Incorporating metapath interaction on heterogeneous information network for social recommendation

doi:10.1007/s11704-022-2438-1

Front. Comput. Sci.

2024, Vol. 18

Issue (1) : 181302 https://doi.org/10.1007/s11704-022-2438-1

Artificial Intelligence

Incorporating metapath interaction on heterogeneous information network for social recommendation

Yanbin JIANG¹, Huifang MA^1,²(

), Xiaohui ZHANG¹, Zhixin LI², Liang CHANG³

¹. College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China
². Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin 541001, China
³. Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin 541004, China

Download: PDF(5772 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Heterogeneous information network (HIN) has recently been widely adopted to describe complex graph structure in recommendation systems, proving its effectiveness in modeling complex graph data. Although existing HIN-based recommendation studies have achieved great success by performing message propagation between connected nodes on the defined metapaths, they have the following major limitations. Existing works mainly convert heterogeneous graphs into homogeneous graphs via defining metapaths, which are not expressive enough to capture more complicated dependency relationships involved on the metapath. Besides, the heterogeneous information is more likely to be provided by item attributes while social relations between users are not adequately considered. To tackle these limitations, we propose a novel social recommendation model MPISR, which models MetaPath Interaction for Social Recommendation on heterogeneous information network. Specifically, our model first learns the initial node representation through a pretraining module, and then identifies potential social friends and item relations based on their similarity to construct a unified HIN. We then develop the two-way encoder module with similarity encoder and instance encoder to capture the similarity collaborative signals and relational dependency on different metapaths. Extensive experiments on five real datasets demonstrate the effectiveness of our method.

Keywords heterogeneous information network social recommender system metapath interaction attention mechanism

Corresponding Author(s): Huifang MA

About author:

Changjian Wang and Zhiying Yang contributed equally to this work.

Just Accepted Date: 08 November 2022 Issue Date: 21 February 2023

Cite this article:

Yanbin JIANG,Huifang MA,Xiaohui ZHANG, et al. Incorporating metapath interaction on heterogeneous information network for social recommendation[J]. Front. Comput. Sci., 2024, 18(1): 181302.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-022-2438-1
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I1/181302

Fig.1 The illustration for HIN on the music dataset(network structure, metapath, metapath instances),

u 1

is the target user. (a) Example of HIN; (b) meta-path; (c) meta-path instances

Fig.2 An illustration of MPISR model framework. (a) Unified HIN; (b) two-ways encoder module; (c) attention fusion

	No.	Metapath	Description
User-side	$P 1$	$U ? U$	Trusted users have similarity
	$P 2$	$U ? U ? I$	Items that friends have interacted with have similarity
	$P 3$	$U ? I ? U$	Users who have interacted with the same items have similarity
	$P 4$	$U ? U ? I ? U$	Users who have interacted with friends on the same item have similarity
	$P 5$	$U ? I$	Users have collaborative similarity with the items they interacted
	$P 6$	$U ? I ? U ? I$	Items that have been interacted with users who have interacted with the same item have similarity
Item-side	$P 1$	$I ? I$	There are a similarity between potential items
	$P 2$	$I ? U ? I$	Items interacted with by the same user have similarity
	$P 3$	$I ? U ? U ? I$	Items that have been interacted with friends of interacted with users have similarity
	$P 4$	$I ? U$	Items have collaborative similarity to the users who have interacted with them
	$P 5$	$I ? U ? I ? U$	Users who have interacted with co-interact items have similarity

Tab.1 Defining metapath for general recommendation datasets

Fig.3 Illustration of single layer GCN operation for user

u 1

on metapath

P

. (a) Inductive graph on metapath p; (b) single layer GCN

Fig.4 Illustration of instance encoder for node

i

on metapath

P

. (a) Unified HIN; (b) metapath-based random walker; (c) reverse and relation-aware light RNN

Dataset	Filmtrust	CiaoDVD	Epinions	Last-fm	Flickr
$♯$ user	1,508	17,615	116,260	1,892	8,358
$♯$ item	2,071	16,121	41,270	17,632	82,120
$♯$ interactions	35,497	72,665	188,477	92,834	327,815
$♯$ trust relation	1,853	40,133	181,304	12,717	187,273

Tab.2 Statistics of five datasets

Tab.3 Results of effectiveness experiments on five different datasets with

k = 20

Tab.4 Results of effectiveness experiments on five different datasets with

k = 50

Fig.5 Experimental results of the different sparsity level user w.r.t HR@20.

