{"type":"ScholarlyArticle","title":"Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities","authors":[{"name":"Chuang Liu","slug":"chuang-liu","given":"Chuang","family":"Liu","affiliation":"School of Computer Science , Wuhan University , Wuhan , China"},{"name":"Yibing Zhan","slug":"yibing-zhan","given":"Yibing","family":"Zhan","affiliation":"JD Explore Academy , JD .com , China"},{"name":"Jia Wu","slug":"jia-wu","given":"Jia","family":"Wu","affiliation":"School of Computing , Macquarie University , Sydney , Australia"},{"name":"Chang Li","slug":"chang-li","given":"Chang","family":"Li","affiliation":"JD Explore Academy , JD .com , China"},{"name":"Bo Du","slug":"bo-du","given":"Bo","family":"Du","affiliation":"National Engineering Research Center for Multimedia Software , Wuhan University , Wuhan , China"},{"name":"Wenbin Hu","slug":"wenbin-hu","given":"Wenbin","family":"Hu","affiliation":"School of Computer Science , Wuhan University , Wuhan , China"},{"name":"Tongliang Liu","slug":"tongliang-liu","given":"Tongliang","family":"Liu","affiliation":"School of Computer Science , University of Sydney , Sydney , Australia"},{"name":"Dacheng Tao","slug":"dacheng-tao","given":"Dacheng","family":"Tao","affiliation":"School of Computer Science , University of Sydney , Sydney , Australia"}],"abstract":"Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation. As an essential component of the architecture,  graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph. Although a great variety of methods have been proposed in this promising and fast-developing research field, to the best of our knowledge, little effort has been made to systematically summarize these works. To set the stage for the development of future works, in this paper, we attempt to fill this gap by providing a broad review of recent methods for graph pooling. Specifically, 1) we first propose a taxonomy of existing graph pooling methods with a mathematical summary for each category; 2) then, we provide an overview of the libraries related to graph pooling, including the commonly used datasets, model architectures for downstream tasks, and open-source implementations; 3) next, we further outline the applications that incorporate the idea of graph pooling in a variety of domains; 4) finally, we discuss certain critical challenges facing current studies and share our insights on future potential directions for research on the improvement of graph pooling.","doi":"10.24963/ijcai.2023/752","url":"https://ijcai.org/proceedings/2023/752","pdf":"https://ijcai.org/proceedings/2023/0752.pdf","markdown":"https://ijcai.org/proceedings/2023/752.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/752","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Survey Track","track":"Survey Track","number":752,"pages":{"first":6712,"last":6722},"keywords":["Survey: Data Mining","Survey: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Adnan et al., 2020] Mohammed Adnan, et al. Representa- tion learning of histopathology images using graph neural networks. In CVPR Workshop, 2020.","title":"Representation learning of histopathology images using graph neural networks","authors":"Adnan","year":"2020","venue":"CVPR Workshop","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Atwood and Towsley, 2016] James Atwood et al. Diffusion- convolutional neural networks. In NeurIPS, 2016.","title":"Diffusionconvolutional neural networks","authors":"James Atwood","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bacciu and Sotto, 2019] Davide Bacciu et al. A non- negative factorization approach to node pooling in graph convolutional neural networks. In AIIA, 2019.","title":"A nonnegative factorization approach to node pooling in graph convolutional neural networks","authors":"Davide Bacciu","year":"2019","venue":"AIIA","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Baek et al., 2021] Jinheon Baek, et al. Accurate learning of graph representations with graph multiset pooling. In ICLR, 2021.","title":"Accurate learning of graph representations with graph multiset pooling","authors":"Baek","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bai et al., 2019] Yunsheng Bai, et al. Unsupervised induc- tive graph-level representation learning via graph-graph proximity. In IJCAI, 2019.","title":"Unsupervised inductive graph-level representation learning via graph-graph proximity","authors":"Yunsheng Bai","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/275"},{"position":6,"raw":"[Bai et al., 2021] Lu Bai, et al. Learning graph convolutional networks based on quantum vertex information propaga- tion. IEEE TKDE, 2021.","title":"Learning graph convolutional networks based on quantum vertex information propagation","authors":"Lu Bai","year":"2021","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bianchi and Lachi, 2023] Filippo Maria Bianchi et al. The expressive power of