{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:05:29Z","timestamp":1773511529086,"version":"3.50.1"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:p>Most existing graph neural networks (GNNs) are limited to undirected graphs, whose restricted scope of the captured relational information hinders their expressive capabilities and deployment. Compared with undirected graphs, directed graphs (digraphs) fit the demand for modeling more complex topological systems by capturing more intricate relationships between nodes. While some directed GNNs have been introduced, their inspiration mainly comes from deep learning architectures, which lead to redundant complexity and computation, making them inapplicable to large-scale databases. To address these issues, we propose LightDiC, a scalable variant of the digraph convolution based on the magnetic Laplacian. Since topology-related computations are conducted solely during offline pre-processing, LightDiC achieves exceptional scalability, enabling downstream predictions to be trained separately without incurring recursive computational costs. Theoretical analysis shows that LightDiC achieves message passing based on the complex field, which corresponds to the proximal gradient descent process of the Dirichlet energy optimization function from the perspective of digraph signal denoising, ensuring its expressiveness. Experimental results demonstrate that LightDiC performs comparably well or even outperforms other SOTA methods in various downstream tasks, with fewer learnable parameters and higher efficiency.<\/jats:p>","DOI":"10.14778\/3654621.3654623","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T22:21:08Z","timestamp":1717107668000},"page":"1542-1551","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["LightDiC: A Simple Yet Effective Approach for Large-Scale Digraph Representation Learning"],"prefix":"10.14778","volume":"17","author":[{"given":"Xunkai","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meihao","family":"Liao","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daohan","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, National Engineering, Laboratory for Big Data, Analytics and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong-Hua","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoren","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD","author":"Besta Maciej","year":"2022","unstructured":"Maciej Besta, Raphael Grob, Cesare Miglioli, Nicola Bernold, Grzegorz Kwasniewski, Gabriel Gjini, Raghavendra Kanakagiri, Saleh Ashkboos, Lukas Gianinazzi, Nikoli Dryden, and Torsten Hoefler. 2022. Motif Prediction with Graph Neural Networks. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD. New York, NY, USA, 35--45."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5393"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054830"},{"key":"e_1_2_1_6_1","volume-title":"International Conference on Learning Representations, ICLR","author":"Bo Deyu","year":"2023","unstructured":"Deyu Bo, Chuan Shi, Lele Wang, and Renjie Liao. 2023. Specformer: Spectral graph neural networks meet transformers. International Conference on Learning Representations, ICLR (2023)."},{"key":"e_1_2_1_7_1","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds. https:\/\/openreview.net\/forum?id=r1ZdKJ-0W","author":"Bojchevski Aleksandar","year":"2018","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking. In ICLR Workshop on Representation Learning on Graphs and Manifolds. https:\/\/openreview.net\/forum?id=r1ZdKJ-0W"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3080635"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","first-page":"31","DOI":"10.37193\/CJM.2019.01.04","article-title":"Bounds for the skew Laplacian spectral radius of oriented graphs","volume":"35","author":"Chat Bilal A","year":"2019","unstructured":"Bilal A Chat, Hilal A Ganie, and S Pirzada. 