Fig.6 Experimental results of the effect of two different encoders.

Fig.7 Experimental results of the effect of attention fusion layer w.r.t HR on Filmtrust and CiaoDVD

Fig.8 Study of embedding size

d

, dropout ratio

p

, friend sample number

k u

and item sample threshold

τ

on Filmtrust. (a) Study of embedding size d; (b) study of dropout ratio p; (c) study of friend sample number k_u; (d) study of item sample threshold τ

Fig.9 Case study for attention weight of each metapath on Filmtrust

1	Y, Jiang H, Ma Y, Liu Z, Li L Chang . Enhancing social recommendation via two-level graph attentional networks. Neurocomputing, 2021, 449: 71–84
2	X, Qian H, Feng G, Zhao T Mei . Personalized recommendation combining user interest and social circle. IEEE Transactions on Knowledge and Data Engineering, 2014, 26( 7): 1763–1777
3	Jamali M, Ester M. A matrix factorization technique with trust propagation for recommendation in social networks. In: Proceedings of the 4th ACM Conference on Recommender Systems. 2010, 135−142
4	M, Jiang P, Cui F, Wang W, Zhu S Yang . Scalable recommendation with social contextual information. IEEE Transactions on Knowledge and Data Engineering, 2014, 26( 11): 2789–2802
5	C, Song B, Wang Q, Jiang Y, Zhang R, He Y Hou . Social recommendation with implicit social influence. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021, 1788−1792
6	X, Wang X, He Y, Cao M, Liu T S Chua . KGAT: knowledge graph attention network for recommendation. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019, 950−958
7	H, Wang M, Zhao X, Xie W, Li M Guo . Knowledge graph convolutional networks for recommender systems. In: Proceedings of the World Wide Web Conference. 2019, 3307−3313
8	L, Chang W, Chen J, Huang C, Bin W Wang . Exploiting multi-attention network with contextual influence for point-of-interest recommendation. Applied Intelligence, 2021, 51( 4): 1904–1917
9	X, Wang X, He M, Wang F, Feng T S Chua . Neural graph collaborative filtering. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2019, 165−174
10	T N, Kipf M Welling . Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. 2017
11	Zheng Y, Gao C, He X, Li Y, Jin D. Price-aware recommendation with graph convolutional networks. In: Proceedings of the 36th IEEE International Conference on Data Engineering. 2020, 133−144
12	X, Wang H, Ji C, Shi B, Wang Y, Ye P, Cui P S Yu . Heterogeneous graph attention network. In: Proceedings of the World Wide Web Conference. 2019, 2022−2032
13	C, Shi P S Yu . Recent developments of deep heterogeneous information network analysis. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2019, 2973−2974
14	X, Yu X, Ren Y, Sun S, Sturt U, Khandelwal Q, Gu B, Norick J Han . Recommendation in heterogeneous information networks with implicit user feedback. In: Proceedings of the 7th ACM Conference on Recommender Systems. 2013, 347−350
15	H, Zhao Q, Yao J, Li Y, Song D L Lee . Meta-graph based recommendation fusion over heterogeneous information networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017, 635−644
16	B, Hu C, Shi W X, Zhao T Yang . Local and global information fusion for top-n recommendation in heterogeneous information network. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018, 1683−1686
17	C, Shi B, Hu W X, Zhao P S Yu . Heterogeneous information network embedding for recommendation. IEEE Transactions on Knowledge and Data Engineering, 2019, 31( 2): 357–370
18	Jiang Z, Liu Z, Fu B, Wu Z, Zhang T. Recommendation in heterogeneous information networks based on generalized random walk model and Bayesian personalized ranking. In: Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 2018, 288−296
19	S, Fan J, Zhu X, Han C, Shi L, Hu B, Ma Y Li . Metapath-guided heterogeneous graph neural network for intent recommendation. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019, 2478−2486
20	X, Yu X, Ren Y, Sun Q, Gu B, Sturt U, Khandelwal B, Norick J Han . Personalized entity recommendation: a heterogeneous information network approach. In: Proceedings of the 7th ACM International Conference on Web Search and Data Mining. 2014, 283−292
21	C, Zhang D, Song C, Huang A, Swami N V Chawla . Heterogeneous graph neural network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019, 793−803
22	Rendle S, Freudenthaler C, Gantner Z, Schmidt-Thieme L. BPR: Bayesian personalized ranking from implicit feedback. In: Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. 2009, 452−461
