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.
|Original language||English (US)|
|Title of host publication||KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining|
|Publisher||Association for Computing Machinery|
|Number of pages||9|
|State||Published - Aug 14 2022|
|Event||28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States|
Duration: Aug 14 2022 → Aug 18 2022
|Name||Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining|
|Conference||28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022|
|Period||8/14/22 → 8/18/22|
Bibliographical notePublisher Copyright:
© 2022 ACM.
- graph neural networks
- tensor-train decomposition