{"type":"ScholarlyArticle","title":"MMGNN: A Molecular Merged Graph Neural Network for Explainable Solvation Free Energy Prediction","authors":[{"name":"Wenjie Du","slug":"wenjie-du","given":"Wenjie","family":"Du","affiliation":"University of Science and Technology of China (USTC) , Hefei , China; Suzhou Institute for Advanced Research , USTC , Suzhou , China"},{"name":"Shuai Zhang","slug":"shuai-zhang","given":"Shuai","family":"Zhang","affiliation":"University of Science and Technology of China (USTC) , Hefei , China; Suzhou Institute for Advanced Research , USTC , Suzhou , China"},{"name":"Di Wu","slug":"di-wu","given":"Di","family":"Wu","affiliation":"University of Science and Technology of China (USTC) , Hefei , China"},{"name":"Jun Xia","slug":"jun-xia","given":"Jun","family":"Xia","affiliation":"Zhejiang University , Hangzhou , China"},{"name":"Ziyuan Zhao","slug":"ziyuan-zhao","given":"Ziyuan","family":"Zhao","affiliation":"Agency for Science, Technology and Research (A*STAR) , Singapore"},{"name":"Junfeng Fang","slug":"junfeng-fang","given":"Junfeng","family":"Fang","affiliation":"University of Science and Technology of China (USTC) , Hefei , China"},{"name":"Yang Wang","slug":"yang-wang","given":"Yang","family":"Wang","affiliation":"University of Science and Technology of China (USTC) , Hefei , China; Suzhou Institute for Advanced Research , USTC , Suzhou , China"}],"abstract":"In this paper, we address the challenge of accurately modeling and predicting Gibbs free energy in solute-solvent interactions, a pivotal yet complex aspect in the field of chemical modeling. Traditional approaches, primarily relying on deep learning models, face limitations in capturing the intricate dynamics of these interactions. To overcome these constraints, we introduce a novel framework, molecular modeling graph neural network (MMGNN), which more closely mirrors real-world chemical processes.Specifically, MMGNN explicitly models atomic interactions such as hydrogen bonds by initially forming indiscriminate connections between intermolecular atoms, which are then refined using an attention-based aggregation method, tailoring to specific solute-solvent pairs.  To address the challenges of non-interactive or repulsive atomic interactions, MMGNN incorporates interpreters for nodes and edges in the merged graph, enhancing explainability and reducing redundancy. MMGNN stands as the first framework to explicitly align with real chemical processes, providing a more accurate and scientifically sound approach to modeling solute-solvent interactions. The infusion of explainability allows for the extraction of key subgraphs, which are pivotal for further research in solute-solvent dynamics. Extensive experimental validation confirms the efficacy and enhanced explainability of MMGNN.","doi":"10.24963/ijcai.2024/642","url":"https://ijcai.org/proceedings/2024/642","pdf":"https://ijcai.org/proceedings/2024/0642.pdf","markdown":"https://ijcai.org/proceedings/2024/642.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/642","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":642,"pages":{"first":5808,"last":5816},"keywords":["Machine Learning: ML: Applications","Data Mining: DM: Applications","Multidisciplinary Topics and Applications: MTA: Bioinformatics"],"videos":[],"references":[{"position":1,"raw":"[Behler, 2015] Jörg Behler. Constructing high-dimensional neural network potentials: a tutorial review. Interna- tional Journal of Quantum Chemistry, 115(16):1032- 1050, 2015.","title":"Constructing high-dimensional neural network potentials: a tutorial review","authors":"Jörg Behler, Behler","year":"2015","venue":"International Journal of Quantum Chemistry","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Behler, 2016] Jörg Behler. Perspective: Machine learning potentials for atomistic simulations. The Journal of chem- ical physics, 145(17):170901, 2016.","title":"Perspective: Machine learning potentials for atomistic simulations","authors":"Jörg Behler, Behler","year":"2016","venue":"The Journal of chemical physics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chung et al., 2022] Y. Chung, F. H. Vermeire, H. Y. Wu, P. J. Walker, M. H. Abraham, and W. H. Green. Group con- tribution and machine learning approaches to