通过优化因果链与互信息，提升模型抽象推理能力
DIO: Refining Mutual Information and Causal Chain to Enhance Machine Abstract Reasoning Ability
- 构建因果链模型，从图像到答案分步建模推理过程
- 在RPM测试中准确率显著提升，首次实现开放问答生成
- 适合关注抽象推理与可解释性研究的学者
尽管深度学习广泛应用，其抽象推理能力仍存瓶颈。本文以瑞文渐进矩阵（RPM）为基准，建模完整的因果链：图像 → 属性 → 进展模式 → 一致性 → 答案，并提出基线模型DIO。然而，DIO采用的互信息下界优化目标存在局限：边界松散且基于统计，忽视了因果主客体关联。为此，本文提出三项改进：1）引入可训练负样本（Brando），收紧变分下界；2）用高斯混合特征模型替代生成，提供无限加权负样本（WORLD），进一步紧化边界；3）加入元数据监督（DIEGO），弥合属性到模式间的语义鸿沟，使表征更符合人类规则。改进后模型在判别式RPM任务中表现大幅提升，并首次实现开放题型的有效答案生成。研究提供了因果驱动的设计范式、目标优化策略及跨模态洞察。
原文摘要 · Abstract (English)
Despite deep learning's broad success, its abstract-reasoning bottleneck persists. We tackle Raven's Progressive Matrices (RPM), the benchmark for pattern, reasoning and problem-solving intelligence. We model the full causal chain image $\rightarrow$ attributes $\rightarrow$ progressive patterns $\rightarrow$ consistency $\rightarrow$ answer and build the baseline DIO. Yet DIO's mutual-information lower-bound objective does not embed human logic: the bound is loose and statistic-based, ignoring causal subject-object links. We therefore present three refinements. 1) Brando introduces trainable negative options to tighten the variational bound. 2) WORLD replaces generation with a Gaussian-mixture feature model that supplies infinite, weighted negatives, further tightening the bound. 3) DIEGO adds metadata supervision to rectify the "attributes $\rightarrow$ patterns" semantic gap, aligning representations with human rules. These upgrades substantially boost discriminative RPM accuracy and, for the first time, let DIO generate valid answers in open-ended RPM. The work provides causal-driven design guidelines, objective-refinement strategies and cross-modal insights for abstract-reasoning research.
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。