23	H J, Xue X Y, Dai J, Zhang S, Huang J Chen . Deep matrix factorization models for recommender systems. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence. 2017, 3203−3209
24	S Rendle . Factorization machines. In: Proceedings of 2010 IEEE International Conference on Data Mining. 2010, 995−1000
25	S Rendle . Factorization machines with libFM. ACM Transactions on Intelligent Systems and Technology, 2012, 3( 3): 57
26	Den Berg R, Van T N, Kipf M Welling . Graph convolutional matrix completion. 2017, arXiv preprint arXiv: 1706.02263
27	X, He K, Deng X, Wang Y, Li Y, Zhang M Wang . 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. 2020, 639−648
28	J, Wu X, He X, Wang F, Wang W, Chen J, Lian X Xie . Graph convolution machine for context-aware recommender system. Frontiers of Computer Science, 2022, 16( 6): 166614
29	Y, Dong N V, Chawla A Swami . metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017, 135−144
30	Fu T Y, Lee W C, Lei Z. Hin2Vec: explore meta-paths in heterogeneous information networks for representation learning. In: Proceedings of 2017 ACM on Conference on Information and Knowledge Management. 2017, 1797−1806
31	J, Jin J, Qin Y, Fang K, Du W, Zhang Y, Yu Z, Zhang A J Smola . An efficient neighborhood-based interaction model for recommendation on heterogeneous graph. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020, 75−84
32	X, Fu J, Zhang Z, Meng I King . MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of the Web Conference 2020. 2020, 2331−2341
33	L, Nie X, Song T S Chua . Learning from Multiple Social Networks. Cham: Springer, 2016, 1−118
34	H, Yin X, Zhou B, Cui H, Wang K, Zheng Q V H Nguyen . Adapting to user interest drift for poi recommendation. IEEE Transactions on Knowledge and Data Engineering, 2016, 28( 10): 2566–2581
35	J, Yu M, Gao J, Li H, Yin H Liu . Adaptive implicit friends identification over heterogeneous network for social recommendation. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018, 357−366
36	W, Guan X, Song T, Gan J, Lin X, Chang L Nie . Cooperation learning from multiple social networks: consistent and complementary perspectives. IEEE Transactions on Cybernetics, 2021, 51( 9): 4501–4514
37	X, Wang X, He L, Nie T S Chua . Item silk road: recommending items from information domains to social users. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2017, 185−194
38	T H, Lin C, Gao Y Li . Recommender systems with characterized social regularization. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018, 1767−1770
39	J, Chen C, Wang S, Zhou Q, Shi Y, Feng C Chen . Samwalker: social recommendation with informative sampling strategy. In: Proceedings of the World Wide Web Conference. 2019, 228−239
40	W, Fan Y, Ma Q, Li Y, He E, Zhao J, Tang D Yin . Graph neural networks for social recommendation. In: Proceedings of the World Wide Web Conference. 2019, 417−426
41	L, Wu J, Li P, Sun R, Hong Y, Ge M Wang . Diffnet++: a neural influence and interest diffusion network for social recommendation. IEEE Transactions on Knowledge and Data Engineering, 2022, 34( 10): 4753–4766
42	C, Zhang Y, Wang L, Zhu J, Song H Yin . Multi-graph heterogeneous interaction fusion for social recommendation. ACM Transactions on Information Systems, 2022, 40( 2): 28
43	Q, Wu H, Zhang X, Gao P, He P, Weng H, Gao G Chen . Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems. In: Proceedings of the World Wide Web Conference. 2019, 2091−2102
44	Y, Sun J, Han X, Yan P S, Yu T Wu . PathSim: meta path-based top-k similarity search in heterogeneous information networks. Proceedings of the VLDB Endowment, 2011, 4( 11): 992–1003
45	Zhang C, Yu L, Wang Y, Shah C, Zhang X. Collaborative user network embedding for social recommender systems. In: Proceedings of 2017 SIAM International Conference on Data Mining. 2017, 381−389
46	R, Ying R, He K, Chen P, Eksombatchai W L, Hamilton J Leskovec . Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018, 974−983
47	W L, Hamilton R, Ying J Leskovec . Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 1025−1035
48	P, Veličković G, Cucurull A, Casanova A, Romero P, Liò Y Bengio . Graph attention networks. 2017, arXiv preprint arXiv:1710, 1090, 3
49	G, Guo J, Zhang N Yorke-Smith . TrustSVD: collaborative filtering with both the explicit and implicit influence of user trust and of item ratings. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence. 2015, 123−125

