Deep neural networks can capture the intricate interaction history information between queries and documents, because of their many complicated nonlinear units, allowing them to provide correct search recommendations. However, service providers frequently face more complex obstacles in real-world circumstances, such as deployment cost constraints and fairness requirements. Knowledge distillation, which transfers the knowledge of a well-trained complex model (teacher) to a simple model (student), has been proposed to alleviate the former concern, but the best current distillation methods focus only on how to make the student model imitate the predictions of the teacher model. To better facilitate the application of deep models, we propose a fair information retrieval framework based on knowledge distillation. This framework can improve the exposure-based fairness of models while considerably decreasing model size. Our extensive experiments on three huge datasets show that our proposed framework can reduce the model size to a minimum of 1% of its original size while maintaining its black-box state. It also improves fairness performance by 15%~46% while keeping a high level of recommendation effectiveness.
翻译:深神经网络可以捕捉查询和文件之间错综复杂的交互历史信息,因为它们有许多复杂的非线性单元,允许它们提供正确的搜索建议。然而,服务提供者经常在现实世界环境中面临更复杂的障碍,如部署成本限制和公平要求。 知识蒸馏(将训练有素的复杂模型(教师)的知识转移至简单模型(学生)的建议,但目前最佳的蒸馏方法只侧重于如何使学生模型模仿教师模型的预测。为了更好地促进深层次模型的应用,我们提议了一个基于知识蒸馏的公平信息检索框架。这个框架可以提高模型基于暴露的公平性,同时大大缩小模型的规模。我们在三个庞大的数据集上进行的广泛实验表明,我们提议的框架可以将模型的大小减少到其原有规模的至少1%,同时保持其黑盒状态。它还将公平性表现提高15 ⁇ 46%,同时保持高水平的建议效果。