Relaxed Oracles for Semi-Supervised Clustering
This addresses the challenge of noisy supervision in clustering for applications relying on human input, though it is incremental as it builds on existing weak oracle models.
The paper tackles the problem of unreliable human supervision in semi-supervised clustering by allowing oracles to give 'not-sure' answers, and it shows that a small query complexity suffices for high-probability effective clustering with experimental validation on synthetic and real data.
Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm to handle such uncertainties in query responses. Two realistic weak oracle models are considered where ambiguity in answering depends on the distance between two points. We show that a small query complexity is adequate for effective clustering with high probability by providing better pairs to the weak oracle. Experimental results on synthetic and real data show the effectiveness of our approach in overcoming supervision uncertainties and yielding high quality clusters.