{"type":"ScholarlyArticle","title":"GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks","authors":[{"name":"Ziyao Li","slug":"ziyao-li","given":"Ziyao","family":"Li","affiliation":"Yuanpei College , Peking University , China"},{"name":"Liang Zhang","slug":"liang-zhang","given":"Liang","family":"Zhang","affiliation":"Yuanpei College , Peking University , China"},{"name":"Guojie Song","slug":"guojie-song","given":"Guojie","family":"Song","affiliation":"Key Laboratory of Machine Perception , Ministry of Education , Peking University , China"}],"abstract":"Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in aggregating local neighborhood information for individual graph nodes. Low-rank proximities and node features are successfully leveraged in existing GCNs, however, attributes that graph links may carry are commonly ignored, as almost all of these models simplify graph links into binary or scalar values describing node connectedness. In our paper instead, links are reverted to hypostatic relationships between entities with descriptional attributes. We propose GCN-LASE (GCN with Link Attributes and Sampling Estimation), a novel GCN model taking both node and link attributes as inputs. To adequately captures the interactions between link and node attributes, their tensor product is used as neighbor features, based on which we define several graph kernels and further develop according architectures for LASE. Besides, to accelerate the training process, the sum of features in entire neighborhoods are estimated through Monte Carlo method, with novel  sampling strategies designed for LASE to minimize the estimation variance. Our experiments show that LASE outperforms strong baselines over various graph datasets, and further experiments corroborate the informativeness of link attributes and our model's ability of adequately leveraging them.","doi":"10.24963/ijcai.2019/410","url":"https://ijcai.org/proceedings/2019/410","pdf":"https://ijcai.org/proceedings/2019/0410.pdf","markdown":"https://ijcai.org/proceedings/2019/410.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/410","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":410,"pages":{"first":2959,"last":2965},"keywords":["Machine Learning: Deep Learning","Machine Learning: Kernel Methods"],"videos":[],"references":[{"position":1,"raw":"[Bruna et al., 2014] Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann Lecun. Spectral networks and locally connected networks on graphs. In Proceedings of the 2nd International Conference on Learning Representa- tions (ICLR'14), 2014.","title":"Spectral networks and locally connected networks on graphs","authors":"Bruna","year":"2014","venue":"Proceedings of the 2nd International Conference on Learning Representations (ICLR'14)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Du et al., 2018] Lun Du, Yun Wang, Guojie Song, Zhicong Lu, and Junshan Wang. Dynamic network embedding : An extended approach for skip-gram based network em- bedding. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI'18), 2018.","title":"Dynamic network embedding : An extended approach for skip-gram based network embedding","authors":"Lun Du, Yun Wang, Guojie Song, Zhicong Lu, Junshan Wang","year":"2018","venue":"Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI'18)","doi":null,"url":null,"internal_url":"/proceedings/2018/288"},{"position":3,"raw":"[Gärtner et al., 2003] Thomas Gärtner, Peter Flach, and Ste- fan Wrobel. On graph kernels: Hardness results and ef- ficient alternatives. In Proceedings of the Annual Con- ference on Computational Learning Theory (CoLT'03), 2003.","title":"On graph kernels: Hardness results and efficient alternatives","authors":"Thomas Gärtner, Peter Flach, Stefan Wrobel","year":"2003","venue":"Proceedings of the Annual Conference on Computational Learning Theory (CoLT'03)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Grover and Leskovec, 2016] Aditya Grover and Jure Leskovec. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16), pages 855-864, 2016.","title":"node2vec: Scalable feature learning for networks","authors":"Leskovec Grover, Aditya Grover, Jure Leskovec","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hamilton et al., 2017] William L. Hamilton, Rex Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS'17), 2017.","title":"Inductive representation learning on large graphs","authors":"William L Hamilton, Rex Ying, Jure Leskovec","year":"2017","venue":"Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS'17)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Henaff et al., 2015] Mikael Henaff, Joan Bruna, and Yann Lecun. Deep convolutional networks on graph-structured data. Computer Science, 2015.","title":"Deep convolutional networks on graph-structured data","authors":"Mikael Henaff, Joan Bruna, Yann Lecun","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huang et al., 2018] Wen-bing Huang, Tong Zhang, Yu Rong, and Junzhou Huang. Adaptive sampling towards fast graph representation learning. CoRR, abs/1809.05343, 2018.","title":"Adaptive sampling towards fast graph representation learning","authors":"Wen-Bing Huang, Tong Zhang, Yu Rong, Junzhou Huang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jie et al., 2018] Chen Jie, Tengfei Ma, and Xiao Cao. Fast- gcn: Fast learning with graph convolutional networks via importance sampling. In Proceedings