← Search

Jian L\"{u}

2 accepted papers

2023

Learning with Logical Constraints but without Shortcut Satisfaction

ICLR 2023top-25%

Recent studies have started to explore the integration of logical knowledge into deep learning via encoding logical constraints as an additional loss function. However, existing approaches tend to vacuously satisfy logical constraints through shortcuts, failing to fully exploit the knowledge. In thi…

2023

Softened Symbol Grounding for Neuro-symbolic Systems

ICLR 2023poster

Neuro-symbolic learning generally consists of two separated worlds, i.e., neural network training and symbolic constraint solving, whose success hinges on symbol grounding, a fundamental problem in AI. This paper presents a novel, softened symbol grounding process, bridging the gap between the two…