pooling in graph neural networks. arXiv:2304.01575, 2023.","title":"The expressive power of pooling in graph neural networks","authors":"Maria Filippo, Bianchi","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Bianchi et al., 2020a] Filippo Maria Bianchi, et al. Spectral clustering with graph neural networks for graph pooling. In ICML, 2020.","title":"Spectral clustering with graph neural networks for graph pooling","authors":"Bianchi","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Bianchi et al., 2020b] Filippo Maria Bianchi, et al. Hier- archical representation learning in graph neural networks with node decimation pooling. IEEE TNNLS, 2020.","title":"Hierarchical representation learning in graph neural networks with node decimation pooling","authors":"Bianchi","year":"2020","venue":"IEEE TNNLS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Bodnar et al., 2020] Cristian Bodnar, et al. Deep graph mapper: Seeing graphs through the neural lens. In NeurIPS Workshop, 2020.","title":"Deep graph mapper: Seeing graphs through the neural lens","authors":"Cristian Bodnar","year":"2020","venue":"NeurIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Cangea et al., 2018] Cȃtȃlina Cangea, et al. Towards sparse hierarchical graph classifiers. arXiv:1811.01287, 2018.","title":"Towards sparse hierarchical graph classifiers","authors":"Cangea","year":"2018","venue":"Cȃtȃlina Cangea","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Chang et al., 2021] Jianxin Chang, et al. Sequential recom- mendation with graph neural networks. In SIGIR, 2021.","title":"Sequential recommendation with graph neural networks","authors":"Jianxin Chang","year":"2021","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Chen et al., 2019] Ting Chen, et al. Are powerful graph neural nets necessary? a dissection on graph classification. arXiv:1905.04579, 2019.","title":"Are powerful graph neural nets necessary? a dissection on graph classification","authors":"Ting Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Chen et al., 2020a] Chaofan Chen, et al. Hapgn: Hierarchi- cal attentive pooling graph network for point cloud seg- mentation. IEEE TMM, 2020.","title":"Hapgn: Hierarchical attentive pooling graph network for point cloud segmentation","authors":"Chen","year":"2020","venue":"IEEE TMM","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Chen et al., 2020b] Zhengdao Chen, et al. Can graph neural networks count substructures? In NeurIPS, 2020.","title":"Can graph neural networks count substructures?","authors":"Chen","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Chen et al., 2022] Kaixuan Chen, et al. Distribution knowl- edge embedding for graph pooling. IEEE TKDE, 2022.","title":"Distribution knowledge embedding for graph pooling","authors":"Kaixuan Chen","year":"2022","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Demir et al., 2021] Andac Demir, et al. Eeg-gnn: Graph neural networks for classification of electroencephalogram (eeg) signals. arXiv:2106.09135, 2021.","title":"Eeg-gnn: Graph neural networks for classification of electroencephalogram (eeg) signals","authors":"Demir","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Diehl, 2019] Frederik Diehl. Edge contraction pooling for graph neural networks. arXiv:1905.10990, 2019.","title":"Edge contraction pooling for graph neural networks","authors":"Frederik Diehl","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Du et al., 2021] Jinlong Du, et al. Multi-channel pooling graph neural networks. In IJCAI, 2021.","title":"Multi-channel pooling graph neural networks","authors":"Jinlong Du","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/199"},{"position":20,"raw":"[Duval and Malliaros, 2022] Alexandre Duval et al. Higher- order clustering and pooling for graph neural networks. In CIKM, 2022.","title":"Higherorder clustering and pooling for graph neural networks","authors":"Alexandre Duval","year":"2022","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Duvenaud et al., 2015] David Duvenaud, et al. Convolu- tional networks on graphs for learning molecular finger- prints. In NeurIPS, 2015.","title":"Convolutional networks on graphs for learning molecular fingerprints","authors":"David Duvenaud","year":"2015","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Dwivedi et al., 2020] Vijay Prakash Dwivedi, et al. Bench- marking graph neural networks. arXiv:2003.00982, 2020.","title":"Benchmarking graph neural networks","authors":"Vijay Prakash Dwivedi","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Errica et al., 2020] Federico Errica, et al. A fair comparison of graph neural networks for graph classification. In ICLR, 2020.","title":"A fair comparison of graph neural networks for graph classification","authors":"Federico Errica","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Fan et al., 2020] Xiaolong Fan, et al. Structured