predict abra- ham solute parameters, solvation free energy, and solva- tion enthalpy. Journal of Chemical Information and Mod- eling, 62(3):433-446, 2022.","title":"Group contribution and machine learning approaches to predict abraham solute parameters, solvation free energy, and solvation enthalpy","authors":"Y Chung, F H Vermeire, H Y Wu, P J Walker, M H Abraham, W H Green","year":"2022","venue":"Journal of Chemical Information and Modeling","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[D'Souza et al., 2011] Malcolm J. D'Souza, Anthony M. Darrington, and Dennis N. Kevill. A study of solvent ef- fects in the solvolysis of propargyl chloroformate. Inter- national Scholarly Research Notices, 2011, 2011.","title":"A study of solvent effects in the solvolysis of propargyl chloroformate","authors":"J Malcolm, Anthony M D'souza, Dennis N Darrington, Kevill","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fang et al., 2022] Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, Jingbo Zhou, Fan Wang, Hua Wu, and Haifeng Wang. Geometry-enhanced molecu- lar representation learning for property prediction. Nature Machine Intelligence, 4(2):127-134, 2022.","title":"Geometry-enhanced molecular representation learning for property prediction","authors":"Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, Jingbo Zhou, Fan Wang, Hua Wu, Haifeng Wang","year":"2022","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fang et al., 2023a] Junfeng Fang, Wei Liu, Yuan Gao, Zemin Liu, An Zhang, Xiang Wang, and Xiangnan He. Evaluating post-hoc explanations for graph neural net- works via robustness analysis. In Thirty-seventh Confer- ence on Neural Information Processing Systems, 2023.","title":"Evaluating post-hoc explanations for graph neural networks via robustness analysis","authors":"Fang","year":"2023","venue":"Thirty-seventh Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fang et al., 2023b] Junfeng Fang, Wei Liu, An Zhang, Xi- ang Wang, Xiangnan He, Kun Wang, and Tat-Seng Chua. On regularization for explaining graph neural networks: An information theory perspective, 2023.","title":"On regularization for explaining graph neural networks: An information theory perspective","authors":"Fang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fang et al., 2023c] Junfeng Fang, Xiang Wang, An Zhang, Zemin Liu, Xiangnan He, and Tat-Seng Chua. Coopera- tive explanations of graph neural networks. In Proceed- ings of the Sixteenth ACM International Conference on Web Search and Data Mining, pages 616-624, 2023.","title":"Cooperative explanations of graph neural networks","authors":"Fang","year":"2023","venue":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fang et al., 2024a] Junfeng Fang, Xinglin Li, Yongduo Sui, Yuan Gao, Guibin Zhang, Kun Wang, Xiang Wang, and Xiangnan He. EXGC: bridging efficiency and explainabil- ity in graph condensation. CoRR, abs/2402.05962, 2024.","title":"EXGC: bridging efficiency and explainability in graph condensation","authors":"Fang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fang et al., 2024b] Junfeng Fang, Shuai Zhang, Chang Wu, Zhengyi Yang, Zhiyuan Liu, Sihang Li, Kun Wang, Wenjie Du, and Xiang Wang. Moltc: Towards molecular relational modeling in language models. CoRR, abs/2402.03781, 2024.","title":"Moltc: Towards molecular relational modeling in language models","authors":"Fang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Glick et al., 2020] Zachary L. Glick, Derek P. Metcalf, Alexios Koutsoukas, Steven A. Spronk, Daniel L. Cheney, and C. David Sherrill. Ap-net: An atomic-pairwise neural network for smooth and transferable interaction potentials. The Journal of Chemical Physics, 153(4):044112, 2020.","title":"Ap-net: An atomic-pairwise neural network for smooth and transferable interaction potentials","authors":"Zachary L Glick, Derek P Metcalf, Alexios Koutsoukas, Steven A Spronk, Daniel L Cheney, C David Sherrill","year":"2020","venue":"The Journal of Chemical Physics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Grubbs et al., 2010] Laura M. Grubbs, Mariam Saifullah, E. Nohelli, Shulin Ye, Sai S. Achi, William E. Acree Jr, and Michael H. Abraham. Mathematical correlations for describing solute transfer into functionalized alkane sol- vents containing