AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

Enhancing Recommendation with Denoising Auxiliary Task

College of Big Data and Information Engineering, Guizhou University, Guiyang 550025, China
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
University of Chinese Academy of Sciences, Beijing 100049, China
Show Author Information

Abstract

The historical interaction sequences of users play a crucial role in training recommender systems that can accurately predict user preferences. However, due to the arbitrariness of user behaviors, the presence of noise in these sequences poses a challenge to predicting their next actions in recommender systems. To address this issue, our motivation is based on the observation that training noisy sequences and clean sequences (sequences without noise) with equal weights can impact the performance of the model. We propose the novel self-supervised Auxiliary Task Joint Training (ATJT) method aimed at more accurately reweighting noisy sequences in recommender systems. Specifically, we strategically select subsets from users’ original sequences and perform random replacements to generate artificially replaced noisy sequences. Subsequently, we perform joint training on these artificially replaced noisy sequences and the original sequences. Through effective reweighting, we incorporate the training results of the noise recognition model into the recommender model. We evaluate our method on three datasets using a consistent base model. Experimental results demonstrate the effectiveness of introducing the self-supervised auxiliary task to enhance the base model’s performance.

Keywords

auxiliary task learningrecommender systemsequence denoising

Electronic Supplementary Material

Download File(s)
JCST-2312-14069-Highlights.pdf (157.2 KB)

References

[1]
Zhou R, Khemmarat S, Gao L. The impact of YouTube recommendation system on video views. In Proc. the 10th ACM SIGCOMM Conference on Internet Measurement, Nov. 2010, pp.404–410. DOI: 10.1145/1879141.1879193.
Crossref
[2]
Lee D, Hosanagar K. Impact of recommender systems on sales volume and diversity. In Proc. the 35th International Conference on Information Systems—Building a Better World through Information Systems, Dec. 2014.
[3]
Lin T H, Gao C, Li Y. CROSS: Cross-platform recommendation for social e-commerce. In Proc. the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2019, pp.515–524. DOI: 10.1145/3331184.3331191.
Crossref
[4]
Hidasi B, Karatzoglou A, Baltrunas L, Tikk D. Session-based recommendations with recurrent neural networks. In Proc. the 4th International Conference on Learning Representations, May 2016.
[5]
Ni Y, Ou D, Liu S, Li X, Ou W, Zeng A, Si L. Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks. In Proc. the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug. 2018, pp.596–605. DOI: 10.1145/3219819.3219828.
Crossref
[6]
Zhou G, Mou N, Fan Y, Pi Q, Bian W, Zhou C, Zhu X, Gai K. Deep interest evolution network for click-through rate prediction. In Proc. the 33rd AAAI Conference on Artificial Intelligence, Jul. 2019, pp.5941–5948. DOI: 10.1609/aaai.v33i01.33015941.
Crossref
[7]
Zhou G, Zhu X, Song C, Fan Y, Zhu H, Ma X, Yan Y, Jin J, Li H, Gai K. Deep interest network for click-through rate prediction. In Proc. the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug. 2018, pp.1059–1068. DOI: 10.1145/3219819.3219823.
Crossref
[8]
Chen H, Lin Y, Pan M, Wang L, Yeh C C M, Li X, Zheng Y, Wang F, Yang H. Denoising self-attentive sequential recommendation. In Proc. the 16th ACM Conference on Recommender Systems, Sept. 2022, pp.92–101. DOI: 10.1145/3523227.3546788.
Crossref
[9]
Davidson J, Liebald B, Liu J, Nandy P, Van Vleet T, Gargi U, Gupta S, He Y, Lambert M, Livingston B, Sampath D. The YouTube video recommendation system. In Proc. the 4th ACM Conference on Recommender Systems, Sept. 2010, pp.293–296. DOI: 10.1145/1864708.1864770.
Crossref
[10]
Wang J, Zhang Y. Opportunity model for e-commerce recommendation: Right product; right time. In Proc. the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 28–Aug. 1, 2013, pp.303–312. DOI: 10.1145/2484028.2484067.
Crossref
[11]
Cheng H T, Koc L, Harmsen J, Shaked T, Chandra T, Aradhye H, Anderson G, Corrado G, Chai W, Ispir M, Anil R, Haque Z, Hong L, Jain V, Liu X, Shah H. Wide & deep learning for recommender systems. In Proc. the 1st Workshop on Deep Learning for Recommender Systems, Sept. 2016, pp.7–10. DOI: 10.1145/2988450.2988454.
Crossref
[12]
Guo H, Tang R, Ye Y, Li Z, He X. DeepFM: A factorization-machine based neural network for CTR prediction. In Proc. the 26th International Joint Conference on Artificial Intelligence, Aug. 2017, pp.1725–1731.
Crossref
[13]
Lin W, Zhao X, Wang Y, Xu T, Wu X. AdaFS: Adaptive feature selection in deep recommender system. In Proc. the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug. 2022, pp.3309–3317. DOI: 10.1145/3534678.3539204.
Crossref
[14]
Wang R, Fu B, Fu G, Wang M. Deep & cross network for ad click predictions. In Proc. the ADKDD2017, Aug. 2017, Article No. 12. DOI: 10.1145/3124749.3124754.
Crossref
[15]