2019. Bounds for the skew Laplacian spectral radius of oriented graphs. Carpathian Journal of Mathematics 35, 1 (2019), 31--40.","journal-title":"Carpathian Journal of Mathematics"},{"key":"e_1_2_1_10_1","first-page":"14556","article-title":"Scalable graph neural networks via bidirectional propagation. Advances in neural information processing systems","volume":"33","author":"Chen Ming","year":"2020","unstructured":"Ming Chen, Zhewei Wei, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen. 2020. Scalable graph neural networks via bidirectional propagation. Advances in neural information processing systems, NeurIPS 33 (2020), 14556--14566.","journal-title":"NeurIPS"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00026-005-0237-z"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2016.11.002"},{"key":"e_1_2_1_13_1","doi-asserted-by":"crossref","first-page":"073141","DOI":"10.1063\/5.0006891","article-title":"Characterization and comparison of large directed networks through the spectra of the magnetic Laplacian. Chaos","volume":"30","author":"de Resende Bruno Messias F.","year":"2020","unstructured":"Bruno Messias F. de Resende and Luciano da F. Costa. 2020. Characterization and comparison of large directed networks through the spectra of the magnetic Laplacian. Chaos: An Interdisciplinary Journal of Nonlinear Science 30, 7 (2020), 073141.","journal-title":"An Interdisciplinary Journal of Nonlinear Science"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2017.01.004"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.95.022302"},{"key":"e_1_2_1_16_1","volume-title":"Proceedings of the ACM Web Conference","author":"Feng Wenzheng","year":"2022","unstructured":"Wenzheng Feng, Yuxiao Dong, Tinglin Huang, Ziqi Yin, Xu Cheng, Evgeny Kharlamov, and Jie Tang. 2022. Grand+: Scalable graph random neural networks. In Proceedings of the ACM Web Conference 2022. 3248--3258."},{"key":"e_1_2_1_17_1","volume-title":"Sign: Scalable inception graph neural networks. arXiv preprint arXiv:2004.11198","author":"Frasca Fabrizio","year":"2020","unstructured":"Fabrizio Frasca, Emanuele Rossi, Davide Eynard, Ben Chamberlain, Michael Bronstein, and Federico Monti. 2020. Sign: Scalable inception graph neural networks. arXiv preprint arXiv:2004.11198 (2020)."},{"key":"e_1_2_1_18_1","volume-title":"Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD. Springer, 447--463","author":"Furutani Satoshi","year":"2020","unstructured":"Satoshi Furutani, Toshiki Shibahara, Mitsuaki Akiyama, Kunio Hato, and Masaki Aida. 2020. Graph signal processing for directed graphs based on the hermitian laplacian. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD. Springer, 447--463."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/jgt.22057"},{"key":"e_1_2_1_20_1","volume-title":"NeurIPS","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, NeurIPS (2017)."},{"key":"e_1_2_1_21_1","volume-title":"NeurIPS","author":"He Mingguo","year":"2022","unstructured":"Mingguo He, Zhewei Wei, and Ji-Rong Wen. 2022. Convolutional neural networks on graphs with chebyshev approximation, revisited. Advances in neural information processing systems, NeurIPS (2022)."},{"key":"e_1_2_1_22_1","volume-title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation. Advances in Neural Information Processing Systems, NeurIPS","author":"He Mingguo","year":"2021","unstructured":"Mingguo He, Zhewei Wei, Hongteng Xu, et al. 2021. Bernnet: Learning arbitrary graph spectral filters via bernstein approximation. Advances in Neural Information Processing Systems, NeurIPS (2021)."},{"key":"e_1_2_1_23_1","volume-title":"Learning on Graphs Conference, LOG. PMLR, 40--1.","author":"He Yixuan","year":"2022","unstructured":"Yixuan He, Michael Perlmutter, Gesine Reinert, and Mihai Cucuringu. 2022. Msgnn: A spectral graph neural network based on a novel magnetic signed laplacian. In Learning on Graphs Conference, LOG. PMLR, 40--1."},{"key":"e_1_2_1_24_1","volume-title":"DIGRAC: Digraph Clustering Based on Flow Imbalance. In Learning on Graphs Conference, LOG. PMLR, 21--1.","author":"He Yixuan","year":"2022","unstructured":"Yixuan He, Gesine Reinert, and Mihai Cucuringu. 2022. DIGRAC: Digraph Clustering Based on Flow Imbalance. In Learning on Graphs Conference, LOG. PMLR, 21--1."},{"key":"e_1_2_1_25_1","volume-title":"PyTorch Geometric Signed Directed: A Survey and Software on Graph Neural Networks for Signed and Directed Graphs. arXiv preprint arXiv:2202.10793","author":"He Yixuan","year":"2022","unstructured":"Yixuan He, Xitong Zhang, Junjie Huang, Mihai Cucuringu, and Gesine Reinert. 