学习用于抽象视觉推理的可微逻辑程序
Learning Differentiable Logic Programs for Abstract Visual Reasoning
AI总结：
针对抽象视觉推理中一阶逻辑表达受限与内存开销大的问题，提出图基可微前向推理器NEUMANN及高效结构学习算法，并引入幕后视觉推理任务，实验表明其性能优于神经、符号及神经符号基线。
摘要：
视觉推理对于构建能够理解世界并在感知之外进行问题求解的智能体至关重要。可微前向推理已被开发出来，用于将推理与基于梯度的机器学习范式相结合。然而，由于内存开销较大，大多数现有方法未能充分发挥一阶逻辑的表达能力，从而缺失了解决抽象视觉推理的关键能力；在该任务中，智能体需要在不同场景下利用抽象概念进行类比推理。为克服这一问题，我们提出了NEUro-symbolic Message-pAssiNg reasoNer（NEUMANN），这是一种基于图的可微前向推理器，能够以内存高效的方式传递消息，并处理带有函子的结构化程序。此外，我们提出了一种计算高效的结构学习算法，用于在复杂视觉场景上进行解释性程序归纳。在评估方面，除了常规视觉推理任务之外，我们还提出了一个新任务——幕后视觉推理，其中智能体需要学习抽象程序，然后通过想象未观察到的场景来回答查询。我们通过实验证明，NEUMANN能够高效地解决视觉推理任务，并优于神经、符号以及神经符号基线方法。
英文摘要：
Visual reasoning is essential for building intelligent agents that understand the world and perform problem-solving beyond perception. Differentiable forward reasoning has been developed to integrate reasoning with gradient-based machine learning paradigms. However, due to the memory intensity, most existing approaches do not bring the best of the expressivity of first-order logic, excluding a crucial ability to solve abstract visual reasoning, where agents need to perform reasoning by using analogies on abstract concepts in different scenarios. To overcome this problem, we propose NEUro-symbolic Message-pAssiNg reasoNer (NEUMANN), which is a graph-based differentiable forward reasoner, passing messages in a memory-efficient manner and handling structured programs with functors. Moreover, we propose a computationally-efficient structure learning algorithm to perform explanatory program induction on complex visual scenes. To evaluate, in addition to conventional visual reasoning tasks, we propose a new task, visual reasoning behind-the-scenes, where agents need to learn abstract programs and then answer queries by imagining scenes that are not observed. We empirically demonstrate that NEUMANN solves visual reasoning tasks efficiently, outperforming neural, symbolic, and neuro-symbolic baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
