{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T05:33:15Z","timestamp":1768714395828,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,10,2]],"date-time":"2022-10-02T00:00:00Z","timestamp":1664668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,2]],"date-time":"2022-10-02T00:00:00Z","timestamp":1664668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology (MOST) of Taiwan","doi-asserted-by":"crossref","award":["109-2636-E-006-017"],"award-info":[{"award-number":["109-2636-E-006-017"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology (MOST) of Taiwan","doi-asserted-by":"crossref","award":["108-2218-E-006-036"],"award-info":[{"award-number":["108-2218-E-006-036"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2022,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recently, increasing attention has been paid to heterogeneous graph representation learning (HGRL), which aims to embed rich structural and semantic information in heterogeneous information networks (HINs) into low-dimensional node representations. To date, most HGRL models rely on hand-crafted meta-paths. However, the dependency on manually-defined meta-paths requires domain knowledge, which is difficult to obtain for complex HINs. More importantly, the pre-defined or generated meta-paths of all existing HGRL methods attached to each node type or node pair cannot be personalised to each individual node. To fully unleash the power of HGRL, we present a novel framework, Personalised Meta-path based Heterogeneous Graph Neural Networks (PM-HGNN), to jointly generate meta-paths that are personalised for each individual node in a HIN and learn node representations for the target downstream task like node classification. Precisely, PM-HGNN treats the meta-path generation as a Markov Decision Process and utilises a policy network to adaptively generate a meta-path for each individual node and simultaneously learn effective node representations. The policy network is trained with deep reinforcement learning by exploiting the performance improvement on a downstream task. We further propose an extension, PM-HGNN<jats:italic>++<\/jats:italic>, to better encode relational structure and accelerate the training during the meta-path generation. Experimental results reveal that both PM-HGNN and PM-HGNN<jats:italic>++<\/jats:italic> can significantly and consistently outperform 16 competing baselines and state-of-the-art methods in various settings of node classification. Qualitative analysis also shows that PM-HGNN<jats:italic>++<\/jats:italic> can identify meaningful meta-paths overlooked by human knowledge.<\/jats:p>","DOI":"10.1007\/s10618-022-00862-z","type":"journal-article","created":{"date-parts":[[2022,10,2]],"date-time":"2022-10-02T01:03:06Z","timestamp":1664672586000},"page":"2299-2333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Personalised meta-path generation for heterogeneous graph neural networks"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1226-5597","authenticated-orcid":false,"given":"Zhiqiang","family":"Zhong","sequence":"first","affiliation":[]},{"given":"Cheng-Te","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Pang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,2]]},"reference":[{"key":"862_CR1","doi-asserted-by":"crossref","unstructured":"Sun Y, Han J (2012) Mining heterogeneous information networks: a structural analysis approach. ACM SIGKDD Explorations Newsletter","DOI":"10.1145\/2481244.2481248"},{"key":"862_CR2","volume-title":"A survey of reinforcement learning in relational domains","author":"M Van Otterlo","year":"2005","unstructured":"Van Otterlo M (2005) A survey of reinforcement learning in relational domains. Centre for Telematics and Information Technology (CTIT) University of Twente, Tech, Rep"},{"key":"862_CR3","doi-asserted-by":"crossref","unstructured":"Zheng J, Ma Q, Gu H, Zheng Z (2021) Multi-view denoising graph auto-encoders on heterogeneous information networks for cold-start recommendation. In: Proceedings of the 2021 ACM Conference on Knowledge Discovery and Data Mining (KDD), pp. 2338\u20132348","DOI":"10.1145\/3447548.3467427"},{"key":"862_CR4","doi-asserted-by":"crossref","unstructured":"Wan G, Du B, Pan S, Haffari G (2020) Reinforcement learning based meta-path discovery in large-scale heterogeneous information networks. In: Proceedings of the 2020 AAAI Conference on Artificial Intelligence (AAAI), pp. 6094\u20136101","DOI":"10.1609\/aaai.v34i04.6073"},{"key":"862_CR5","doi-asserted-by":"crossref","unstructured":"Wang X, Ji H, Shi C, Wang B, Ye Y, Cui P, Yu PS (2019) Heterogeneous graph attention network. In: Proceedings of the 2019 International Conference on World Wide Web (WWW), pp. 2022\u20132032","DOI":"10.1145\/3308558.3313562"},{"key":"862_CR6","doi-asserted-by":"crossref","unstructured":"Fu X, Zhang J, Meng Z, King I (2020) MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of the 2020 International Conference on World Wide Web (WWW), pp. 2331\u20132341","DOI":"10.1145\/3366423.3380297"},{"key":"862_CR7","doi-asserted-by":"crossref","unstructured":"Dong