self- attention architecture for graph-level representation learn- ing. Pattern Recognition, 2020.","title":"Structured selfattention architecture for graph-level representation learning","authors":"Xiaolong Fan","year":"2020","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Fey et al., 2018] Matthias Fey, et al. Splinecnn: Fast geo- metric deep learning with continuous b-spline kernels. In CVPR, 2018.","title":"Splinecnn: Fast geometric deep learning with continuous b-spline kernels","authors":"Matthias Fey","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Gao and Ji, 2019] Hongyang Gao et al. Graph u-nets. In ICML, 2019.","title":"Graph u-nets","authors":"Ji ; Hongyang Gao, Gao","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Gao et al., 2019] Hongyang Gao, et al. Learning graph pooling and hybrid convolutional operations for text rep- resentations. In WWW, 2019.","title":"Learning graph pooling and hybrid convolutional operations for text representations","authors":"Gao","year":"2019","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Gao et al., 2020] Zhangyang Gao, et al. Lookhops: light multi-order convolution and pooling for graph classifica- tion. arXiv:2012.15741, 2020.","title":"Lookhops: light multi-order convolution and pooling for graph classification","authors":"Gao","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Gao et al., 2021a] H. Gao, et al. Topology-aware graph pooling networks. IEEE TPAMI, 2021.","title":"Topology-aware graph pooling networks","authors":"Gao","year":"2021","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Gao et al., 2021b] Xing Gao, et al. ipool-information- based pooling in hierarchical graph neural networks. IEEE TNNLS, 2021.","title":"ipool-informationbased pooling in hierarchical graph neural networks","authors":"Gao","year":"2021","venue":"IEEE TNNLS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Gaudelet et al., 2021] Thomas Gaudelet, et al. Utilizing graph machine learning within drug discovery and devel- opment. Briefings in Bioinformatics, 2021.","title":"Utilizing graph machine learning within drug discovery and development","authors":"Thomas Gaudelet","year":"2021","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Gopinath et al., 2022] Karthik Gopinath, et al. Learnable pooling in graph convolutional networks for brain surface analysis. IEEE TPAMI, 2022.","title":"Learnable pooling in graph convolutional networks for brain surface analysis","authors":"Karthik Gopinath","year":"2022","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Grattarola et al., 2021] Daniele Grattarola, et al. Un- derstanding pooling in graph neural networks. arXiv:2110.05292, 2021.","title":"Understanding pooling in graph neural networks","authors":"Daniele Grattarola","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Gu, 2021] Jindong Gu. Interpretable graph capsule net- works for object recognition. AAAI, 2021.","title":"Interpretable graph capsule networks for object recognition","authors":"Jindong Gu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Hermosilla et al., 2021] Pedro Hermosilla, et al. Intrinsic- extrinsic convolution and pooling for learning on 3d pro- tein structures. In ICLR, 2021.","title":"Intrinsicextrinsic convolution and pooling for learning on 3d protein structures","authors":"Hermosilla","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Holtz et al., 2019] Chester Holtz, et al. Multi-task learning on graphs with node and graph level labels. In NeurIPS Workshop, 2019.","title":"Multi-task learning on graphs with node and graph level labels","authors":"Holtz","year":"2019","venue":"NeurIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Hu et al., 2020] Weihua Hu, et al. Open graph bench- mark: Datasets for machine learning on graphs. arXiv:2005.00687, 2020.","title":"Open graph benchmark: Datasets for machine learning on graphs","authors":"Weihua Hu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Huang et al., 2019] Jingjia Huang, et al. Attpool: Towards hierarchical feature representation in graph convolutional networks via attention mechanism. In ICCV, 2019.","title":"Attpool: Towards hierarchical feature representation in graph convolutional networks via attention mechanism","authors":"Huang","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Isufi and Mazzola, 2021] Elvin Isufi et al. Graph-time con- volutional neural networks. arXiv:2103.01730, 2021.","title":"Graph-time convolutional neural networks","authors":"Mazzola Isufi, Elvin Isufi","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Itoh et al., 2022] Takeshi D. Itoh, et al. Multi-level atten- tion pooling for graph neural networks: Unifying graph representations with multiple localities. Neural Networks, 2022.","title":"Multi-level attention pooling for graph neural networks: Unifying graph representations with multiple localities","authors":"D