Resource-Bounded Information Gathering for Correlation Clustering

We present a new class of problems, called resource-bounded information gathering for correlation clustering. Our goal is to perform correlation clustering under circumstances in which accuracy may be improved by augmenting the given graph with additional information. This information is obtained by querying an external source under resource constraints. The problem is to develop the most effective query selection strategy to minimize some loss function on the resulting partitioning. We motivate the problem using an entity resolution task. 1 Problem Definition The standard correlation clustering problem on a graph with real-valued edge weights is as follows: there exists a fully connected graph G(V, E) with n nodes and edge weights, wij ∈ [−1, +1]. The goal is to partition the vertices in V by minimizing the inconsistencies with the edge weights [1]. That is, we want to find a partitioning that maximizes the objective function F = ij wijf(i, j), where f(i, j) = 1 when vi and vj ...

• Type: Conference
• Year: 2007
• Where: COLT
• Authors: Pallika Kanani, Andrew McCallum
• Keywords: Additional Information, COLT 2007, Correlation Clustering, Edge Weights, Machine Learning