SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data· SoftReason：高维感知数据上的完全可微神经软符号演绎推理架构
In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensional inputs. Further, the predicate vocabulary, argument structure, and trusted evidence are supplied by a Knowledge Graph (KG), or rule definitions. Classical neuro-symbolic pipelines have a discrete interface between perception and deduction. We present a neuro-soft-symbolic architecture for differentiable deductive reasoning over latent perceptual facts and knowledge-provided predicates. SoftReason removes the gradient gap by representing the deductive state as a local soft interpretation tensor over candidate constants and predicates. Perception proposes probabilistic base facts, KG triples enter as high-confidence soft evidence, and every query anchor, predicate choice,
将神经网络与软符号推理结合，实现高维感知数据上的完全可微演绎推理。
- 核心方法
- 提出SoftReason架构，用局部软解释张量表示演绎状态，使感知提供的概率基础事实与知识图谱的软证据能够无缝结合，实现端到端的可微推理。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 神经符号系统在处理高维感知数据时面临梯度中断的问题，以及如何融合感知和知识图谱信息进行推理。
- 关键实验
- 未提供
- 主要贡献
- 解决了神经符号系统中的梯度中断问题，提供了一种新的高维感知数据和知识融合的可微演绎推理方法。
- 意义与局限
- 意义在于突破了传统神经符号系统的局限，但目前实验数据缺失，具体应用效果有待验证。