Side-information, such as bundle, type, or brand, can be used to improve item recommendations. Use of graph convolutional networks (GCN) to calculate embeddings of side-information through user-side-item heterogeneous networks is common in the recommendation domain. However, current GCN-based methods largely ignore the limitations of bundle side-information. This is for two reasons: in some bundles, interaction with users or items is sparse; while in others, contributions of items cannot be estimated accurately due to irrelevant and noisy interactions. To overcome these limitations, we propose Graph Convolutional Network incorporating Bundle-based Side-Information (GCN-BSI). Unlike earlier studies, which model user, item and side-information into a unified graph, this model reduces the negative influence of bundle side-information by splitting the graph into three-level (lower, middle and upper) propagation models and incorporating these models into a unified framework by adopting different propagation strategies at different levels. This framework can make better use of bundle semantic information by iteratively optimising models from lower to upper levels, thereby controlling the quality of propagated information. This refined approach can further improve the performance of item recommendations. In a series of experiments, GCN-BSI was compared with eight state-of-the-art baselines using data from NetEase and SteamGame. GCN-BSI showed a significant improvement. An ablation test and case studies further indicated that the optimised solution was better at capturing user–item correlations from specific side-information. The code and data can be visited at: https://github.com/zhongshsh/GCN-BSI
RicciFRokachLShapiraB.Recommender systems: introduction and challenges. In: RicciFRokachLShapiraB (eds) Recommender Systems Handbook. 2nd ed.Berlin: Springer, 2015, pp. 1–34.
2.
WangHZhangFWangJ, et al. RippleNet: Propagating user preferences on the knowledge graph for recommender systems. In: Proceedings of the 27th ACM international conference on information and knowledge management (CIKM’18), Torino, 22–26 October 2018, pp. 417–426. New York: Association for Computing Machinery.
3.
SunRYanJRenF, et al. Improving the recommendation accuracy of TrustSVD via trustworthy analysis in the social network environment. J Inf Sci. Epub ahead of print 23November2022. DOI: 10.1177/01655515221136221.
4.
XieRLingCWangY, et al. Deep feedback network for recommendation. In: Proceedings of the 29th international joint conference on artificial intelligence (IJCAI’20), Yokohama, Japan, 7–15 January 2020, pp. 2519–2525. New York: Association for Computing Machinery.
5.
SmithBLindenG. Two decades of recommender systems at amazon.com. IEEE Internet Comput2017; 21(3): 12–18.
6.
XuJHeXLiH. Deep learning for matching in search and recommendation. In: Proceedings of the 41st international ACM SIGIR conference on research & development in information retrieval (SIGIR’18), Ann Arbor, MI, USA, 8–12 July 2018, pp. 1365–1368. New York: Association for Computing Machinery.
7.
HeXLiaoLZhangH, et al. Neural collaborative filtering. In: Proceedings of the 26th international conference on world wide web (WWW’17), Perth, WA, Australia, 3-7 April 2017, pp. 173–182. New York: Association for Computing Machinery.
8.
ChenYZhaoXRijkeM. Top-N recommendation with high-dimensional side-information via locality preserving projection. In: Proceedings of the 40rd international ACM SIGIR conference on research and development in information retrieval (SIGIR’17), Tokyo, Japan, 7–11 August 2017, pp. 985–988. New York: Association for Computing Machinery.
9.
WangXHeXWangM, et al. Neural graph collaborative filtering. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval (SIGIR’19), Paris, 21–25 July 2019, pp. 165–174. New York: Association for Computing Machinery.
10.
SunZGuoQYangJ, et al. Research commentary on recommendations with side-information: A survey and research directions. Electron Commer R A2019; 37: 100879.
11.
ZhouGZhuXSongC, et al. Deep interest network for click-through rate prediction. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (KDD’18), London, 19–23 August 2018, pp. 1059–1068. New York: Association for Computing Machinery.
12.
LianJZhouXZhangF, et al. xDeepFM: combining explicit and implicit feature interactions for recommender systems. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (KDD’18), London, 19–23 August 2018, pp. 1754–1763. New York: Association for Computing Machinery.
13.
HeXDengKWangX, et al. LightGCN: simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd International ACM SIGIR conference on research and development in information retrieval (SIGIR ’20), Virtual Event, China, 25–30 July 2020, pp. 639–648. New York: Association for Computing Machinery.
14.
TzabanHGuyIGreenstein-MessicaA, et al. Product bundle identification using semi-supervised learning. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (SIGIR’20), Virtual Event, China, 25–30 July 2020, pp. 791–800. New York: Association for Computing Machinery.
15.
ZhouJCuiGZhangZ, et al. Graph neural networks: a review of methods and applications. AI Open2020; 1: 57–81.
16.
ChangJGaoCHeX, et al. Bundle recommendation with graph convolutional networks. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (SIGIR '20), Virtual Event, China, 25–30 July 2020, pp. 1673–1676. New York: Association for Computing Machinery.
17.