of the 6th International Conference on Learning Representations (ICLR'18), 2018.","title":"Fastgcn: Fast learning with graph convolutional networks via importance sampling","authors":"Chen Jie, Tengfei Ma, Xiao Cao","year":"2018","venue":"Proceedings of the 6th International Conference on Learning Representations (ICLR'18)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kipf and Welling, 2016] Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In Proceedings of the 4th International Con- ference on Learning Representations (ICLR'16), 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"Thomas N Kipf, Max Welling","year":"2016","venue":"Proceedings of the 4th International Conference on Learning Representations (ICLR'16)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2018] Ziyao Li, Liang Zhang, and Guojie Song. Sepne: Bringing separability to network embedding. CoRR, abs/1811.05614, 2018.","title":"Sepne: Bringing separability to network embedding","authors":"Li","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Niepert et al., 2016] Mathias Niepert, Mohamed Ahmed, and Konstantin Kutzkov. Learning convolutional neural networks for graphs. In Proceedings of the 33rd Interna- tional Conference on Machine Learning (ICML'16), 2016.","title":"Learning convolutional neural networks for graphs","authors":"Mathias Niepert, Mohamed Ahmed, Konstantin Kutzkov","year":"2016","venue":"Proceedings of the 33rd International Conference on Machine Learning (ICML'16)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Owen, 2013] Art B. Owen. Monte Carlo theory, methods and examples. 2013. [Perozzi et al., 2014]","title":"Monte Carlo theory, methods and examples","authors":"Art B Owen","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: online learning of social repre- sentations. In Proceedings of the 20th ACM SIGKDD In- ternational Conference on Knowledge Discovery and Data Mining (KDD'14), 2014.","title":"Deepwalk: online learning of social representations","authors":"Bryan Perozzi, Rami Al-Rfou, Steven Skiena","year":"2014","venue":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'14)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Qiu et al., 2018] Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, and Jie Tang. Network embedding as matrix factorization: Unifying deepwalk, line, pte, and node2vec. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM'18), 2018.","title":"Network embedding as matrix factorization: Unifying deepwalk, line, pte, and node2vec","authors":"Qiu","year":"2018","venue":"Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM'18)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ribeiro et al., 2017] Leonardo F.R. Ribeiro, Pedro H.P. Saverese, and Daniel R. Figueiredo. Struc2vec: Learning node representations from structural identity. In Proceed- ings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17), 2017.","title":"Struc2vec: Learning node representations from structural identity","authors":"F R Leonardo, Ribeiro, H P Pedro, Daniel R Saverese, Figueiredo","year":"2017","venue":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Schölkopf and Smola, 2002] B. Schölkopf and Alexan- der Johannes Smola. Learning With Kernels. The MIT Press, 2002.","title":"Learning With Kernels","authors":"B Schölkopf, Alexander Johannes, Smola","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shervashidze et al., 2011] Nino Shervashidze, Pascal Schweitzer, Erik Jan, Van Leeuwen, Kurt Mehlhorn, and Karsten M. Borgwardt. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research, 12(3):2539-2561, 2011.","title":"Weisfeiler-lehman graph kernels","authors":"Nino Shervashidze, Pascal Schweitzer, Erik Jan, Kurt Van Leeuwen, Karsten M Mehlhorn, Borgwardt","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tang et al., 2015] Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. Line:large- scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web (WWW'15), 2015.","title":"Line:largescale information network embedding","authors":"Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Qiaozhu Mei","year":"2015","venue":"Proceedings of the 24th International Conference on World Wide Web (WWW'15)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tao et al., 2017] Lei Tao, Wengong Jin, Regina Barzilay, and Tommi Jaakkola. Deriving neural architectures from sequence and graph kernels. In Proceedings of the 34 th In- ternational Conference on Machine Learning (ICML'17), 2017.","title":"Deriving neural architectures from sequence and graph kernels","authors":"Lei Tao, Wengong Jin, Regina Barzilay, Tommi Jaakkola","year":"2017","venue":"Proceedings of the 34 th International Conference on Machine Learning (ICML'17)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vishwanathan et al., 2008] S. V. N. Vishwanathan, Karsten M. Borgwardt, Imre Risi Kondor, and Nicol N. Schraudolph. Graph kernels. Journal of Machine Learning Research, 11(2):1201-1242, 2008.","title":"Graph kernels","authors":"S V N Vishwanathan, Karsten M Borgwardt, Imre Risi Kondor, Nicol N Schraudolph","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2016] Daixin Wang, Peng Cui, and Wenwu Zhu. Structural deep network embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16), 2016.","title":"Structural deep network embedding","authors":"Wang","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}