论文标题
歧视性和神经符号半监督学习的概率模型
A Probabilistic Model for Discriminative and Neuro-Symbolic Semi-Supervised Learning
论文作者
论文摘要
通过组合利用数据分布不同方面的方法，例如一致性正则化依赖于$ p（x）$的属性，而熵最小化涉及标签分布$ p（y | x）$。为了关注后者，我们提出了一个歧视性SSL的概率模型，该模型反映了其经典的生成对应物。在假设$ y | x $是确定性的下，潜在变量的先前变量变为离散。我们表明，可以将几种众所周知的SSL方法解释为近似此事先，并且可以改进。我们将判别模型扩展到神经符号SSL，其中标签具有满足逻辑规则，通过显示此类规则直接与上述先验有关，从而证明了将统计学习和逻辑推理联系起来的方法家族，并将其与常规SSL统一。
Much progress has been made in semi-supervised learning (SSL) by combining methods that exploit different aspects of the data distribution, e.g. consistency regularisation relies on properties of $p(x)$, whereas entropy minimisation pertains to the label distribution $p(y|x)$. Focusing on the latter, we present a probabilistic model for discriminative SSL, that mirrors its classical generative counterpart. Under the assumption $y|x$ is deterministic, the prior over latent variables becomes discrete. We show that several well-known SSL methods can be interpreted as approximating this prior, and can be improved upon. We extend the discriminative model to neuro-symbolic SSL, where label features satisfy logical rules, by showing such rules relate directly to the above prior, thus justifying a family of methods that link statistical learning and logical reasoning, and unifying them with regular SSL.