Fang H, Zhang D, Shu Y, Guo G. Deep learning for sequential recommendation: Algorithms, influential factors, and evaluations. ACM Trans. Information Systems, 2020, 39(1): Article No. 10. DOI: 10.1145/3426723.
Crossref Google Scholar
[16]
Wang T, Xia L, Huang C. Denoised self-augmented learning for social recommendation. In Proc. the 32nd International Joint Conference on Artificial Intelligence, Aug. 2023, pp.2324–2331.
Crossref
[17]
Fan Z, Xu K, Dong Z, Peng H, Zhang J, Yu P S. Graph collaborative signals denoising and augmentation for recommendation. In Proc. the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2023, pp.2037–2041. DOI: 10.1145/3539618.3591994.
Crossref
[18]
Wang W, Feng F, He X, Nie L, Chua T S. Denoising implicit feedback for recommendation. In Proc. the 14th ACM International Conference on Web Search and Data Mining, Mar. 2021, pp.373–381. DOI: 10.1145/3437963.3441800.
Crossref
[19]
Gantner Z, Drumond L, Freudenthaler C, Schmidt-Thieme L. Personalized ranking for non-uniformly sampled items. In Proc. the 2011 International Conference on KDD Cup 2011, Jan. 2011, pp.231–247.
[20]
Hu K, Li L, Xie Q, Liu J, Tao X. What is next when sequential prediction meets implicitly hard interaction? In Proc. the 30th ACM International Conference on Information & Knowledge Management, Nov. 2021, pp.710–719. DOI: 10.1145/3459637.3482492.
Crossref
[21]
Wang Z, Xu Q, Yang Z, Cao X, Huang Q. Implicit feedbacks are not always favorable: Iterative relabeled one-class collaborative filtering against noisy interactions. In Proc. the 29th ACM International Conference on Multimedia, Oct. 2021, pp.3070–3078. DOI: 10.1145/3474085.3475446.
Crossref
[22]
Qin Y, Wang P, Li C. The world is binary: Contrastive learning for denoising next basket recommendation. In Proc. the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2021, pp.859–868. DOI: 10.1145/3404835.3462836.
Crossref
[23]
Yu W, Qin Z. Sampler design for implicit feedback data by noisy-label robust learning. In Proc. the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2020, pp.861–870. DOI: 10.1145/3397271.3401155.
Crossref
[24]
Wang Y, Xin X, Meng Z, Jose J M, Feng F, He X. Learning robust recommenders through cross-model agreement. In Proc. the 2022 ACM Web Conference, Apr. 2022, pp.2015–2025. DOI: 10.1145/3485447.3512202.
Crossref
[25]
Lin W, Zhao X, Wang Y, Zhu Y, Wang W. AutoDenoise: Automatic data instance denoising for recommendations. In Proc. the 2023 ACM Web Conference, Apr. 30–May 4, 2023, pp.1003–1011. DOI: 10.1145/3543507.3583339.
Crossref
[26]
He R, Kang W C, McAuley J. Translation-based recommendation. In Proc. the 11th ACM Conference on Recommender Systems, Aug. 2017, pp.161–169. DOI: 10.1145/3109859.3109882.
Crossref
[27]
He R, McAuley J. Fusing similarity models with Markov chains for sparse sequential recommendation. In Proc. the 16th IEEE International Conference on Data Mining (ICDM), Dec. 2016, pp.191–200. DOI: 10.1109/ICDM.2016.0030.
Crossref
[28]

