Our paper “MemMAP: Compact and Generalizable Meta-LSTM Models for Memory Access Prediction” has been accepted as a full paper at the 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2020. This paper proposes a clustered meta-learning-based approach to obtain more general prediction models that can achieve high accuracy of memory access prediction after a small number of gradient steps and can even generalize to unseen/new applications.