2022. PyTorch Geometric Signed Directed: A Survey and Software on Graph Neural Networks for Signed and Directed Graphs. arXiv preprint arXiv:2202.10793 (2022)."},{"key":"e_1_2_1_26_1","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems","volume":"33","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, NeurIPS 33 (2020), 22118--22133.","journal-title":"NeurIPS"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3108192"},{"key":"e_1_2_1_28_1","volume-title":"International Conference on Learning Representations, ICLR","author":"Huang Qian","year":"2021","unstructured":"Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, and Austin R Benson. 2021. Combining label propagation and simple models out-performs graph neural networks. International Conference on Learning Representations, ICLR (2021)."},{"key":"e_1_2_1_29_1","volume-title":"International Conference on Learning Representations, ICLR.","author":"Kipf Thomas N","year":"2017","unstructured":"Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations, ICLR."},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the Conference on Artificial Intelligence, AAAI","volume":"36","author":"Kollias Georgios","year":"2022","unstructured":"Georgios Kollias, Vasileios Kalantzis, Tsuyoshi Id\u00e9, Aur\u00e9lie Lozano, and Naoki Abe. 2022. Directed Graph Auto-Encoders. In Proceedings of the Conference on Artificial Intelligence, AAAI, Vol. 36. 7211--7219."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753532"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330982"},{"key":"e_1_2_1_33_1","first-page":"121","article-title":"Controversial users demand local trust metrics: An experimental study on epinions. com community","volume":"1","author":"Massa Paolo","year":"2005","unstructured":"Paolo Massa and Paolo Avesani. 2005. Controversial users demand local trust metrics: An experimental study on epinions. com community. In AAAI, Vol. 1. 121--126.","journal-title":"AAAI"},{"key":"e_1_2_1_34_1","volume-title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks. arXiv preprint arXiv:2007.02901","author":"Mernyei P\u00e9ter","year":"2020","unstructured":"P\u00e9ter Mernyei and C\u00e1t\u00e1lina Cangea. 2020. Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks. arXiv preprint arXiv:2007.02901 (2020)."},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of The Web Conference, WWW. 1378--1388","author":"Ordozgoiti Bruno","year":"2020","unstructured":"Bruno Ordozgoiti, Antonis Matakos, and Aristides Gionis. 2020. Finding large balanced subgraphs in signed networks. In Proceedings of The Web Conference, WWW. 1378--1388."},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the ACM Web Conference, WWW. 1475--1485","author":"Schweimer Christoph","year":"2022","unstructured":"Christoph Schweimer, Christine Gfrerer, Florian Lugstein, David Pape, Jan A Velimsky, Robert Els\u00e4sser, and Bernhard C Geiger. 2022. Generating simple directed social network graphs for information spreading. In Proceedings of the ACM Web Conference, WWW. 1475--1485."},{"key":"e_1_2_1_37_1","volume-title":"International Joint Conference on Artificial Intelligence, IJCAI","author":"Shi Yunsheng","year":"2021","unstructured":"Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjin Wang, and Yu Sun. 2021. Masked label prediction: Unified message passing model for semi-supervised classification. International Joint Conference on Artificial Intelligence, IJCAI (2021)."},{"key":"e_1_2_1_38_1","volume-title":"Discrete magnetic laplacian. Communications in mathematical physics 164, 2","author":"Shubin MA","year":"1994","unstructured":"MA Shubin. 1994. Discrete magnetic laplacian. Communications in mathematical physics 164, 2 (1994), 259--275."},{"key":"e_1_2_1_39_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition, CVPR. 2818--2826","author":"Szegedy Christian","year":"2016","unstructured":"Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, CVPR. 2818--2826."