | RMSE: 27.06 -> 25.11 | Helped |
| add spatial graph convolution (ablation) | Z-GCNETs · PeMSD8 | RMSE: 26.86 -> 25.11 | Helped |
| add temporal graph convolution (ablation) | Z-GCNETs · PeMSD8 | RMSE: 26.44 -> 25.11 | Helped |
| add zigzag persistence representation learning (ablation) | Z-GCNETs · Bytom | MAPE: 33.19% -> 31.04% | Helped |
| add spatial graph convolution (ablation) | Z-GCNETs · Bytom | MAPE: 34.32% -> 31.04% | Helped |
| add temporal graph convolution (ablation) | Z-GCNETs · Bytom | MAPE: 31.25% -> 31.04% | Helped |
| add zigzag persistence representation learning (ablation) | Z-GCNETs · Decentraland | MAPE: 24.24% -> 23.81% | Helped |
| add spatial graph convolution (ablation) | Z-GCNETs · Decentraland | MAPE: 25.22% -> 23.81% | Helped |
| add temporal graph convolution (ablation) | Z-GCNETs · Decentraland | MAPE: 24.62% -> 23.81% | Helped |
Closest papers by meaning
- Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence (AAAI 2024 · similarity 0.87)
- Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms (NeurIPS 2024 · similarity 0.86)
- Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks (AAAI 2025 · similarity 0.86)
- Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs (NeurIPS 2024 · similarity 0.85)
- Persistent Topological Features in Large Language Models (ICML 2025 · similarity 0.85)
- TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction (ICML 2025 · similarity 0.85)
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.