← 研踪 PaperTrailarXiv:2603.18436 · v2
AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning Architecture
首次提交 2026-03-19 10:51
版本更新 2026-11-04 11:44
雷达观测 2026-11-05 11:10
摘要
Neuro-symbolic systems typically combine neural perception with discrete symbolic solvers, limiting end-to-end optimization. We introduce Attention-Based Soft Answer Sets (AS$^2$), a fully differentiable neuro-symbolic architecture that replaces discrete solving with a continuous approximation of the Answer Set Programming (ASP) immediate-consequence operator $T_P$. AS$^2$ maintains probability distributions over finite symbol domains and learns by minimizing the fixed-point residual of a probabilistic version of $T_P$, enabling differentiation through constraint checking without external solvers during training or inference. For spatial constraint-satisfaction tasks, AS$^2$ replaces positional embeddings with constraint-group membership embeddings derived directly from declarative ASP specifications, making the model independent of arbitrary position indexing. On Visual Sudoku, AS$^2$ achieves 99.89% raw cell accuracy and 100% constraint satisfaction after greedy decoding, without external solvers. On CLEVR-Hans, AS2 achieves 99.94% on CLEVR-Hans3 and 87.77% on CLEVR-Hans7. These results demonstrate that differentiable fixed-point reasoning, constraint-aware attention, and declarative constraint specifications can match or outperform pipeline-based and solver-based neuro-symbolic approaches while preserving end-to-end differentiability.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-04 11:44 · 最新观测版本
AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning Architecture
Neuro-symbolic systems typically combine neural perception with discrete symbolic solvers, limiting end-to-end optimization. We introduce Attention-Based Soft Answer Sets (AS$^2$), a fully differentiable neuro-symbolic architecture that replaces discrete solving with a continuous approximation of the Answer Set Programming (ASP) immediate-consequence operator $T_P$. AS$^2$ maintains probability distributions over finite symbol domains and learns by minimizing the fixed-point residual of a probabilistic version of $T_P$, enabling differentiation through constraint checking without external solvers during training or inference. For spatial constraint-satisfaction tasks, AS$^2$ replaces positional embeddings with constraint-group membership embeddings derived directly from declarative ASP specifications, making the model independent of arbitrary position indexing. On Visual Sudoku, AS$^2$ achieves 99.89% raw cell accuracy and 100% constraint satisfaction after greedy decoding, without external solvers. On CLEVR-Hans, AS2 achieves 99.94% on CLEVR-Hans3 and 87.77% on CLEVR-Hans7. These results demonstrate that differentiable fixed-point reasoning, constraint-aware attention, and declarative constraint specifications can match or outperform pipeline-based and solver-based neuro-symbolic approaches while preserving end-to-end differentiability.
查看此版本解读 →查看此版本原文 ↗