},{"key":"e_1_2_1_40_1","first-page":"17907","article-title":"Digraph inception convolutional networks. Advances in neural information processing systems","volume":"33","author":"Tong Zekun","year":"2020","unstructured":"Zekun Tong, Yuxuan Liang, Changsheng Sun, Xinke Li, David Rosenblum, and Andrew Lim. 2020. Digraph inception convolutional networks. Advances in neural information processing systems, NeurIPS 33 (2020), 17907--17918.","journal-title":"NeurIPS"},{"key":"e_1_2_1_41_1","volume-title":"Directed graph convolutional network. arXiv preprint arXiv:2004.13970","author":"Tong Zekun","year":"2020","unstructured":"Zekun Tong, Yuxuan Liang, Changsheng Sun, David S Rosenblum, and Andrew Lim. 2020. Directed graph convolutional network. arXiv preprint arXiv:2004.13970 (2020)."},{"key":"e_1_2_1_42_1","volume-title":"International Conference on Learning Representations, ICLR.","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations, ICLR."},{"key":"e_1_2_1_43_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning, ICML.","author":"Wang Xiyuan","year":"2022","unstructured":"Xiyuan Wang and Muhan Zhang. 2022. How Powerful are Spectral Graph Neural Networks. In Proceedings of the 39th International Conference on Machine Learning, ICML."},{"key":"e_1_2_1_44_1","volume-title":"International conference on machine learning, ICML.","author":"Wu Felix","year":"2019","unstructured":"Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In International conference on machine learning, ICML."},{"key":"e_1_2_1_45_1","volume-title":"International conference on machine learning. PMLR, 5453--5462","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In International conference on machine learning. PMLR, 5453--5462."},{"key":"e_1_2_1_46_1","volume-title":"International Conference on Machine Learning, ICML. PMLR, 25261--25279","author":"Yang Mingqi","year":"2022","unstructured":"Mingqi Yang, Yanming Shen, Rui Li, Heng Qi, Qiang Zhang, and Baocai Yin. 2022. A new perspective on the effects of spectrum in graph neural networks. In International Conference on Machine Learning, ICML. PMLR, 25261--25279."},{"key":"e_1_2_1_47_1","volume-title":"MGC: A complex-valued graph convolutional network for directed graphs. arXiv e-prints","author":"Zhang Jie","year":"2021","unstructured":"Jie Zhang, Bo Hui, Po-Wei Harn, Min-Te Sun, and Wei-Shinn Ku. 2021. MGC: A complex-valued graph convolutional network for directed graphs. arXiv e-prints (2021), arXiv-2110."},{"key":"e_1_2_1_48_1","volume-title":"NeurIPS","author":"Zhang Muhan","year":"2018","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. Advances in neural information processing systems, NeurIPS (2018)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511986"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539121"},{"key":"e_1_2_1_51_1","first-page":"27003","article-title":"Magnet: A neural network for directed graphs. Advances in neural information processing systems","volume":"34","author":"Zhang Xitong","year":"2021","unstructured":"Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, and Matthew Hirn. 2021. Magnet: A neural network for directed graphs. Advances in neural information processing systems, NeurIPS 34 (2021), 27003--27015.","journal-title":"NeurIPS"},{"key":"e_1_2_1_52_1","volume-title":"Hierarchical graph pooling with structure learning. arXiv preprint arXiv:1911.05954","author":"Zhang Zhen","year":"2019","unstructured":"Zhen Zhang, Jiajun Bu, Martin Ester, Jianfeng Zhang, Chengwei Yao, Zhi Yu, and Can Wang. 2019. Hierarchical graph pooling with structure learning. arXiv preprint arXiv:1911.05954 (2019)."},{"key":"e_1_2_1_53_1","volume-title":"International conference on learning representations, ICLR.","author":"Zhu Hao","year":"2021","unstructured":"Hao Zhu and Piotr Koniusz. 2021. Simple spectral graph convolution. In International conference on learning representations, ICLR."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3654621.3654623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T22:25:21Z","timestamp":1717107921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3654621.3654623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":52,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10.14778\/3654621.3654623"],"URL":"https:\/\/doi.org\/10.14778\/3654621.3654623","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3]]},"assertion":[{"value":"2024-05-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}