发表机构
Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出溯因候选保留（ACR）方法，通过平衡监督锐度与模型质量覆盖，选择保留候选子集以提升溯因学习中概念准确率。
AI 中文摘要
溯因学习将神经感知与符号推理相结合，利用溯因生成的解释来监督感知模型。同一符号目标的多个有效解释可能对相同输入分配冲突的标签。常见策略要么选择单一候选作为伪标签，这可能强化错误的分配；要么对所有候选进行加权，这可能将监督分散到相互竞争的标签上。这些风险促使我们选择保留一个子集，以平衡监督的锐度与模型质量的覆盖。为指导这一选择，我们利用保留的不确定性、丢弃的模型质量以及模型失配来界定坐标级监督误差。对于固定的模型和训练对，仅前两项依赖于保留集。我们提出了溯因候选保留（ACR），该方法利用这些项来指导贪婪添加，当候选的恢复质量超过保留不确定性的增加时接受该候选。实验表明，在大多数评估的聚合模加法设置中，ACR相比单候选基线和A3BL提高了概念准确率。目标消融实验支持联合使用不确定性和后验质量。
英文摘要
Abductive learning combines neural perception with symbolic reasoning, using explanations generated by abduction to supervise the perception model. Multiple valid explanations of the same symbolic target can assign conflicting labels to the same inputs. Common policies select a single candidate as a pseudo-label, which may reinforce mistaken assignments, or weight all candidates, which may spread supervision across competing labels. These risks motivate selecting a retained subset to balance supervision sharpness and model-mass coverage. To guide this choice, we bound the coordinate-level supervision error using retained uncertainty, discarded model mass, and model mismatch. For a fixed model and training pair, only the first two terms depend on the retained set. We propose Abductive Candidate Retention (ACR), which uses these terms to guide greedy additions, accepting a candidate when its recovered mass exceeds the increase in retained uncertainty. Experiments show that ACR improves concept accuracy over single-candidate baselines and A3BL in most evaluated aggregated mod-addition settings. Objective ablations support the joint use of uncertainty and posterior mass.