hydroxyl, ether, ester or ketone solvents. Fluid phase equilibria, 298(1):48-53, 2010.","title":"Mathematical correlations for describing solute transfer into functionalized alkane solvents containing hydroxyl, ether, ester or ketone solvents","authors":"Laura M Grubbs, Mariam Saifullah, E Nohelli, Shulin Ye, S Sai, William E Achi, Michael H Acree, Abraham","year":"2010","venue":"Fluid phase equilibria","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hildebrand, 1981] J. H. Hildebrand. A history of solution theory. Annual Review of Physical Chemistry, 32:1-23, 1981.","title":"A history of solution theory","authors":"J H Hildebrand","year":"1981","venue":"Annual Review of Physical Chemistry","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Klamt and Eckert, 2000] A. Klamt and F. Eckert. Cosmo- rs: a novel and efficient method for the a priori prediction of thermophysical data of liquids. Fluid Phase Equilibria, 172(1):43-72, 2000.","title":"Cosmors: a novel and efficient method for the a priori prediction of thermophysical data of liquids","authors":"Eckert Klamt, A Klamt, F Eckert","year":"2000","venue":"Fluid Phase Equilibria","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lee et al., 2023] Namkyeong Lee, Dongmin Hyun, Gy- oung S. Na, Sungwon Kim, Junseok Lee, and Chanyoung Park. Conditional graph information bottleneck for molec- ular relational learning. arXiv preprint arXiv:2305.01520, 2023.","title":"Conditional graph information bottleneck for molecular relational learning","authors":"Lee","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Low et al., 2022] K. Low, M. L. Coote, and E. I. Izgorod- ina. Explainable solvation free energy prediction combin- ing graph neural networks with chemical intuition. J Chem Inf Model, 62(22):5457-5470, 2022.","title":"Explainable solvation free energy prediction combining graph neural networks with chemical intuition","authors":"K Low, M L Coote, E I Izgorodina","year":"2022","venue":"J Chem Inf Model","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Maas et al., 2013] Andrew L Maas, Awni Y Hannun, An- drew Y Ng, et al. Rectifier nonlinearities improve neu- ral network acoustic models. In Proc. icml, volume 30, page 3. Atlanta, GA, 2013.","title":"Rectifier nonlinearities improve neural network acoustic models","authors":"Andrew L Maas, Andrew Y Awni Y Hannun, Ng","year":"2013","venue":"Proc. icml","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Marenich et al., 2007] A. V. Marenich, R. M. Olson, C. P. Kelly, C. J. Cramer, and D. G. Truhlar. Self-consistent reaction field model for aqueous and nonaqueous solu- tions based on accurate polarized partial charges. Journal of Chemical Theory and Computation, 3(6):2011-2033, 2007.","title":"Self-consistent reaction field model for aqueous and nonaqueous solutions based on accurate polarized partial charges","authors":"A V Marenich, R M Olson, C P Kelly, C J Cramer, D G Truhlar","year":"2007","venue":"Journal of Chemical Theory and Computation","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Meng et al., 2023] Fanwang Meng, Hanwen Zhang, Juan Samuel Collins-Ramirez, and Paul W. Ayers. Something for nothing: Improved solvation free energy prediction with -learning. 2023.","title":"Something for nothing: Improved solvation free energy prediction with -learning","authors":"Meng","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Miao et al., 2022] Siqi Miao, Mia Liu, and Pan Li. Inter- pretable and generalizable graph learning via stochastic at- tention mechanism. In ICML, pages 15524-15543, 2022.","title":"Interpretable and generalizable graph learning via stochastic attention mechanism","authors":"Siqi Miao, Mia Liu, Pan Li","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mobley and Guthrie, 2014] David L. Mobley and J. Peter Guthrie. Freesolv: a database of experimental and cal- culated hydration free energies, with input files. Journal of computer-aided molecular design, 28:711-720, 2014.","title":"Freesolv: a database of experimental and calculated hydration free energies, with input files","authors":"David L Mobley, J Peter Guthrie","year":"2014","venue":"Journal of computer-aided molecular design","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Moine et al., 