Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization
This work provides an incremental improvement for researchers and practitioners needing more efficient GNN training by enhancing existing compression techniques.
The paper tackles the problem of reducing memory consumption in training large-scale graph neural networks by improving the EXACT activation compression method with block-wise quantization and better variance estimation, achieving over 15% further memory reduction and about 5% runtime speedup per epoch with minimal performance loss.
Efficient training of large-scale graph neural networks (GNNs) has been studied with a specific focus on reducing their memory consumption. Work by Liu et al. (2022) proposed extreme activation compression (EXACT) which demonstrated drastic reduction in memory consumption by performing quantization of the intermediate activation maps down to using INT2 precision. They showed little to no reduction in performance while achieving large reductions in GPU memory consumption. In this work, we present an improvement to the EXACT strategy by using block-wise quantization of the intermediate activation maps. We experimentally analyze different block sizes and show further reduction in memory consumption (>15%), and runtime speedup per epoch (about 5%) even when performing extreme extents of quantization with similar performance trade-offs as with the original EXACT. Further, we present a correction to the assumptions on the distribution of intermediate activation maps in EXACT (assumed to be uniform) and show improved variance estimations of the quantization and dequantization steps.