Takeshi, Itoh","year":"2022","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Jo et al., 2021] Jaehyeong Jo, et al. Edge representation learning with hypergraphs. In NeurIPS, 2021.","title":"Edge representation learning with hypergraphs","authors":"Jo","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Khasahmadi et al., 2020] Amir Hosein Khasahmadi, et al. Memory-based graph networks. In ICLR, 2020.","title":"Memory-based graph networks","authors":"Amir Hosein Khasahmadi","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Kim et al., 2021] Byung-Hoon Kim, et al. Learning dy- namic graph representation of brain connectome with spatio-temporal attention. In NeurIPS, 2021.","title":"Learning dynamic graph representation of brain connectome with spatio-temporal attention","authors":"Byung-Hoon Kim","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Kipf and Welling, 2017] Thomas N. Kipf et al. Semi- supervised classification with graph convolutional net- works. In ICLR, 2017.","title":"Semisupervised classification with graph convolutional networks","authors":"N Thomas, Kipf","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Knyazev et al., 2019] Boris Knyazev, et al. Understanding attention and generalization in graph neural networks. In NeurIPS, 2019.","title":"Understanding attention and generalization in graph neural networks","authors":"Boris Knyazev","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Lee et al., 2019] Junhyun Lee, et al. Self-attention graph pooling. In ICML, 2019.","title":"Self-attention graph pooling","authors":"Lee","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Lee et al., 2021] Dongha Lee, et al. Learnable structural se- mantic readout for graph classification. In ICDM, 2021.","title":"Learnable structural semantic readout for graph classification","authors":"Lee","year":"2021","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Li et al., 2016] Yujia Li, et al. Gated graph sequence neural networks. In ICLR, 2016.","title":"Gated graph sequence neural networks","authors":"Yujia Li","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Li et al., 2020a] Juanhui Li, et al. Graph pooling with rep- resentativeness. In ICDM, 2020.","title":"Graph pooling with representativeness","authors":"Li","year":"2020","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Li et al., 2020b] Maosen Li, et al. Graph cross networks with vertex infomax pooling. In NeurIPS, 2020.","title":"Graph cross networks with vertex infomax pooling","authors":"Li","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Li et al., 2020c] Xiaoxiao Li, et al. Pooling regularized graph neural network for fmri biomarker analysis. In MIC- CAI, 2020.","title":"Pooling regularized graph neural network for fmri biomarker analysis","authors":"Li","year":"2020","venue":"MIC-CAI","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Li et al., 2021a] Jia Li, et al. Deconvolutional networks on graph data. NeurIPS, 2021.","title":"Deconvolutional networks on graph data","authors":"Li","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Li et al., 2021b] Shuangli Li, et al. Structure-aware inter- active graph neural networks for the prediction of protein- ligand binding affinity. In KDD, 2021.","title":"Structure-aware interactive graph neural networks for the prediction of proteinligand binding affinity","authors":"Li","year":"2021","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Li et al., 2021c] Xiaoxiao Li, et al. Braingnn: Interpretable brain graph neural network for fmri analysis. Medical Im- age Analysis, 2021.","title":"Braingnn: Interpretable brain graph neural network for fmri analysis","authors":"Li","year":"2021","venue":"Medical Image Analysis","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Liang et al., 2020] Yanyan Liang, et al. Mxpool: Multi- plex pooling for hierarchical graph representation learn- ing. arXiv:2004.06846, 2020.","title":"Mxpool: Multiplex pooling for hierarchical graph representation learning","authors":"Yanyan Liang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":56,"raw":"[Liu et al., 2020] Fanzhen Liu, et al. Deep learning for com- munity detection: progress, challenges and opportunities. In IJCAI, 2020.","title":"Deep learning for community detection: progress, challenges and opportunities","authors":"Liu","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/693"},{"position":57,"raw":"[Liu et al., 2021a] Ning Liu, et al. Hierarchical adaptive pooling by capturing high-order dependency for graph rep- resentation learning. IEEE TKDE, 2021.","title":"Hierarchical adaptive pooling by capturing high-order dependency for graph representation learning","authors":"Liu","year":"2021","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":58,"raw":"[Liu et al., 2021b] Y. Liu, et al. Learning hierarchical review graph representations for recommendation. IEEE TKDE, 