Y, Hu Z, Wang K, Sun Y, Tang J (2020) Heterogeneous network representation learning. In: Proceedings of the 2020 International Joint Conferences on Artifical Intelligence (IJCAI), pp. 4861\u20134867","DOI":"10.24963\/ijcai.2020\/677"},{"key":"862_CR8","doi-asserted-by":"crossref","unstructured":"Dong Y, Chawla N.V, Swami A (2017) metapath2vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the 2017 ACM Conference on Knowledge Discovery and Data Mining (KDD), pp. 135\u2013144","DOI":"10.1145\/3097983.3098036"},{"key":"862_CR9","doi-asserted-by":"crossref","unstructured":"Fu T, Lee W, Lei Z (2017) Hin2vec: Explore meta-paths in heterogeneous information networks for representation learning. In: Proceedings of the 2017 ACM International Conference on Information and Knowledge Management (CIKM), pp. 1797\u20131806","DOI":"10.1145\/3132847.3132953"},{"key":"862_CR10","doi-asserted-by":"crossref","unstructured":"Shi C, Hu B, Zhao WX, Yu PS (2019) Heterogeneous information network embedding for recommendation. IEEE Transactions on Knowledge and Data Engineering","DOI":"10.1109\/TKDE.2018.2833443"},{"key":"862_CR11","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionally. In: Proceedings of the 2013 Annual Conference on Neural Information Processing Systems (NIPS), pp. 3111\u20133119"},{"key":"862_CR12","unstructured":"Le QV, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 2014 International Conference on Machine Learning (ICML), pp. 1188\u20131196"},{"key":"862_CR13","doi-asserted-by":"crossref","unstructured":"Hussein R, Yang D, Cudr\u00e9-Mauroux P (2018) Are meta-paths necessary?: Revisiting heterogeneous graph embeddings. In: Proceedings of the 2018 ACM International Conference on Information and Knowledge Management (CIKM), pp. 437\u2013446","DOI":"10.1145\/3269206.3271777"},{"key":"862_CR14","doi-asserted-by":"crossref","unstructured":"Jiang J, Li Z, Ju CJ-, Wang W (2020) MARU: meta-context aware random walks for heterogeneous network representation learning. In: Proceedings of the 2020 ACM International Conference on Information and Knowledge Management (CIKM), pp. 575\u2013584","DOI":"10.1145\/3340531.3412040"},{"key":"862_CR15","doi-asserted-by":"crossref","unstructured":"Zhao J, Wang X, Shi C, Liu Z, Ye Y (2020) Network schema preserving heterogeneous information network embedding. In: Proceedings of the 2020 International Joint Conferences on Artifical Intelligence (IJCAI), pp. 1366\u20131372","DOI":"10.24963\/ijcai.2020\/190"},{"key":"862_CR16","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the 2017 International Conference on Learning Representations (ICLR)"},{"key":"862_CR17","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: Proceedings of the 2018 International Conference on Learning Representations (ICLR)"},{"key":"862_CR18","doi-asserted-by":"crossref","unstructured":"Schlichtkrull MS, Kipf TN, Bloem P, van den Berg R, Titov I, Welling M (2019) Modeling relational data with graph convolutional networks. In: European Semantic Web Conference (ESWC), pp. 593\u2013607","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"862_CR19","doi-asserted-by":"crossref","unstructured":"Zhang C, Song D, Huang C, Swami A, Chawla NV (2019) Heterogeneous graph neural network. In: Proceedings of the 2019 ACM Conference on Knowledge Discovery and Data Mining (KDD), pp. 793\u2013803","DOI":"10.1145\/3292500.3330961"},{"key":"862_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller MA, Fidjeland A, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533","journal-title":"Nature"},{"key":"862_CR21","doi-asserted-by":"crossref","unstructured":"Meng C, Cheng R, Maniu S, Senellart P, Zhang W (2015) Discovering meta-paths in large heterogeneous information networks. In: Proceedings of the 2015 International Conference on World Wide Web (WWW), pp. 754\u2013764","DOI":"10.1145\/2736277.2741123"},{"key":"862_CR22","doi-asserted-by":"crossref","unstructured":"Yang C, Liu M, He F, Zhang X, Peng J, Han J (2018) Similarity modeling on heterogeneous networks via automatic path discovery. In: European Conference on Machine Learning and Knowledge Discovery in Databases (ECMLPKDD), pp. 37\u201354","DOI":"10.1007\/978-3-030-10928-8_3"},{"key":"862_CR23","doi-asserted-by":"crossref","unstructured":"Raedt LD (2008) Logical and Relational Learning. Cognitive Technologies","DOI":"10.1007\/978-3-540-68856-3"},{"issue":"1\u20132","key":"862_CR24","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/S0004-3702(98)00034-4","volume":"101","author":"H Blockeel","year":"1998","unstructured":"Blockeel H, Raedt LD (1998) Top-down induction of first-order logical decision trees. Artif Intell 101(1\u20132):285\u2013297","journal-title":"Artif Intell"},{"issue":"12","key":"862_CR25","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TKDE.2018.2822307","volume":"30","author":"F Serafino","year":"2018","unstructured":"Serafino F, Pio G, Ceci M (2018) Ensemble learning for multi-type classification in heterogeneous networks. IEEE Trans Knowl Data Eng 