Medsker L R, Jain L. Recurrent neural networks. Design and Applications, 2001, 5: 64–67.
Google Scholar
[29]
Graves A. Long short-term memory. In Supervised Sequence Labelling with Recurrent Neural Networks, Graves A (ed.), Springer, 2012, pp.37–45. DOI: 10.1007/978-3-642-24797-2_4.
Crossref
[30]
Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y. Transformer in transformer. In Proc. the 34th Advances in Neural Information Processing Systems, Dec. 2021, pp.15908–15919.
[31]
Fan X, Liu Z, Lian J, Zhao W X, Xie X, Wen J R. Lighter and better: Low-rank decomposed self-attention networks for next-item recommendation. In Proc. the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2021, pp.1733–1737. DOI: 10.1145/3404835.3462978.
Crossref
[32]
Tan Q, Zhang J, Yao J, Liu N, Zhou J, Yang H, Hu X. Sparse-interest network for sequential recommendation. In Proc. the 14th ACM International Conference on Web Search and Data Mining, Mar. 2021, pp.598–606. DOI: 10.1145/3437963.3441811.
Crossref
[33]
Xie X, Sun F, Liu Z, Wu S, Gao J, Zhang J, Ding B, Cui B. Contrastive learning for sequential recommendation. In Proc. the 38th IEEE International Conference on Data Engineering (ICDE), May 2022, pp.1259–1273. DOI: 10.1109/ICDE53745.2022.00099.
Crossref
[34]

Huang L, Ma Y, Liu Y, Du B D, Wang S, Li D. Position-enhanced and time-aware graph convolutional network for sequential recommendations. ACM Trans. Information Systems, 2023, 41(1): Article No. 6. DOI: 10.1145/3511700.
Crossref Google Scholar
[35]
He X, Deng K, Wang X, Li Y, Zhang Y, Wang M. LightGCN: Simplifying and powering graph convolution network for recommendation. In Proc. the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2020, pp.639–648. DOI: 10.1145/3397271.3401063.
Crossref
[36]
Mao K, Zhu J, Xiao X, Lu B, Wang Z, He X. UltraGCN: Ultra simplification of graph convolutional networks for recommendation. In Proc. the 30th ACM International Conference on Information & Knowledge Management, Nov. 2021, pp.1253–1262. DOI: 10.1145/3459637.3482291.
Crossref
[37]
Fan Z, Liu Z, Zhang J, Xiong Y, Zheng L, Yu P S. Continuous-time sequential recommendation with temporal graph collaborative transformer. In Proc. the 30th ACM International Conference on Information & Knowledge Management, Nov. 2021, pp.433–442. DOI: 10.1145/3459637.3482242.
Crossref
[38]
Kang W C, McAuley J. Self-attentive sequential recommendation. In Proc. the 2018 IEEE International Conference on Data Mining (ICDM), Nov. 2018, pp.197–206. DOI: 10.1109/ICDM.2018.00035.
Crossref
[39]
Zhou K, Wang H, Zhao W X, Zhu Y, Wang S, Zhang F, Wang Z, Wen J R. S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization. In Proc. the 29th ACM International Conference on Information & Knowledge Management, Oct. 2020, pp.1893–1902. DOI: 10.1145/3340531.3411954.
Crossref
[40]
Hu J, Chan Z, Zhang Y, Han S, Lou S, Liu B, Zhu H, Jiang Y, Xu J, Zheng B. PS-SA: An efficient self-attention via progressive sampling for user behavior sequence modeling. In Proc. the 32nd ACM International Conference on Information and Knowledge Management, Oct. 2023, pp.4639–4645. DOI: 10.1145/3583780.3615495.
Crossref
[41]
Du X, Yuan H, Zhao P, Qu J, Zhuang F, Liu G, Liu Y, Sheng V S. Frequency enhanced hybrid attention network for sequential recommendation. In Proc. the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2023, pp.78–88. DOI: 10.1145/3539618.3591689.
Crossref
[42]
Hjelm R D, Fedorov A, Lavoie-Marchildon S, Grewal K, Bachman P, Trischler A, Bengio Y. Learning deep representations by mutual information estimation and maximization. In Proc. the 7th International Conference on Learning Representations, May 2019.
[43]
Qiu R, Huang Z, Yin H, Wang Z. Contrastive learning for representation degeneration problem in sequential recommendation. In Proc. the 15th ACM International Conference on Web Search and Data Mining, Feb. 2022, pp.813–823. DOI: 10.1145/3488560.3498433.
Crossref
[44]