2021.","title":"Learning hierarchical review graph representations for recommendation","authors":"Liu","year":"2021","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":59,"raw":"[Liu et al., 2022a] Chuang Liu, et al. On exploring node- feature and graph-structure diversities for node drop graph pooling, 2022.","title":"On exploring nodefeature and graph-structure diversities for node drop graph pooling","authors":"Liu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":60,"raw":"[Liu et al., 2022b] Ning Liu, et al. Unsupervised hierarchi- cal graph pooling via substructure-sensitive mutual infor- mation maximization. In CIKM, 2022.","title":"Unsupervised hierarchical graph pooling via substructure-sensitive mutual information maximization","authors":"Liu","year":"2022","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":61,"raw":"[Liu et al., 2023] Chuang Liu, et al. Masked graph auto- encoder constrained graph pooling. In ECML-PKDD, 2023.","title":"Masked graph autoencoder constrained graph pooling","authors":"Chuang Liu","year":"2023","venue":"ECML-PKDD","doi":null,"url":null,"internal_url":null},{"position":62,"raw":"[Ma et al., 2019] Yao Ma, et al. Graph convolutional net- works with eigenpooling. In KDD, 2019.","title":"Graph convolutional networks with eigenpooling","authors":"Yao Ma","year":"2019","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":63,"raw":"[Ma et al., 2020] Zheng Ma, et al. Path integral based convo- lution and pooling for graph neural networks. In NeurIPS, 2020.","title":"Path integral based convolution and pooling for graph neural networks","authors":"Zheng Ma","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":64,"raw":"[Ma et al., 2021] Xiaoxiao Ma, et al. A comprehensive sur- vey on graph anomaly detection with deep learning. IEEE TKDE, 2021.","title":"A comprehensive survey on graph anomaly detection with deep learning","authors":"Xiaoxiao Ma","year":"2021","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":65,"raw":"[Mai et al., 2020] Sijie Mai, et al. Analyzing unaligned mul- timodal sequence via graph convolution and graph pooling fusion. arXiv:2011.13572, 2020.","title":"Analyzing unaligned multimodal sequence via graph convolution and graph pooling fusion","authors":"Sijie Mai","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":66,"raw":"[Mao et al., 2022] Qianren Mao, et al. Higil: Hierarchical graph inference learning for fact checking. In ICDM, 2022.","title":"Higil: Hierarchical graph inference learning for fact checking","authors":"Mao","year":"2022","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":67,"raw":"[Mesquita et al., 2020] Diego Mesquita, et al. Rethinking pooling in graph neural networks. In NeurIPS, 2020.","title":"Rethinking pooling in graph neural networks","authors":"Mesquita","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":68,"raw":"[Morris et al., 2020] Christopher Morris, et al. Tudataset: A collection of benchmark datasets for learning with graphs. arXiv:2007.08663, 2020.","title":"Tudataset: A collection of benchmark datasets for learning with graphs","authors":"Christopher Morris","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":69,"raw":"[Murphy et al., 2019] Ryan Murphy, et al. Relational pool- ing for graph representations. In ICML, 2019.","title":"Relational pooling for graph representations","authors":"Ryan Murphy","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":70,"raw":"[Nadgeri et al., 2021] Abhishek Nadgeri, et al. KGPool: Dy- namic knowledge graph context selection for relation ex- traction. In ACL, 2021.","title":"KGPool: Dynamic knowledge graph context selection for relation extraction","authors":"Nadgeri","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":71,"raw":"[Navarin et al., 2019] Nicolò Navarin, et al. Universal read- out for graph convolutional neural networks. In IJCNN, 2019.","title":"Universal readout for graph convolutional neural networks","authors":"Navarin","year":"2019","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":72,"raw":"[Noutahi et al., 2019] Emmanuel Noutahi, et al. Towards in- terpretable sparse graph representation learning with lapla- cian pooling. arXiv:1905.11577, 2019.","title":"Towards interpretable sparse graph representation learning with laplacian pooling","authors":"Emmanuel Noutahi","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":73,"raw":"[Pan et al., 2021] Li Pan, et al. Identifying autism spectrum disorder based on individual-aware down-sampling and multi-modal learning. arXiv:2109.09129, 2021.","title":"Identifying autism spectrum disorder based on individual-aware down-sampling and multi-modal learning","authors":"Li Pan","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":74,"raw":"[Pang et al., 2021] Yunsheng Pang, et al. Graph pooling via coarsened graph infomax. In SIGIR, 2021.","title":"Graph pooling via coarsened graph