Expertise Drift in Referral Networks

Learning-to-refer is a challenge in expert referral networks, wherein Active Learning helps experts (agents) estimate the skills of other connected experts for different categories of tasks that the initial expert cannot solve and therefore must seek referral to experts with more appropriate expertise. Prior research has investigated different reinforcement action selection algorithms to assess viability of the learning setting both with uninformative priors and with partially available noisy priors, where experts are allowed to advertise a subset of their skills to their colleagues. Prior to this work, time-varying expertise drift (e.g., experts learning with experience) has not been considered though it is an aspect that may often arise in practice. This paper addresses the challenge of referral learning with time-varying expertise, proposing Hybrid, a novel combination of Optimistic Thompson Sampling, Pessimistic Thompson Sampling and Distributed Interval Estimation Learning (DIEL). In our extensive empirical evaluation, considering both biased and unbiased drift, the proposed algorithm outperforms the previous state-of-the-art (DIEL) and approaches the drift-aware oracle upper bound.