{"type":"ScholarlyArticle","title":"Inductive Link Prediction for Nodes Having Only Attribute Information","authors":[{"name":"Yu Hao","slug":"yu-hao","given":"Yu","family":"Hao","affiliation":"University of New South Wales"},{"name":"Xin Cao","slug":"xin-cao","given":"Xin","family":"Cao","affiliation":"University of New South Wales"},{"name":"Yixiang Fang","slug":"yixiang-fang","given":"Yixiang","family":"Fang","affiliation":"University of New South Wales"},{"name":"Xike Xie","slug":"xike-xie","given":"Xike","family":"Xie","affiliation":"University of Science and Technology of China"},{"name":"Sibo Wang","slug":"sibo-wang","given":"Sibo","family":"Wang","affiliation":"The Chinese University of Hong Kong"}],"abstract":"Predicting the link between two nodes is a fundamental problem for graph data analytics. In attributed graphs, both the structure and attribute information can be utilized for link prediction. Most existing studies focus on transductive link prediction where both nodes are already in the graph. However, many real-world applications require inductive prediction for new nodes having only attribute information. It is more challenging since the new nodes do not have structure information and cannot be seen during the model training. To solve this problem, we propose a model called DEAL, which consists of three components: two node embedding encoders and one alignment mechanism. The two encoders aim to output the attribute-oriented node embedding and the structure-oriented node embedding, and the alignment mechanism aligns the two types of embeddings to build the connections between the attributes and links. Our model DEAL is versatile in the sense that it works for both inductive and transductive link prediction. Extensive experiments on several benchmark datasets show that our proposed model significantly outperforms existing inductive link prediction methods, and also outperforms the state-of-the-art methods on transductive link prediction.","doi":"10.24963/ijcai.2020/168","url":"https://ijcai.org/proceedings/2020/168","pdf":"https://ijcai.org/proceedings/2020/0168.pdf","markdown":"https://ijcai.org/proceedings/2020/168.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/168","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Data Mining","track":"Main track","number":168,"pages":{"first":1209,"last":1215},"keywords":["Data Mining: Mining Graphs, Semi Structured Data, Complex Data"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24875/file_24875.m3u8","length_sec":289,"provider":"hls"}],"references":[{"position":1,"raw":"[Bhagavatula et al., 2018] Chandra Bhagavatula, Sergey Feldman, et al. Content-based citation recommendation. In Proc. of NAACL, pages 238-251, 2018.","title":"Content-based citation recommendation","authors":"Chandra Bhagavatula, Sergey Feldman","year":"2018","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bojchevski and Günnemann, 2018] Aleksandar Bojchevski and Stephan Günnemann. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. In Proc. of ICLR, pages 1-13, 2018.","title":"Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking","authors":"Aleksandar Bojchevski, Stephan Günnemann","year":"2018","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Clevert et al., 2015] Djork-Arné Clevert, Thomas Un- terthiner, and Sepp Hochreiter. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289, 2015.","title":"Djork-Arné Clevert, Thomas Unterthiner, and Sepp Hochreiter. Fast and accurate deep network learning by exponential linear units","authors":"Clevert","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gao and Huang, 2018] Hongchang Gao and Heng Huang. Deep attributed network embedding. In Proc. of IJCAI, volume 18, pages 3364-3370, 2018.","title":"Deep attributed network embedding","authors":"Huang ; ] Hongchang Gao, Heng Gao, Huang","year":"2018","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/467"},{"position":5,"raw":"[Gao et al., 2019] Hongchang Gao, Jian Pei, and Heng Huang. Progan: Network embedding via proximity gener- ative adversarial network. In Proc. of KDD, pages 1308- 1316, 2019.","title":"Progan: Network embedding via proximity generative adversarial network","authors":"Hongchang Gao, Jian Pei, Heng Huang","year":"2019","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goodfellow et al., 2016] Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016.","title":"Deep Learning","authors":"Ian Goodfellow, Yoshua Bengio, Aaron Courville","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Grover and