Efficient Spectral Graph Convolutional Network Deployment on Memristive Crossbars
- Publisher:
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Publication Type:
- Journal Article
- Citation:
- IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, PP, (99)
- Issue Date:
- 2022-01-01
Embargoed
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Efficient Spectral Graph Convolutional Network Deployment on Memristive Crossbars.pdf | Accepted version | 1.25 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is currently unavailable due to the publisher's embargo.
Graph Neural Networks (GNNs) have attracted increasing research interest for their remarkable capability to model graph-structured knowledge. However, GNNs suffer from intensive data exchange and poor data locality, which will cause critical performance and energy bottlenecks under conventional complementary metal oxide semiconductor (CMOS)-based von-Neumann computing architectures (graphics processing unit (GPU), central processing unit (CPU)) for the “Memory Wall” issue. Fortunately, memristive crossbar-based computation has emerged as one of the most promising neuromorphic computing architectures, which has been widely studied as the computing platform for convolutional neural network (CNNs), recurrent neural network (RNNs), spiking neural network (SNNs), etc. This paper proposes the deployment of spectral graph convolutional networks (GCNs) on memristive crossbars. Further, based on the structure of GCNs (extremely high sparsity and unbalanced non-zero data distribution) and the neuromorphic characteristics of memristive crossbar circuit, we propose the acceleration method that consists of Sparse Laplace Matrix Reordering and Diagonal Block Matrix Multiplication. The simulated experiment on memristor crossbars achieves 90.3% overall accuracy on the supervised learning graph dataset (QM7), and compared with the original computation, the proposed acceleration computing framework (with half-size diagonal blocks) achieves a 27.3% reduction of memristor number. Additionally, on the unsupervised learning dataset (Karate club), our method shows no loss of accuracy with half-size diagonal block mapping and reaches a 32.2% reduction of memristor number.
Please use this identifier to cite or link to this item: