Curriculum Abductive Learning

TL;DR

Curriculum Abductive Learning (C-ABL) enhances abductive learning by progressively integrating knowledge base sub-bases, improving training stability, convergence, and accuracy in complex scenarios.

Contribution

C-ABL introduces a curriculum-based approach that leverages knowledge base structure to stabilize and accelerate abductive learning training.

Findings

C-ABL outperforms previous methods in accuracy.

Training stability and convergence speed are significantly improved.

Effective in complex knowledge base settings.

Abstract

Abductive Learning (ABL) integrates machine learning with logical reasoning in a loop: a learning model predicts symbolic concept labels from raw inputs, which are revised through abduction using domain knowledge and then fed back for retraining. However, due to the nondeterminism of abduction, the training process often suffers from instability, especially when the knowledge base is large and complex, resulting in a prohibitively large abduction space. While prior works focus on improving candidate selection within this space, they typically treat the knowledge base as a static black box. In this work, we propose Curriculum Abductive Learning (C-ABL), a method that explicitly leverages the internal structure of the knowledge base to address the ABL training challenges. C-ABL partitions the knowledge base into a sequence of sub-bases, progressively introduced during training. This reduces the abduction space throughout training and enables the model to incorporate logic in a stepwise, smooth way. Experiments across multiple tasks show that C-ABL outperforms previous ABL implementations, significantly improves training stability, convergence speed, and final accuracy, especially under complex knowledge setting.