30(12):2326\u20132339","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"862_CR26","doi-asserted-by":"crossref","unstructured":"Petkovic M, Ceci M, Kersting K, Dzeroski S (2020) Estimating the importance of relational features by using gradient boosting. In: International Symposium on Foundations of Intelligent Systems (ISMIS). Lecture Notes in Computer Science, vol. 12117, pp. 362\u2013371","DOI":"10.1007\/978-3-030-59491-6_34"},{"issue":"7","key":"862_CR27","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1007\/s10994-020-05890-8","volume":"109","author":"N Lavrac","year":"2020","unstructured":"Lavrac N, Skrlj B, Robnik-Sikonja M (2020) Propositionalization and embeddings: two sides of the same coin. Mach Learn 109(7):1465\u20131507","journal-title":"Mach Learn"},{"key":"862_CR28","unstructured":"Bruna J, Zaremba W, Szlam A, LeCun Y (2014) Spectral networks and locally connected networks on graphs. In: Proceedings of the 2014 International Conference on Learning Representations (ICLR)"},{"key":"862_CR29","unstructured":"Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 2016 Annual Conference on Neural Information Processing Systems (NIPS), pp. 3837\u20133845"},{"key":"862_CR30","doi-asserted-by":"crossref","unstructured":"Fan Y, Hou S, Zhang Y, Ye Y, Abdulhayoglu M (2018) Gotcha - sly malware!: Scorpion A metagraph2vec based malware detection system. In: Proceedings of the 2018 ACM Conference on Knowledge Discovery and Data Mining (KDD), pp. 253\u2013262","DOI":"10.1145\/3219819.3219862"},{"key":"862_CR31","doi-asserted-by":"crossref","unstructured":"Hu Z, Dong Y, Wang K, Sun Y (2020) Heterogeneous graph transformer. In: Proceedings of the 2020 International Conference on World Wide Web (WWW), pp. 2704\u20132710","DOI":"10.1145\/3366423.3380027"},{"key":"862_CR32","unstructured":"Yun S, Jeong M, Kim R, Kang J, Kim HJ (2019) Graph transformer networks. In: Proceedings of the 2019 Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 11960\u201311970"},{"key":"862_CR33","unstructured":"Tanon TP, Stepanova D, Razniewski S, Mirza P, Weikum G (2018) Completeness-aware rule learning from knowledge graphs. In: Proceedings of the 2018 International Joint Conferences on Artifical Intelligence (IJCAI), pp. 5339\u20135343"},{"key":"862_CR34","doi-asserted-by":"crossref","unstructured":"Ahmadi N, Huynh V, Meduri VV, Ortona S, Papotti P (2020) Mining expressive rules in knowledge graphs. ACM Journal of Data and Information Quality","DOI":"10.1145\/3371315"},{"issue":"5","key":"862_CR35","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1109\/TNN.1998.712192","volume":"9","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: An introduction. IEEE Transactions on Neural Networks and Learning Systems 9(5):1054\u20131054","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"862_CR36","doi-asserted-by":"crossref","unstructured":"Arulkumaran K, Deisenroth MP, Brundage M, Bharath AA (2017) Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine","DOI":"10.1109\/MSP.2017.2743240"},{"key":"862_CR37","unstructured":"Haykin S (1999) Neural networks: A comprehensive foundation. Knowledge Engineering Review"},{"key":"862_CR38","doi-asserted-by":"crossref","unstructured":"Hou Y, Liu L, Wei Q, Xu X, Chen C (2017) A novel DDPG method with prioritized experience replay. In: Proceedings of the 2017 International Conference on Systems Man and Cybernetics (SMC), pp. 316\u2013321","DOI":"10.1109\/SMC.2017.8122622"},{"key":"862_CR39","unstructured":"Fan J, Wang Z, Xie Y, Yang Z (2020) A theoretical analysis of deep q-learning. In: Proceedings of the 2020 Annual Conference on Learning for Dynamics and Control (L4DC). Proceedings of Machine Learning Research, vol. 120, pp. 486\u2013489"},{"key":"862_CR40","doi-asserted-by":"crossref","unstructured":"Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. In: Proceedings of the 2015 International Conference on World Wide Web (WWW), pp. 1067\u20131077","DOI":"10.1145\/2736277.2741093"},{"key":"862_CR41","doi-asserted-by":"crossref","unstructured":"Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the 2014 ACM Conference on Knowledge Discovery and Data Mining (KDD), pp. 701\u2013710","DOI":"10.1145\/2623330.2623732"},{"key":"862_CR42","unstructured":"Shang J, Qu M, Liu J, Kaplan LM, Han J, Peng J (2016) Meta-path guided embedding for similarity search in large-scale heterogeneous information networks. CoRR abs\/1610.09769"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-022-00862-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-022-00862-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-022-00862-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T12:20:30Z","timestamp":1668601230000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-022-00862-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,2]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["862"],"URL":"https:\/\/doi.org\/10.1007\/s10618-022-00862-z","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,2]]},"assertion":[{"value":"9 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}