2017] Edouard Moine, Romain Privat, Bap- tiste Sirjean, and Jean-Noël Jaubert. Estimation of sol- vation quantities from experimental thermodynamic data: Development of the comprehensive compsol databank for pure and mixed solutes. Journal of Physical and Chemical Reference Data, 46(3):033102, 2017.","title":"Estimation of solvation quantities from experimental thermodynamic data: Development of the comprehensive compsol databank for pure and mixed solutes","authors":"Edouard Moine, Romain Privat, Baptiste Sirjean, Jean-Noël Jaubert","year":"2017","venue":"Journal of Physical and Chemical Reference Data","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pathak et al., 2020] Yashaswi Pathak, Siddhartha Laghu- varapu, Sarvesh Mehta, and U Deva Priyakumar. Chemi- cally interpretable graph interaction network for prediction of pharmacokinetic properties of drug-like molecules. In Proceedings of the AAAI Conference on Artificial Intelli- gence, volume 34, pages 873-880, 2020.","title":"Chemically interpretable graph interaction network for prediction of pharmacokinetic properties of drug-like molecules","authors":"Pathak","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Rong et al., 2020] Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, and Junzhou Huang. Self-supervised graph transformer on large-scale molecular data. Advances in Neural Information Process- ing Systems, 33:12559-12571, 2020.","title":"Self-supervised graph transformer on large-scale molecular data","authors":"Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, Junzhou Huang","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Varghese and Mushrif, 2019] Jithin John Varghese and Samir H Mushrif. Origins of complex solvent effects on chemical reactivity and computational tools to investigate them: a review. Reaction Chemistry & Engineering, 4(2):165-206, 2019.","title":"Origins of complex solvent effects on chemical reactivity and computational tools to investigate them: a review","authors":"John Jithin, Varghese, H Samir, Mushrif","year":"2019","venue":"Reaction Chemistry & Engineering","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Velickovic et al., 2017] Petar Velickovic, Guillem Cucu- rull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio, et al. Graph attention networks. stat, 1050(20):10-48550, 2017.","title":"Graph attention networks","authors":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2017","venue":"stat","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vermeire and Green, 2021] Florence H Vermeire and William H Green. Transfer learning for solvation free energies: From quantum chemistry to experiments. Chemical Engineering Journal, 418:129307, 2021.","title":"Transfer learning for solvation free energies: From quantum chemistry to experiments","authors":"Green ; Vermeire, H Florence, William H Vermeire, Green","year":"2021","venue":"Chemical Engineering Journal","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2023] Binwu Wang, Yudong Zhang, Jiahao Shi, Pengkun Wang, Xu Wang, Lei Bai, and Yang Wang. Knowledge expansion and consolidation for continual traf- fic prediction with expanding graphs. IEEE Transactions on Intelligent Transportation Systems, 2023.","title":"Knowledge expansion and consolidation for continual traffic prediction with expanding graphs","authors":"Wang","year":"2023","venue":"IEEE Transactions on Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2024] Binwu Wang, Pengkun Wang, Yudong Zhang, Xu Wang, Zhengyang Zhou, Lei Bai, and Yang Wang. Towards dynamic spatial-temporal graph learning: A decoupled perspective. In Proceedings of the AAAI Con- ference on Artificial Intelligence, volume 38, pages 9089- 9097, 2024.","title":"Towards dynamic spatial-temporal graph learning: A decoupled perspective","authors":"Wang","year":"2024","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wen et al., 2021] Mingjian Wen, Samuel M. Blau, Evan Walter Clark Spotte-Smith, Shyam Dwaraknath, and Kristin A. Persson. Bondnet: a graph neural network for the prediction of bond dissociation energies for charged molecules. Chemical science, 12(5):1858-1868, 2021.","title":"Bondnet: a graph neural network for the prediction of bond dissociation energies for charged molecules","authors":"Mingjian