Leskovec, 2016] Aditya Grover and Jure Leskovec. node2vec: Scalable feature learning for networks. In Proc. of KDD, pages 855-864, 2016.","title":"node2vec: Scalable feature learning for networks","authors":"Leskovec Grover, Aditya Grover, Jure Leskovec","year":"2016","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hadsell et al., 2006] Raia Hadsell, Sumit Chopra, and Yann LeCun. Dimensionality reduction by learning an invariant mapping. In Proc. of CVPR, pages 1735-1742, 2006.","title":"Dimensionality reduction by learning an invariant mapping","authors":"Raia Hadsell, Sumit Chopra, Yann Lecun","year":"2006","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hamilton et al., 2017] William L. Hamilton, Rex Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Proc. of NeurIPS, 2017.","title":"Inductive representation learning on large graphs","authors":"William L Hamilton, Rex Ying, Jure Leskovec","year":"2017","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kazemi and Poole, 2018] Seyed Mehran Kazemi and David Poole. Simple embedding for link prediction in knowledge graphs. In Proc. of NeurIPS, pages 4284-4295, 2018.","title":"Simple embedding for link prediction in knowledge graphs","authors":"Seyed Mehran, Kazemi, David Poole","year":"2018","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Variational graph auto-encoders. NeurIPS Workshop, 2016.","title":"Variational graph auto-encoders","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":"NeurIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kipf and Welling, 2017] Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In Proc. of ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"Thomas N Kipf, Max Welling","year":"2017","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kovács et al., 2019] István A Kovács, Katja Luck, Kerstin Spirohn, et al. Network-based prediction of protein inter- actions. Nature communications, 10(1):1-8, 2019.","title":"Network-based prediction of protein interactions","authors":"Kovács","year":"2019","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[LeCun et al., 2006] Yann LeCun, Sumit Chopra, et al. A tutorial on energy-based learning. Predicting structured data, 1(0), 2006.","title":"A tutorial on energy-based learning","authors":"Yann Lecun, Sumit Chopra","year":"2006","venue":"Predicting structured data","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liben-Nowell and Kleinberg, 2007] David Liben-Nowell and Jon M. Kleinberg. The link-prediction problem for social networks. JASIST, 58(7):1019-1031, 2007.","title":"The link-prediction problem for social networks","authors":"Liben-Nowell Kleinberg, ; ] David Liben-Nowell, Jon M Kleinberg","year":"2007","venue":"JASIST","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Masnadi-Shirazi and Vasconcelos, 2015] Hamed Masnadi- Shirazi and Nuno Vasconcelos. A view of margin losses as regularizers of probability estimates. The Journal of Machine Learning Research, 16(1):2751-2795, 2015.","title":"A view of margin losses as regularizers of probability estimates","authors":"Masnadi-Shirazi, Vasconcelos","year":"2015","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[McAuley et al., 2015] Julian McAuley, Christopher Targett, et al. Image-based recommendations on styles and substi- tutes. In Proc. of SIGIR, pages 43-52, 2015.","title":"Image-based recommendations on styles and substitutes","authors":"Julian Mcauley, Christopher Targett","year":"2015","venue":"Proc. of SIGIR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[McCallum et al., 2000] Andrew Kachites McCallum, Ka- mal Nigam, et al. Automating the construction of inter- net portals with machine learning. Information Retrieval, 3(2):127-163, 2000.","title":"Automating the construction of internet portals with machine learning","authors":"Mccallum","year":"2000","venue":"Information Retrieval","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Namata et al., 2012] Galileo Namata, Ben London, et al. Query-driven active surveying for collective classification. In 10th International Workshop on Mining and Learning with Graphs, page 8, 2012.","title":"Galileo Namata, Ben London, et al. Query-driven active surveying for collective classification","authors":"Namata","year":"2012","venue":"10th International Workshop on Mining and Learning with Graphs","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Perozzi et al., 2014] Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social rep- resentations. In Proc. of KDD, pages 701-710, 2014.","title":"Deepwalk: Online learning of social representations","authors":"Bryan Perozzi, Rami Al-Rfou, Steven Skiena","year":"2014","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qiu et al., 2019] Zhenyu Qiu, Wenbin Hu, Jia Wu, , Weiwei Liu, Bo Du, et al. Temporal network embedding with high- order nonlinear information. In Proc. of AAAI, 2019.","title":"Temporal network embedding with highorder nonlinear information","authors":"Zhenyu Qiu, Wenbin Hu, Jia Wu, Weiwei Liu, Bo Du","year":"2019","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Salimans and Kingma, 2016] Tim Salimans and Durk P Kingma. Weight normalization: A simple reparameteri- zation to accelerate training of deep neural networks. In Proc. of NeurIPS, pages 901-909, 2016.","title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","authors":"Kingma Salimans, Tim Salimans, P Durk, Kingma","year":"2016","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sen et al., 2008] Prithviraj Sen, Galileo Namata, Mustafa Bilgic, et al. Collective classification in network data. AI magazine, 29(3):93-93, 2008.","title":"Collective classification in network data","authors":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic","year":"2008","venue":"AI magazine","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shchur et al., 2018] Oleksandr Shchur, Maximilian Mumme, et al. Pitfalls of graph neural network evalua- tion. NeurIPS Workshop, 2018.","title":"Pitfalls of graph neural network evaluation","authors":"Oleksandr Shchur, Maximilian Mumme","year":"2018","venue":"NeurIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, et al. Graph Attention Networks. In Proc. of ICLR, 2018.","title":"Graph Attention Networks","authors":"Petar Veličković, Guillem Cucurull","year":"2018","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2016] Daixin Wang, Peng Cui, and Wenwu Zhu. Structural deep network embedding. In Proc. of KDD, pages 1225-1234, 2016.","title":"Structural deep network embedding","authors":"Wang","year":"2016","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xu et al., 2019a] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works? In Proc. of ICLR, 2019.","title":"How powerful are graph neural networks?","authors":"Xu","year":"2019","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2019b] Pinghua Xu, Wenbin Hu, Jia Wu, and Bo Du. Link prediction with signed latent factors in signed social networks. In Proc. of KDD, pages 1046-1054, 2019.","title":"Link prediction with signed latent factors in signed social networks","authors":"Xu","year":"2019","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2019c] Pinghua Xu, Wenbin Hu, Jia Wu, Weiwei Liu, Bo Du, and Jian Yang. Social trust network embed- ding. In Proc. of ICDM, pages 678-687, 2019.","title":"Social trust network embedding","authors":"Xu","year":"2019","venue":"Proc. of ICDM","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[You et al., 2019] Jiaxuan You, Rex Ying, and Jure Leskovec. Position-aware graph neural networks. In Proc. of ICML, pages 7134-7143, 2019.","title":"Position-aware graph neural networks","authors":"You","year":"2019","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang and Chen, 2018] Muhan Zhang and Yixin Chen. Link prediction based on graph neural networks. In Proc. of NeurIPS, pages 5165-5175, 2018.","title":"Link prediction based on graph neural networks","authors":"Chen ; ] Muhan Zhang, Yixin Zhang, Chen","year":"2018","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhao et al., 2016] Peixiang Zhao, Charu C. Aggarwal, and Gewen He. Link prediction in graph streams. In Proc. of ICDE, pages 553-564, 2016.","title":"Link prediction in graph streams","authors":"Zhao","year":"2016","venue":"Proc. of ICDE","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhou et al., 2009] Tao Zhou, Linyuan Lü, and Yi-Cheng Zhang. Predicting missing links via local information. The European Physical Journal B, 71(4):623-630, 2009.","title":"Predicting missing links via local information","authors":"Tao Zhou, Linyuan Lü, Yi-Cheng Zhang","year":"2009","venue":"The European Physical Journal B","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zitnik and Leskovec, 2017] Marinka Zitnik and Jure Leskovec. Predicting multicellular function through multi-layer tissue networks. Bioinformatics, 33(14):190- 198, 2017.","title":"Predicting multicellular function through multi-layer tissue networks","authors":"Leskovec Zitnik, Marinka Zitnik, Jure Leskovec","year":"2017","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}