面向生成式抽象推理：通过规则抽象与选择完成Raven渐进矩阵
Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection
AI总结：
针对现有RPM求解器缺乏生成式推理能力的问题，提出基于规则抽象与选择的深度潜变量模型RAISE，在多类RPM任务上表现优于现有方法，具备处理未见规则属性组合的泛化能力。
摘要：
赋予机器抽象推理能力一直是人工智能领域的长期研究课题。Raven渐进矩阵（Raven's Progressive Matrix, RPM）被广泛用于探究机器智能中的抽象视觉推理，在该任务中模型需要分析潜在规则，并从候选图像中选择一张来补全图像矩阵。RPM测试的参与者可以通过推断并组合属性变化规则、想象矩阵任意位置的缺失图像，展现出强大的推理能力。然而，现有求解器在真实RPM测试中几乎无法体现这种能力。本文提出了一种基于规则抽象与选择（Rule AbstractIon and SElection, RAISE）的深度潜变量模型，用于解决答案生成问题。RAISE可将图像属性编码为潜概念，并抽象出作用于这些潜概念的原子规则。生成答案时，RAISE从全局知识集中为每个潜概念选择一条原子规则，共同构成某道RPM题目的潜在规则。在右下角位置和任意位置的答案生成实验中，RAISE在真实RPM数据集的大多数配置下表现优于对比求解器。在异常项识别任务和两种留出配置中，RAISE能够利用习得的潜概念与原子规则，找出矩阵中违反规则的图像，并处理规则与属性的未见组合问题。
英文摘要：
Endowing machines with abstract reasoning ability has been a long-term research topic in artificial intelligence. Raven's Progressive Matrix (RPM) is widely used to probe abstract visual reasoning in machine intelligence, where models will analyze the underlying rules and select one image from candidates to complete the image matrix. Participators of RPM tests can show powerful reasoning ability by inferring and combining attribute-changing rules and imagining the missing images at arbitrary positions of a matrix. However, existing solvers can hardly manifest such an ability in realistic RPM tests. In this paper, we propose a deep latent variable model for answer generation problems through Rule AbstractIon and SElection (RAISE). RAISE can encode image attributes into latent concepts and abstract atomic rules that act on the latent concepts. When generating answers, RAISE selects one atomic rule out of the global knowledge set for each latent concept to constitute the underlying rule of an RPM. In the experiments of bottom-right and arbitrary-position answer generation, RAISE outperforms the compared solvers in most configurations of realistic RPM datasets. In the odd-one-out task and two held-out configurations, RAISE can leverage acquired latent concepts and atomic rules to find the rule-breaking image in a matrix and handle problems with unseen combinations of rules and attributes.
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。
