I read in an answer here :

If you only have a small set of labels but lots of unlabeled data, then you might try a Manifold Regularizer (i.e. Transductive SVM), with or without a non-linear Kernel

Is there implementation of Transductive SVM on Scikit-Learn ?

有帮助吗?

解决方案

No, Scikit-Learn has only the standard SVMs via Cython bindings to LibSVM

许可以下: CC-BY-SA归因
不隶属于 StackOverflow
scroll top