Wen, Samuel M Blau, Evan Walter, Clark Spotte-Smith, Shyam Dwaraknath, Kristin A Persson","year":"2021","venue":"Chemical science","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Wu et al., 2020] Tailin Wu, Hongyu Ren, Pan Li, and Jure Leskovec. Graph information bottleneck. In NeurIPS, 2020.","title":"Graph information bottleneck","authors":"Tailin Wu, Hongyu Ren, Pan Li, Jure Leskovec","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Xia et al., 2023a] Jun Xia, Haitao Lin, Yongjie Xu, Cheng Tan, Lirong Wu, Siyuan Li, and Stan Z Li. Gnn cleaner: Label cleaner for graph structured data. IEEE Transactions on Knowledge and Data Engineering, 2023.","title":"Gnn cleaner: Label cleaner for graph structured data","authors":"Xia","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Xia et al., 2023b] Jun Xia, Yanqiao Zhu, Yuanqi Du, Yue Liu, and Stan Z Li. A systematic survey of chemical pre- trained models. IJCAI, 2023.","title":"A systematic survey of chemical pretrained models","authors":"Xia","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yao et al., 2018] Kun Yao, John E. Herr, David W. Toth, Ryker McKintyre, and John Parkhill. The tensormol-0.1 model chemistry: a neural network augmented with long- range physics. Chemical science, 9(8):2261-2269, 2018.","title":"The tensormol-0.1 model chemistry: a neural network augmented with longrange physics","authors":"Kun Yao, John E Herr, David W Toth, Ryker Mckintyre, John Parkhill","year":"2018","venue":"Chemical science","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Ying et al., 2019] Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. Gnnexplainer: Generating explanations for graph neural networks. In NeurIPS, pages 9240-9251, 2019.","title":"Gnnexplainer: Generating explanations for graph neural networks","authors":"Ying","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Yu et al., 2021] Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, Junzhou Huang, and Ran He. Graph information bottleneck for subgraph recognition. In ICLR. OpenRe- view.net, 2021.","title":"Graph information bottleneck for subgraph recognition","authors":"Yu","year":"2021","venue":"ICLR. OpenReview.net","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Yu et al., 2023] Jiahui Yu, Chengwei Zhang, Yingying Cheng, Yun-Fang Yang, Yuan-Bin She, Fengfan Liu, Weike Su, and An Su. Solvbert for solvation free energy and solubility prediction: a demonstration of an nlp model for predicting the properties of molecular complexes. Dig- ital Discovery, 2(2):409-421, 2023.","title":"Solvbert for solvation free energy and solubility prediction: a demonstration of an nlp model for predicting the properties of molecular complexes","authors":"Jiahui Yu, Chengwei Zhang, Yingying Cheng, Yun-Fang Yang, Yuan-Bin She, Fengfan Liu, Weike Su, An Su","year":"2023","venue":"Digital Discovery","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zhang et al., 2022] D. D. Zhang, S. Xia, and Y. K. Zhang. Accurate prediction of aqueous free solvation energies us- ing 3d atomic feature-based graph neural network with transfer learning. Journal of Chemical Information and Modeling, 62(8):1840-1848, 2022.","title":"Accurate prediction of aqueous free solvation energies using 3d atomic feature-based graph neural network with transfer learning","authors":"D D Zhang, S Xia, Y K Zhang","year":"2022","venue":"Journal of Chemical Information and Modeling","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhou et al., 2023a] Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. Uni-mol: a universal 3d molecular representation learning framework. 2023.","title":"Uni-mol: a universal 3d molecular representation learning framework","authors":"Zhou","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zhou et al., 2023b] Zhengyang Zhou, Qihe Huang, Gengyu Lin, Kuo Yang, Lei Bai, and Yang Wang. Greto: reme- dying dynamic graph topology-task discordance via target homophily. In The eleventh international conference on learning representations, 2023.","title":"Greto: remedying dynamic graph topology-task discordance via target homophily","authors":"Zhou","year":"2023","venue":"The eleventh international conference on learning representations","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}