infomax","authors":"Yunsheng Pang","year":"2021","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":75,"raw":"[Papp et al., 2021] Pál András Papp, et al. Dropgnn: Ran- dom dropouts increase the expressiveness of graph neural networks. NeurIPS, 2021.","title":"Dropgnn: Random dropouts increase the expressiveness of graph neural networks","authors":"Pál András Papp","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":76,"raw":"[Qin et al., 2020] Jian Qin, et al. Uniform pooling for graph networks. Appl. Sci., 2020.","title":"Uniform pooling for graph networks","authors":"Jian Qin","year":"2020","venue":"Appl. Sci","doi":null,"url":null,"internal_url":null},{"position":77,"raw":"[Ranjan et al., 2020] Ekagra Ranjan, et al. Asap: Adap- tive structure aware pooling for learning hierarchical graph representations. In AAAI, 2020.","title":"Asap: Adaptive structure aware pooling for learning hierarchical graph representations","authors":"Ranjan","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":78,"raw":"[Rhee et al., 2018] Sungmin Rhee, et al. Hybrid approach of relation network and localized graph convolutional fil- tering for breast cancer subtype classification. In IJCAI, 2018.","title":"Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification","authors":"Rhee","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/490"},{"position":79,"raw":"[Roy et al., 2021] Kashob Kumar Roy, et al. Structure-aware hierarchical graph pooling using information bottleneck. In IJCNN, 2021.","title":"Structure-aware hierarchical graph pooling using information bottleneck","authors":"Roy","year":"2021","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":80,"raw":"[Shen et al., 2018] Y. Shen, et al. Mining point cloud lo- cal structures by kernel correlation and graph pooling. In CVPR, 2018.","title":"Mining point cloud local structures by kernel correlation and graph pooling","authors":"Y Shen","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":81,"raw":"[Shirian et al., 2022] Amir Shirian, et al. Dynamic emotion modeling with learnable graphs and graph inception net- work. IEEE TMM, 2022.","title":"Dynamic emotion modeling with learnable graphs and graph inception network","authors":"Amir Shirian","year":"2022","venue":"IEEE TMM","doi":null,"url":null,"internal_url":null},{"position":82,"raw":"[Simonovsky and Komodakis, 2017] Martin Simonovsky et al. Dynamic edge-conditioned filters in convolutional neural networks on graphs. In CVPR, 2017.","title":"Dynamic edge-conditioned filters in convolutional neural networks on graphs","authors":"Martin Simonovsky","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":83,"raw":"[Su et al., 2021] Zidong Su, et al. Hierarchical graph repre- sentation learning with local capsule pooling. In MMAsia, 2021.","title":"Hierarchical graph representation learning with local capsule pooling","authors":"Su","year":"2021","venue":"MMAsia","doi":null,"url":null,"internal_url":null},{"position":84,"raw":"[Tak et al., 2021] Hemlata Tak, et al. End-to-end spectro- temporal graph attention networks for speaker veri- fication anti-spoofing and speech deepfake detection. arXiv:2107.12710, 2021.","title":"End-to-end spectrotemporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection","authors":"Hemlata Tak","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":85,"raw":"[Tang et al., 2020] Haoteng Tang, et al. Adversarial at- tack on hierarchical graph pooling neural networks. arXiv:2005.11560, 2020.","title":"Adversarial attack on hierarchical graph pooling neural networks","authors":"Tang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":86,"raw":"[Tang et al., 2021] Haoteng Tang, et al. Commpool: An interpretable graph pooling framework for hierarchical graph representation learning. Neural Networks, 2021.","title":"Commpool: An interpretable graph pooling framework for hierarchical graph representation learning","authors":"Tang","year":"2021","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":87,"raw":"[Vinyals et al., 2016] Oriol Vinyals, et al. Order matters: Se- quence to sequence for sets. In ICLR, 2016.","title":"Order matters: Sequence to sequence for sets","authors":"Vinyals","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":88,"raw":"[Wang and Ji, 2020] Zhengyang Wang et al. Second-order pooling for graph neural networks. IEEE TPAMI, 2020.","title":"Second-order pooling for graph neural networks","authors":"Wang, Ji ; Zhengyang Wang","year":"2020","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":89,"raw":"[Wang et al., 2020] Yu Guang Wang, et al. Haar graph pool- ing. In ICML, 2020.","title":"Haar graph pooling","authors":"Yu Guang, Wang","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":90,"raw":"[Wang et al., 2021] Jie Wang, et al. Papooling: Graph-based position adaptive aggregation of local geometry in point clouds. arXiv:2111.14067, 2021.","title":"Papooling: Graph-based position adaptive aggregation of local geometry in point clouds","authors":"Jie Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":91,"raw":"[Wei et al., 2021] Lanning Wei, et al. Pooling architecture search for graph classification. In CIKM, 2021.","title":"Pooling architecture search for graph classification","authors":"Lanning Wei","year":"2021","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":92,"raw":"[Wu and others, 2022] Junran Wu et al. Structural entropy guided graph hierarchical pooling. In ICML, 2022.","title":"Structural entropy guided graph hierarchical pooling","authors":"Others ; Junran Wu, Wu","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":93,"raw":"[Wu et al., 2019] Jun Wu, et al. Demo-net: Degree-specific graph neural networks for node and graph classification. In KDD, 2019.","title":"Demo-net: Degree-specific graph neural networks for node and graph classification","authors":"Wu","year":"2019","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":94,"raw":"[Wu et al., 2021] Chuhan Wu, et al. User-as-graph: User modeling with heterogeneous graph pooling for news rec- ommendation. In IJCAI, 2021.","title":"User-as-graph: User modeling with heterogeneous graph pooling for news recommendation","authors":"Wu","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/224"},{"position":95,"raw":"[Xu et al., 2019] Keyulu Xu, et al. How powerful are graph neural networks? In ICLR, 2019.","title":"How powerful are graph neural networks?","authors":"Xu","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":96,"raw":"[Xu et al., 2021] Keyulu Xu, et al. How neural networks ex- trapolate: From feedforward to graph neural networks. In ICLR, 2021.","title":"How neural networks extrapolate: From feedforward to graph neural networks","authors":"Xu","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":97,"raw":"[Yang et al., 2021] Jinyu Yang, et al. Hierarchical graph cap- sule network. In AAAI, 2021.","title":"Hierarchical graph capsule network","authors":"Jinyu Yang","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":98,"raw":"[Ying et al., 2018] Zhitao Ying, et al. Hierarchical graph representation learning with differentiable pooling. In NeurIPS, 2018.","title":"Hierarchical graph representation learning with differentiable pooling","authors":"Ying","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":99,"raw":"[Yuan and Ji, 2020] Hao Yuan et al. Structpool: Structured graph pooling via conditional random fields. In ICLR, 2020.","title":"Structpool: Structured graph pooling via conditional random fields","authors":"Hao Yuan","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":100,"raw":"[Yuan et al., 2020] Hao Yuan, et al. Explainability in graph neural networks: A taxonomic survey. arXiv:2012.15445, 2020.","title":"Explainability in graph neural networks: A taxonomic survey","authors":"Hao Yuan","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":101,"raw":"[Zeng et al., 2021] Hanqing Zeng, et al. Decoupling the depth and scope of graph neural networks. In NeurIPS, 2021.","title":"Decoupling the depth and scope of graph neural networks","authors":"Hanqing Zeng","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":102,"raw":"[Zhang et al., 2018] Muhan Zhang, et al. An end-to-end deep learning architecture for graph classification. In AAAI, 2018.","title":"An end-to-end deep learning architecture for graph classification","authors":"Zhang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":103,"raw":"[Zhang et al., 2020a] Liang Zhang, et al. Structure-feature based graph self-adaptive pooling. In WWW, 2020.","title":"Structure-feature based graph self-adaptive pooling","authors":"Zhang","year":"2020","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":104,"raw":"[Zhang et al., 2020b] Zhen Zhang, et al. Hierarchical graph pooling with structure learning. In AAAI, 2020.","title":"Hierarchical graph pooling with structure learning","authors":"Zhang","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":105,"raw":"[Zhang et al., 2021] Zhen Zhang, et al. Hierarchical multi- view graph pooling with structure learning. IEEE TKDE, 2021.","title":"Hierarchical multiview graph pooling with structure learning","authors":"Zhen Zhang","year":"2021","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":106,"raw":"[Zhong et al., 2022] Zhiqiang Zhong, et al. Multi-grained semantics-aware graph neural networks. IEEE TKDE, 2022.","title":"Multi-grained semantics-aware graph neural networks","authors":"Zhiqiang Zhong","year":"2022","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":107,"raw":"[Zhou et al., 2020] Kaixiong Zhou, et al. Multi-channel graph neural networks. In IJCAI, 2020.","title":"Multi-channel graph neural networks","authors":"Zhou","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/188"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}