高级检索
    朱海萍, 赵成成, 刘启东, 郑庆华, 曾疆维, 田锋, 陈妍. 基于互惠性约束的可解释就业推荐方法[J]. 计算机研究与发展, 2021, 58(12): 2660-2672. DOI: 10.7544/issn1000-1239.2021.20211008
    引用本文: 朱海萍, 赵成成, 刘启东, 郑庆华, 曾疆维, 田锋, 陈妍. 基于互惠性约束的可解释就业推荐方法[J]. 计算机研究与发展, 2021, 58(12): 2660-2672. DOI: 10.7544/issn1000-1239.2021.20211008
    Zhu Haiping, Zhao Chengcheng, Liu Qidong, Zheng Qinghua, Zeng Jiangwei, Tian Feng, Chen Yan. Reciprocal-Constrained Interpretable Job Recommendation[J]. Journal of Computer Research and Development, 2021, 58(12): 2660-2672. DOI: 10.7544/issn1000-1239.2021.20211008
    Citation: Zhu Haiping, Zhao Chengcheng, Liu Qidong, Zheng Qinghua, Zeng Jiangwei, Tian Feng, Chen Yan. Reciprocal-Constrained Interpretable Job Recommendation[J]. Journal of Computer Research and Development, 2021, 58(12): 2660-2672. DOI: 10.7544/issn1000-1239.2021.20211008

    基于互惠性约束的可解释就业推荐方法

    Reciprocal-Constrained Interpretable Job Recommendation

    • 摘要: 当前,基于协同过滤和隐因子模型的大学生就业推荐方法,仅考虑学生对就业单位单向偏好易导致“能力失配”,且一个用户一次就业的历史记录极易致负样本不可信,影响推荐性能,同时忽略了对推荐结果的可解释性需求.针对此,依据多任务学习的思路,设计并构建了基于互惠性约束的可解释就业推荐方法.其中,引入注意力机制与模糊门机制,提取并自适应聚合学生与就业单位双向的偏好与需求,缓解“能力失配”问题;提出面向就业意图和就业特征的推荐解释方法,满足可解释性需求;提出基于相似度的随机负采样方法,克服负样本不置信问题.在某高校5届毕业生就业真实数据集上的实验结果表明:相比于多个经典和同时代的推荐方法,所提方法在AUC指标上提升超6%,并且通过消融实验验证了所提方法中各模块的有效性.

       

      Abstract: Current college student job recommendation methods based on collaborative filtering and latent factor model only consider job interests of students and ignore the requirements of employers, often leading to ‘capability mismatch’. Moreover, in most of the historical employment data, only one employment record per student is stored, which leads to unreliable negative samples and affects recommendation performance. Additionally, many methods ignore the demand for recommendation result interpretability. To this end, inspired by the idea of multi-task learning, we construct a reciprocal-constrained interpretable job recommendation method. In which, we introduce attention mechanism to extract bidirectional preferences of both students and employers, and then use fuzzy gate mechanism to adaptively aggregate them in order to alleviate the problem of capability mismatch. Next, we propose a recommendation interpretation module oriented to employer intention and employer characteristics to meet the interpretability demand. We also propose a similarity-based negative sampling method to solve the problem of incredible negative samples. The results of experiment on a real-world undergraduate employment dataset of five years, EMDAU, indicate that our method outperforms other classic and state-of-art recommendation methods and has over 6% improvement in AUC. Besides, the results of ablation experiments conducted verify the effectiveness of each module in our method.

       

    /

    返回文章
    返回