Timezone: »

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
Matthias Fey · Jan Eric Lenssen · Frank Weichert · Jure Leskovec

Thu Jul 22 05:35 AM -- 05:40 AM (PDT) @

We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations, leading to constant GPU memory consumption in respect to input node size without dropping any data. While existing solutions weaken the expressive power of message passing due to sub-sampling of edges or non-trainable propagations, our approach is provably able to maintain the expressive power of the original GNN. We achieve this by providing approximation error bounds of historical embeddings and show how to tighten them in practice. Empirically, we show that the practical realization of our framework, PyGAS, an easy-to-use extension for PyTorch Geometric, is both fast and memory-efficient, learns expressive node representations, closely resembles the performance of their non-scaling counterparts, and reaches state-of-the-art performance on large-scale graphs.

Author Information

Matthias Fey (TU Dortmund University)
Jan Eric Lenssen (TU Dortmund)
Frank Weichert (Technical University of Dortmund)
Jure Leskovec (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors