Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
–Neural Information Processing Systems
Although transformer-based methods have achieved great success in multi-scale temporal pattern interaction modeling, two key challenges limit their further development: (1) Individual time points contain less semantic information, and leveraging attention to model pair-wise interactions may cause the information utilization bottleneck.
Neural Information Processing Systems
May-29-2025, 04:42:04 GMT
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Information Technology > Security & Privacy (0.46)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.87)
- Natural Language (1.00)
- Representation & Reasoning (1.00)
- Vision (0.93)
- Machine Learning > Neural Networks
- Data Science (1.00)
- Artificial Intelligence
- Information Technology