构建表征空间提升AI解决复杂推理题能力
Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Ability
- 设计表征空间框架，用学习到的表征替代依赖选项配置的原始方法
- 在Raven推理题上显著提升性能，超越传统端到端模型
- 适合关注认知推理与视觉表征的新研究者
本文深入探讨提升AI抽象推理能力的挑战，聚焦于涉及复杂类人概念的瑞文渐进矩阵（RPM）任务。首先指出，传统端到端的RPM求解模型严重依赖选项池配置，这种依赖限制了模型的推理能力。为此，本文提出Johnny架构——一种基于表征空间的RPM求解新框架。该框架通过表征提取模块与推理模块的协同运作，通过引入学习到的表征空间来补充原始的负向选项配置，显著增强推理性能。此外，为加强模型对局部特征间位置关系的捕捉能力，提出Spin-Transformer网络结构，并设计轻量级的Straw Spin-Transformer变体，通过参数共享和注意力机制优化降低计算开销。实验表明，Johnny与Spin-Transformer在RPM任务上均取得优异表现，为推进AI抽象推理能力提供了创新方法。
原文摘要 · Abstract (English)
This paper thoroughly investigates the challenges of enhancing AI's abstract reasoning capabilities, with a particular focus on Raven's Progressive Matrices (RPM) tasks involving complex human-like concepts. Firstly, it dissects the empirical reality that traditional end-to-end RPM-solving models heavily rely on option pool configurations, highlighting that this dependency constrains the model's reasoning capabilities. To address this limitation, the paper proposes the Johnny architecture - a novel representation space-based framework for RPM-solving. Through the synergistic operation of its Representation Extraction Module and Reasoning Module, Johnny significantly enhances reasoning performance by supplementing primitive negative option configurations with a learned representation space. Furthermore, to strengthen the model's capacity for capturing positional relationships among local features, the paper introduces the Spin-Transformer network architecture, accompanied by a lightweight Straw Spin-Transformer variant that reduces computational overhead through parameter sharing and attention mechanism optimization. Experimental evaluations demonstrate that both Johnny and Spin-Transformer achieve superior performance on RPM tasks, offering innovative methodologies for advancing AI's abstract reasoning capabilities.
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。