Few-shot graph learning with robust and energy-efficient memory-augmented graph neural network (MAGNN) based on homogeneous computing-in-memory

作者：Woyu Zhang, Shaocong Wang, Yi Li, Xiaoxin Xu, Danian Dong, Nanjia Jiang, Fei Wang, Zeyu Guo, Renrui Fang, Chunmeng Dou, Kai Ni, Zhongrui Wang, Dashan Shang, Ming Liu · 发表于：2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits) · 年份：2022 · DOI：10.1109/vlsitechnologyandcir46769.2022.9830418 · 被引用次数：11 · 研究领域：Ferroelectric and Negative Capacitance Devices、Advanced Memory and Neural Computing、Machine Learning and ELM

Learning graph structured data from limited examples on-the-fly is a key challenge to smart edge devices. Here, we present the first chip-level demonstration of few-shot graph learning which homogeneously implements both the controller and associative memory of a memory-augmented graph neural network using a 1T1R resistive random-access memory (RRAM). Leveraging the in-memory computing paradigm, we validated the high end-to-end accuracy of 78% (GPU baseline 80%) and robustness on node classification of CORA dataset, while achieved 70-fold reduction in latency and 60-fold reduction in energy consumption compared with conventional digital systems.