SPARE: A Single-Pass Neural Model for Relational Databases
This addresses the problem of slow training for deep learning on relational databases, which is incremental as it builds on GNN approaches.
The paper tackles the inefficiency of training Graph Neural Networks (GNNs) on large relational databases by proposing SPARE, a single-pass neural model that achieves similar accuracies while significantly speeding up training and inference, as demonstrated in empirical evaluations.
While there has been extensive work on deep neural networks for images and text, deep learning for relational databases (RDBs) is still a rather unexplored field. One direction that recently gained traction is to apply Graph Neural Networks (GNNs) to RBDs. However, training GNNs on large relational databases (i.e., data stored in multiple database tables) is rather inefficient due to multiple rounds of training and potentially large and inefficient representations. Hence, in this paper we propose SPARE (Single-Pass Relational models), a new class of neural models that can be trained efficiently on RDBs while providing similar accuracies as GNNs. For enabling efficient training, different from GNNs, SPARE makes use of the fact that data in RDBs has a regular structure, which allows one to train these models in a single pass while exploiting symmetries at the same time. Our extensive empirical evaluation demonstrates that SPARE can significantly speedup both training and inference while offering competitive predictive performance over numerous baselines.