[1]

FCS-22438-OF-YJ_suppl_1

Download

[1]	Youming GE, Cong HUANG, Yubao LIU, Sen ZHANG, Weiyang KONG. Unsupervised social network embedding via adaptive specific mappings[J]. Front. Comput. Sci., 2024, 18(3): 183310-.
[2]	Yajing GUO, Xiujuan LEI, Lian LIU, Yi PAN. circ2CBA: prediction of circRNA-RBP binding sites combining deep learning and attention mechanism[J]. Front. Comput. Sci., 2023, 17(5): 175904-.
[3]	Baiyou QIAO, Zhongqiang WU, Ling MA, Yicheng Zhou, Yunjiao SUN. Effective ensemble learning approach for SST field prediction using attention-based PredRNN[J]. Front. Comput. Sci., 2023, 17(1): 171601-.
[4]	Qingwen LI, Lichao ZHANG, Lei XU, Quan ZOU, Jin WU, Qingyuan LI. Identification and classification of promoters using the attention mechanism based on long short-term memory[J]. Front. Comput. Sci., 2022, 16(4): 164348-.
[5]	Mingyang LI, Yuqing XING, Fang KONG, Guodong ZHOU. Towards better entity linking[J]. Front. Comput. Sci., 2022, 16(2): 162308-.
[6]	Dongjin YU, Lin WANG, Xin CHEN, Jie CHEN. Using BiLSTM with attention mechanism to automatically detect self-admitted technical debt[J]. Front. Comput. Sci., 2021, 15(4): 154208-.
[7]	Chuan SHI, Jiayu DING, Xiaohuan CAO, Linmei HU, Bin WU, Xiaoli LI. Entity set expansion in knowledge graph: a heterogeneous information network perspective[J]. Front. Comput. Sci., 2021, 15(1): 151307-.
[8]	Lu LIU, Shang WANG. Meta-path-based outlier detection in heterogeneous information network[J]. Front. Comput. Sci., 2020, 14(2): 388-403.
[9]	Wenhao ZHENG, Hongyu ZHOU, Ming LI, Jianxin WU. CodeAttention: translating source code to comments by exploiting the code constructs[J]. Front. Comput. Sci., 2019, 13(3): 565-578.

Viewed

Full text

Abstract

Cited

Shared

Discussed