DengQWangKZhaoM, et al. Personalized bundle recommendation in online games. In: Proceedings of the 29th ACM international conference on information & knowledge management (CIKM ‘20), Virtual Event, 19–23 October 2020, pp. 2381–2388. New York: Association for Computing Machinery.
18.
KipfTNWellingM. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th international conference on learning representations (ICLR’17), Toulon, 24–26 April 2017, pp. 1–13. New York: Association for Computing Machinery.
19.
GaoCWangXHeX, et al. Graph neural networks for recommender system. In: Proceedings of the 15th ACM international conference on web search and data mining (WSDM’22), Virtual Event, Tempe, AZ, USA, 21–25 February 2022, pp. 1623–1625. New York: Association for Computing Machinery.
20.
RendleSKricheneWZhangL, et al. Neural collaborative filtering vs. matrix factorization revisited. In: Proceedings of the 14th ACM conference on recommender systems (RecSys’20), Virtual Event, Brazil, 22–26 September 2020, pp. 240–248. New York: Association for Computing Machinery.
21.
FanZXuKDongZ, et al. Graph collaborative signals denoising and augmentation for recommendation. In: Proceedings of the 46th International ACM SIGIR conference on research and development in information retrieval (SIGIR’23), Taipei, 23–27 July 2023, pp. 2037–2041. New York: Association for Computing Machinery.
22.
YiMLiuMFengC, et al. A cross-domain recommendation model by unified modelling high-order information and rating information. J Inf Sci. Epub ahead of print 8 July 2023. DOI: 10.1177/01655515231182068.
23.
PathakAGuptaKMcAuleyJ. Generating and personalizing bundle recommendations on steam. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval (SIGIR’17), Tokyo, Japan, 7–11 August 2017, pp. 1073–1076. New York: Association for Computing Machinery.
24.
WangXHeXCaoY, et al. KGAT: Knowledge graph attention network for recommendation. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (SIGKDD’19), Anchorage, AK, 4–8 August 2019, pp. 950–958. New York: Association for Computing Machinery.
25.
ChenLLiuYHeX, et al. Matching user with item set: collaborative bundle recommendation with deep attention network. In: Proceedings of the 28th international joint conference on artificial intelligence (IJCAI’19), Macao, China, 10–16 August 2019, pp. 2095–2101. New York: Association for Computing Machinery.
26.
WangXWangDXuC, et al. Explainable reasoning over knowledge graphs for recommendation. In: Proceedings of the 33th AAAI conference on artificial intelligence (AAAI’19), Honolulu, HI, USA, 27 January–1 February 2019, pp. 5329–5336. Palo Alto, CA: AAAI Press.
27.
GengSFuZTanJ, et al. Path language modeling over knowledge graphs for explainable recommendation. In: Proceedings of the ACM world wide web conference (WWW’22), Virtual Event, Lyon, 25–29 April 2022, pp. 946–955. New York: Association for Computing Machinery.
28.
LiDMaddenA.Cascade embedding model for knowledge graph inference and retrieval. Inf Process Manag2019; 56(6): 102093.
29.
LuYFangYShiC. Meta-learning on heterogeneous information networks for cold-start recommendation. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (KDD’20), Virtual Event, 23–27 August 2020, pp. 1563–1573. New York: Association for Computing Machinery.
30.
HuPDuRHuY, et al. Hybrid item-item recommendation via semi-parametric embedding. In: Proceedings of the 28th international joint conference on artificial intelligence (IJCAI’19), Macao, China, 10–16 August 2019, pp. 2521–2527. New York: Association for Computing Machinery.
31.
ZhaoWShangLYuY, et al. Personalized tag recommendation via denoising auto-encoder. World Wide Web2023; 26(1): 95–114.
32.
BerkaniLBelkacemSOuafiM.Recommendation of users in social networks: a semantic and social based classification approach. Expert Syst2020; 38(2): 1–35.
33.
AhmadianMAhmadiMAhmadianS, et al. Integration of deep sparse autoencoder and particle swarm optimization to develop a recommender System. In: Proceedings of IEEE international conference on systems, man, and cybernetics (SMC’21), Melbourne, VIC, Australia, 17–20 October 2021, pp. 2524–2530. Washington, DC: IEEE Computer Society.
34.
AhmadianMAhmadiMAhmadianS.A reliable deep representation learning to improve trust-aware recommendation systems. Expert Syst Appl2022; 197(1): 1–17.
35.
AhmadianSAhmadianMJaliliM.A deep learning-based trust-and tag-aware recommender system. Neurocomputing2022; 488(1): 557–571.
36.
HuBShiCZhaoW, et al. Leveraging Meta-path based context for top-n recommendation with a neural co-attention model. In: Proceedings of the 41st international ACM SIGIR conference on research and development in information retrieval (SIGIR’18), Ann Arbor, MI, 8–12 July 2018, pp. 1531–1540. New York: Association for Computing Machinery.
37.
