1. Multi-level Graph Memory Network Cluster Convolutional Recurrent Network for traffic forecasting.
- Author
-
Sun, Le, Dai, Wenzhang, and Muhammad, Ghulam
- Subjects
- *
TRAFFIC estimation , *COMPUTER network traffic , *INTELLIGENT transportation systems , *MEMORY , *MEMORIZATION - Abstract
Traffic forecasting plays a vital role in the management of urban road networks and the development of intelligent transportation systems. To effectively capture spatial and temporal dependencies within traffic data, Graph Neural Networks (GNNs) emerge by combining recurrent neural networks and dynamic graph learning. However, traditional GNNs face challenges in efficiently memorizing patterns at different levels of these dependencies, including long-term shared patterns and short-term specific patterns. We propose a traffic forecasting model, the Multi-level Graph Memory Network Cluster Convolutional Recurrent Network (MMNCCRN). The MMNCCRN consists of four modules: Encoder Module (EM), Attention Module (AM), Memory Network Cluster Module (MNCM), and Decoder Module (DM). To enhance the model's performance, AM incorporates a concise yet efficient attention mechanism that augments important information in the output of EM. This alleviates the pressure on MNCM to identify patterns at different levels. Meanwhile, in MNCM, we extensively leverage memory networks and introduce the concept of clustering. By storing and memorizing patterns implicit in spatial and temporal dependencies, MNCM assists the model in learning underlying graph structures and discovering new hidden patterns. Experimental results show that our model outperforms others in most metrics on four datasets. • Specific patterns and shared patterns are implicit in traffic data. • Memory network cluster can memorize, and utilize patterns at multiple levels. • An effective attention machanism helps alleviate the memory burden of the cluster. • Memory items are collectively used to represent the graph structure. • Memory network cluster is more effective than simply expanding one single network. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF