Nimble GNN Embedding with Tensor-Train Decomposition
This addresses the need for efficient GPU-based training of GNNs on large graphs without node features, offering a domain-specific incremental improvement.
The paper tackles the problem of compactly representing embedding tables for graph neural networks (GNNs) in scenarios lacking node features, using tensor-train decomposition to reduce size by 1,659 to 81,362 times on benchmark datasets while achieving comparable or better accuracy and speedups on multi-GPU systems.
This paper describes a new method for representing embedding tables of graph neural networks (GNNs) more compactly via tensor-train (TT) decomposition. We consider the scenario where (a) the graph data that lack node features, thereby requiring the learning of embeddings during training; and (b) we wish to exploit GPU platforms, where smaller tables are needed to reduce host-to-GPU communication even for large-memory GPUs. The use of TT enables a compact parameterization of the embedding, rendering it small enough to fit entirely on modern GPUs even for massive graphs. When combined with judicious schemes for initialization and hierarchical graph partitioning, this approach can reduce the size of node embedding vectors by 1,659 times to 81,362 times on large publicly available benchmark datasets, achieving comparable or better accuracy and significant speedups on multi-GPU systems. In some cases, our model without explicit node features on input can even match the accuracy of models that use node features.