no code implementations • 21 Jun 2022 • Chunxing Yin, Da Zheng, Israt Nisa, Christos Faloutos, George Karypis, Richard Vuduc
This paper describes a new method for representing embedding tables of graph neural networks (GNNs) more compactly via tensor-train (TT) decomposition.
1 code implementation • 25 Jan 2021 • Chunxing Yin, Bilge Acun, Xing Liu, Carole-Jean Wu
TT-Rec achieves 117 times and 112 times model size compression, for Kaggle and Terabyte, respectively.