Task 016/017: End-to-End Performance Benchmark / Neuromorphic Design Flow

Abstract: Ensembles improve the accuracy and robustness of Graph Neural Networks (GNNs), but suffer from high latency and storage requirements. We propose GEENI, a new approach to creating efficient GNN ensembles through Error Node Isolation (ENI).  ENI identifies nodes that are likely to be incorrectly classified (error nodes) and suppresses their outgoing messages, leading to both computational and accuracy improvements. ENI also enables aggressive approximations of the models in the ensemble while maintaining accuracy. We propose techniques to create diverse ensembles and identify error nodes in GEENI. Our models are simultaneously up to 4.6% (3.8%) more accurate and up to 2.8X (5.7X) faster compared to non-ensemble (conventional ensemble) models.  

 

Bio: Amrit Nagarajan is a PhD student in the School of Electrical and Computer Engineering, Purdue University, working as a Research Assistant under the supervision of Prof. Anand Raghunathan. He received his B.E degree from Anna University, Chennai, India, in 2018. His research interests include approximate computing and hardware-aware software optimizations for efficient deep learning inference.