从图像中自动学习可解释的逻辑规则，无需标签支持。
Visual Perceptual to Conceptual First-Order Rule Learning Networks
- 构建可微分框架γILP，实现图像常量替换到规则结构的端到端学习。
- 在符号数据与图像数据上均表现优异，包括基安迪尼图案数据集。
- 适合需要模型可解释性与视觉推理能力的研究者使用。
规则学习在深度学习中至关重要，尤其在可解释人工智能和提升大语言模型推理能力方面。现有方法主要针对符号数据，而从无标签图像数据中自动学习规则并发明谓词仍是挑战。本文提出γILP框架，实现从图像常量替换到规则结构诱导的完全可微分流程。大量实验表明，γILP不仅在经典符号关系数据集上表现良好，也在关系图像数据和纯图像数据集（如Kandinsky模式）上取得优异效果。
原文摘要 · Abstract (English)
Learning rules plays a crucial role in deep learning, particularly in explainable artificial intelligence and enhancing the reasoning capabilities of large language models. While existing rule learning methods are primarily designed for symbolic data, learning rules from image data without supporting image labels and automatically inventing predicates remains a challenge. In this paper, we tackle these inductive rule learning problems from images with a framework called γILP, which provides a fully differentiable pipeline from image constant substitution to rule structure induction. Extensive experiments demonstrate that γILP achieves strong performance not only on classical symbolic relational datasets but also on relational image data and pure image datasets, such as Kandinsky patterns.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。