CaoYWangXHeX, et al. Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences. In: Proceeding of the world wide web conference (WWW ’19), San Francisco, CA, 13–17 May 2019, pp. 151–161. New York: Association for Computing Machinery.
38.
TaoZWeiYWangX.MGAT: Multimodal graph attention network for recommendation. Inf Process Manag2020; 57(5): 1–11.
39.
ChenJYuJLuW.IR-Rec: An interpretive rules-guided recommendation over knowledge graph. Inf Sci2021; 563: 326–341.
40.
YengikandAKMeghdadiMAhmadianS, et al. Deep representation learning using multilayer perceptron and stacked autoencoder for recommendation systems. In: Proceedings of 2021 IEEE international conference on systems, man, and cybernetics (SMC’21), Melbourne, VIC, Australia, 17–20 October 2021, pp. 2485–2491. Washington, DC: IEEE Computer Society.
41.
EbesuTShenBFangY. Collaborative memory network for recommendation systems. In: Proceedings of the 41th international ACM SIGIR conference on research & development in information retrieval (SIGIR’19), Ann Arbor, MI, 8–12 July 2018. New York: Association for Computing Machinery.
42.
SongWXiaoZWangY, et al. Session-based social recommendation via dynamic graph attention networks. In: Proceedings of the 12th ACM international conference on web search and data mining (WSDM ’19), Melbourne, VIC, Australia, 11–15 February 2019, pp. 555–563. New York: Association for Computing Machinery.
43.
WuLSunPFuY, et al. A neural influence diffusion model for social recommendation. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval (SIGIR’19), Paris, 21–25 July 2019, pp. 235–244. New York: Association for Computing Machinery.
44.
WuLYangYChenL, et al. Learning to transfer graph embeddings for inductive graph based recommendation. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (SIGIR ’20), Virtual Event, China, 25–30 July 2020, pp. 1211–1220. New York: Association for Computing Machinery.
45.
BergRKipfTWellingM.Graph convolutional matrix completion. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery & data mining (KDD’18 workshop), London, 19–23 August 2018. New York: Association for Computing Machinery.
46.
YingRHeRChenK, et al. Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (KDD’18), London, 19–23 August 2018, pp. 974–983. New York: Association for Computing Machinery.
47.
ZhengYGaoCHeX, et al. Price-aware recommendation with graph convolutional networks. In: Proceedings of the 2020 IEEE 36th international conference on data engineering (ICDE’20), Dallas, TX, 20–24 April 2020, pp. 133–144. Washington, DC: IEEE Computer Society.
48.
WuSTangYZhuY, et al. Session-based recommendation with graph neural networks. In: Proceedings of the AAAI conference on artificial intelligence (AAAI’19), Honolulu, HI, 27 January–1 February 2019, pp. 346–353. Palo Alto, CA: AAAI Press.
49.
HuLLiCShiC.Graph neural news recommendation with long-term and short-term interest modeling. Inf Process Manag2020; 57(2): 102142.
50.
HuYXiongFPanS, et al. Bayesian personalized ranking based on multiple-layer neighborhoods. Inf Sci2021; 542: 156–176.
51.
KoukiPFountalisIVasiloglouN, et al. Product collection recommendation in online retail. In: Proceedings of the 13th ACM conference on recommender systems (RecSys’19), Copenhagen, 16–20 September 2019, pp. 486–490. New York: Association for Computing Machinery.
52.
ShalomOKoenigsteinNPaquetU, et al. Beyond collaborative filtering: the list recommendation problem. In: Proceeding of the 25th international conference on World Wide Web (WWW '16), Montreal, QC, Canada, 11–15 April 2016, pp. 63–72. New York: Association for Computing Machinery.
53.
YalcinEBilgeA.Investigating and counteracting popularity bias in group recommendations. Inf Process Manag2021; 58(5): 102608.
54.
Misztal-RadeckaJIndurkhyaB.Bias-aware hierarchical clustering for detecting the discriminated groups of users in recommendation systems. Inf Process & Manag2021; 58(3): 102519.
55.
CaoDNieLHeX, et al. Embedding factorization models for jointly recommending items and user generated lists. In: Proceedings of the 40rd international ACM SIGIR conference on research and development in information retrieval (SIGIR’17), Tokyo, Japan, 7–11 August 2017, pp. 585–594. New York: Association for Computing Machinery.
56.
BaiJZhouCSongJ, et al. Personalized bundle list recommendation. In: Proceedings of the international world wide web conference (WWW’19), San Francisco, CA, 13–17 May 2019, pp. 60-71. New York: Association for Computing Machinery.
57.
WillHYingZLeskovecJ. Inductive representation learning on large graphs. In: Proceedings of the 31st international conference on neural information processing systems (NIPS’17), Long Beach, CA, 4–9 December 2017, pp. 1025–1035. New York: Association for Computing Machinery.
58.
QiuHLiuYGuoG, et al. BPRH: Bayesian personalized ranking for heterogeneous implicit feedback. Inf Sci2018; 453: 80–98.
