HodgeRank with Information Maximization for Crowdsourced Pairwise Ranking Aggregation
This work addresses the challenge of optimizing budget allocation in crowdsourcing experiments, offering incremental improvements in sampling efficiency for domain-specific applications.
The paper tackles the problem of budget-limited crowdsourcing for pairwise ranking aggregation by proposing active sampling strategies based on information maximization within the HodgeRank framework, resulting in improved sampling efficiency compared to traditional schemes.
Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains. However, task requester usually has a limited amount of budget, thus it is desirable to have a policy to wisely allocate the budget to achieve better quality. In this paper, we study the principle of information maximization for active sampling strategies in the framework of HodgeRank, an approach based on Hodge Decomposition of pairwise ranking data with multiple workers. The principle exhibits two scenarios of active sampling: Fisher information maximization that leads to unsupervised sampling based on a sequential maximization of graph algebraic connectivity without considering labels; and Bayesian information maximization that selects samples with the largest information gain from prior to posterior, which gives a supervised sampling involving the labels collected. Experiments show that the proposed methods boost the sampling efficiency as compared to traditional sampling schemes and are thus valuable to practical crowdsourcing experiments.