LPU

LPU (which stands for Learning from Positive and Unlabeled data) is a text learning or classification system that learns from a set of positive documents and a set of unlabeled documents (without labeled negative documents). This type of learning is different from classic text learning/classification, in which both positive and negative training documents are required. Given a set of positive documents and a set of unlabeled documents, the LPU algorithm learns a classifier in two steps:

• Step 1 : Identifying a set of reliable negative documents from the unlabeled set. For this step, LPU has three techniques, i.e., spy, roc (rocchio), nb (naive bayes) and DNF. In all these techniques, the unlabeled set is treated as negative data. In Spy technique you sample a certain % of positive examples and put them into unlabeled set to act as “spies”.Then run a classification algorithm assuming all unlabeled examples are negative, we will know the behavior of those actual positive examples in the unlabeled set through the “spies”.We can then extract reliable negative examples from the unlabeled set more accurance.
• Step 2 : Building and selecting a classifier, which consists of two sub-steps:
1. Building a set of classifiers by iteratively applying a classification algorithm. For this step, LPU has two techniques, SVM(Support vector machines ) and EM (Expectation Maximization).
2. Selecting a good classifier from the set of classifiers constructed above. We call this sub-step "catching a good classifier".
LPU system can be used for retrieval or classification. For retrieval, the document collection is the unlabeled set, which is also the test set. For classification, you can provide a separate test set that is different from the unlabeled set used in training.