Hao B, Yin H, Zhang J, Li C, Chen H. A multi-strategy-based pre-training method for cold-start recommendation. ACM Trans. Information Systems, 2023, 41(2): 31. DOI: 10.1145/3544107.
Crossref Google Scholar
[45]
Chen Y, Liu Z, Li J, McAuley J, Xiong C. Intent contrastive learning for sequential recommendation. In Proc. the 2022 ACM Web Conference, Apr. 2022, pp.2172–2182. DOI: 10.1145/3485447.3512090.
Crossref
[46]
Yu J, Yin H, Xia X, Chen T, Cui L, Nguyen Q V H. Are graph augmentations necessary?: Simple graph contrastive learning for recommendation. In Proc. the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2022, pp.1294–1303. DOI: 10.1145/3477495.3531937.
Crossref
[47]
Hao B, Zhang J, Yin H, Li C, Chen H. Pre-training graph neural networks for cold-start users and items representation. In Proc. the 14th ACM International Conference on Web Search and Data Mining, Mar. 2021, pp.265–273. DOI: 10.1145/3437963.3441738.
Crossref
[48]
Yu J, Yin H, Li J, Wang Q, Hung N Q V, Zhang X. Self-supervised multi-channel hypergraph convolutional network for social recommendation. In Proc. the 2021 Web Conference, Apr. 2021, pp.413–424. DOI: 10.1145/3442381.3449844.
Crossref
[49]
Xia X, Yin H, Yu J, Wang Q, Cui L, Zhang X. Self-supervised hypergraph convolutional networks for session-based recommendation. In Proc. the 35th AAAI Conference on Artificial Intelligence, May 2021, pp.4503–4511. DOI: 10.1609/aaai.v35i5.16578.
Crossref
[50]
Yu J, Yin H, Gao M, Xia X, Zhang X, Hung N Q V. Socially-aware self-supervised tri-training for recommendation. In Proc. the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Aug. 2021, pp.2084–2092. DOI: 10.1145/3447548.3467340.
Crossref
[51]

Wilson D R, Martinez T R. Reduction techniques for instance-based learning algorithms. Machine Learning, 2000, 38(3): 257–286. DOI: 10.1023/A:1007626913721.
Crossref Google Scholar
[52]

Leyva E, Gonzalez A, Pérez R. Three new instance selection methods based on local sets: A comparative study with several approaches from a bi-objective perspective. Pattern Recognition, 2015, 48(4): 1523–1537. DOI: 10.1016/j.patcog.2014.10.001.
Crossref Google Scholar
[53]
Zhang J, Hao B, Chen B, Li C, Chen H, Sun J. Hierarchical reinforcement learning for course recommendation in MOOCs. In Proc. the 33rd AAAI Conference on Artificial Intelligence, Jul. 2019, pp.435–442. DOI: 10.1609/aaai.v33i01.3301435.
Crossref
[54]
Qiu R, Huang Z, Yin H. Memory augmented multi-instance contrastive predictive coding for sequential recommendation. In Proc. the 2021 IEEE International Conference on Data Mining (ICDM), Dec. 2021, pp.519–528. DOI: 10.1109/ICDM51629.2021.00063.
Crossref
[55]
Wang Y, Zhang H, Liu Z, Yang L, Yu P S. ContrastVAE: Contrastive variational autoencoder for sequential recommendation. In Proc. the 31st ACM International Conference on Information & Knowledge Management, Oct. 2022, pp.2056–2066. DOI: 10.1145/3511808.3557268.
Crossref
[56]
Fan Z, Liu Z, Wang S, Zheng L, Yu P S. Modeling sequences as distributions with uncertainty for sequential recommendation. In Proc. the 30th ACM International Conference on Information & Knowledge Management, Nov. 2021, pp.3019–3023. DOI: 10.1145/3459637.3482145.
Crossref
[57]
Liu Y, Xuan H, Li B, Wang M, Chen T, Yin H. Self-supervised dynamic hypergraph recommendation based on hyper-relational knowledge graph. In Proc. the 32nd ACM International Conference on Information and Knowledge Management, Oct. 2023, pp.1617–1626. DOI: 10.1145/3583780.3615054.
Crossref
[58]
Wu J, Wang X, Feng F, He X, Chen L, Lian J, Xie X. Self-supervised graph learning for recommendation. In Proc. the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul. 2021, pp.726–735. DOI: 10.1145/3404835.3462862.
Crossref
Journal of Computer Science and Technology
Volume 39 Issue 5,
September 2024
Pages 1123-1137
DOI: 10.1007/s11390-024-4069-5

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Cite this Report
Close
Close
Cite this article:
Liu P-S, Zheng L-N, Chen J-L, et al. Enhancing Recommendation with Denoising Auxiliary Task. Journal of Computer Science and Technology, 2024, 39(5): 1123-1137. https://doi.org/10.1007/s11390-024-4069-5

161

Views

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 25 December 2023
Accepted: 25 June 2024
Published: 05 December 2024
© Institute of Computing Technology, Chinese Academy of Sciences 2024