Scallop: End-to-end Differentiable Reasoning at Scale

Approaches to systematically combine symbolic reasoning with deep learning have demonstrated remarkable promise in terms of accuracy and generalizability. However, the complexity of exact probabilistic reasoning renders these methods inefficient for real-world, data-intensive machine learning applications. We propose Scallop, a scalable differentiable probabilistic Datalog engine equipped with a top-k approximate inference algorithm. We show that our algorithm significantly reduces the amount of computation needed for inference and learning tasks without affecting their principal outcomes. To evaluate Scallop, we craft a challenging dataset, VQAR, comprising 4 million Visual Question Answering (VQA) instances that necessitate reasoning about real-world images with external common-sense knowledge. We demonstrate that Scallop not only scales to these instances, but also outperforms state-of-the-art neural-based approaches by 12.44%.