习题推荐是利用推荐算法将习题推荐给学生的任务,点击率(CTR)预测则是推荐领域的主流研究方向之一,现有的大部分习题推荐模型没有重视注意力机制的创新,因而落后于CTR预测领域。为了研究CTR预测模型中注意力机制在教育领域的应用前景,该文提出一种分层次学习注意力权重的双路注意力推荐模型(SEFM)。该模型通过因子分解机(FM)与压缩激励注意力网络(SENET)两个注意力机制的并行运行,实现学习特征之间的关系以及特征本身的权重,从而完成推荐。在两个CTR广告数据集与一个教育数据集上的实验表明,SEFM能准确地学习特征在多种维度上的权重,在两个评价指标上的表现均优于现有的先进基准模型。
Abstract
Question recommendation is a task of recommending Question to students by using recommendation algorithm. Click-through rate (CTR) prediction is one of the mainstream research directions in the recommendation field. To explore the attention mechanism in the CTR prediction model, this paper proposes a two-way attention recommendation model (SEFM) with hierarchical learning of attention weights. This model can learn the relationship between features and the weight of the feature itself through the parallel operation of the two attention mechanisms via factorization machine (FM) and compressed excitation attention network (SENET). Experiments on two CTR advertising datasets and one educational dataset demonstrate that SEFM can outperform existing state-of-the-art benchmark models on two evaluation metrics.
关键词
推荐系统 /
点击率预测 /
习题推荐 /
个性化学习
{{custom_keyword}} /
Key words
recommendation system /
CTR prediction /
question recommendation /
personalized learning
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] WEN H, ZHANG J, LIN Q, et al. Multi level deep cascade trees for conversion rate prediction in recommendation system[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York, USA: ACM Press,2019, 33(01): 338-345.
[2] RENDLE S. Factorization machines[C]//Proceedings of the IEEE International Conference on Data Mining.Washington D C,USA: IEEE Press, 2010: 995-1000.
[3] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington D C,USA: IEEE Press, 2016: 770-778.
[4] CHO K, VAN MERRINBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv preprint arXiv: 1406.1078, 2014.
[5] HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web. Republic and Canton of Geneva, Switzerland, WWW Press, 2017: 173-182.
[6] GUO H, TANG R, YE Y, et al. DeepFM: A factorization-machine based neural network for CTR prediction[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. New York, USA: ACM Press, 2017: 1725-1731.
[7] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30.
[8] XIAO J, YE H, HE X, et al. Attentional factorization machines: learning the weight of feature interactions via attention networks[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. New York, USA: ACM Press, 2017: 3119-3125.
[9] HUANG T, ZHANG Z, ZHANG J. FiBiNET: Combining feature importance and bilinear feature interaction for click-through rate prediction[C]//Proceedings of the 13th ACM Conference on Recommender Systems. New York, USA: ACM Press, 2019: 169-177.
[10] SONG W, SHI C, XIAO Z, et al. Autoint: Cautomatic feature interaction learning via self-attentive neural networks[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York, USA: ACM Press,2019: 1161-1170.
[11] LIAN J, ZHOU X, ZHANG F, et al. xDeepFM: Combining explicit and implicit feature interactions for recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, USA: ACM Press, 2018: 1754-1763.
[12] LU W, YU Y, CHANG Y, et al. A dual input-aware factorization machine for CTR prediction[C]//Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence. New York, USA: ACM Press, 2021: 3139-3145.
[13] 阎世宏,马为之,张敏,等.结合用户长短期兴趣的深度强化学习推荐方法[J].中文信息学报, 2021, 35(8): 107-116.
[14] 刘淇,陈恩红,朱天宇,等.面向在线智慧学习的教育数据挖掘技术研究[J].模式识别与人工智能,2018,31(01): 77-90.
[15] 刘昱良. 基于知识图谱的个性化学习资源推荐研究[D].新乡:河南师范大学硕士学位论文,2018.
[16] 朱天宇,黄振亚,陈恩红,等.基于认知诊断的个性化试题推荐方法[J].计算机学报,2017,40(01): 176-191.
[17] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D C,USA: IEEE Press, 2018: 7132-7141.
[18] LING C X, HUANG J, ZHANG H. AUC: A statistically consistent and more discriminating measurethan accuracy[C]//Proceedings of the 18th International Joint Conference on Artificial Intelligence. Acapulco: IJCAI,2003: 519-524.
[19] WANG R, FU B, FU G, et al. Deep & cross network for ad click predictions[C]//Proceedings of the ADKDD. 2017: 1-7.
[20] WANG F,WANG Y, LI D, et al. Enhancing CTR prediction with context-aware feature representation learning[J]. arXiv preprint arXiv: 2204.08758, 2022.
[21] KINGMA D P, BA J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv: 1412.6980, 2014.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61672389);广州市大数据智能教育重点实验室(201905010009)
{{custom_fund}}
PDF(2717 KB)
