{"type":"ScholarlyArticle","title":"All in One: Multi-task Prompting for Graph Neural Networks (Extended Abstract)","authors":[{"name":"Xiangguo Sun","slug":"xiangguo-sun","given":"Xiangguo","family":"Sun","affiliation":"SEEM and SHIAE , The Chinese University of Hong Kong"},{"name":"Hong Cheng","slug":"hong-cheng","given":"Hong","family":"Cheng","affiliation":"SEEM and SHIAE , The Chinese University of Hong Kong"},{"name":"Jia Li","slug":"jia-li","given":"Jia","family":"Li","affiliation":"The Hong Kong University of Science and Technology (Guangzhou )"},{"name":"Bo Liu","slug":"bo-liu","given":"Bo","family":"Liu","affiliation":"Southeast University"},{"name":"Jihong Guan","slug":"jihong-guan","given":"Jihong","family":"Guan","affiliation":"Tongji University"}],"abstract":"This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award. The paper introduces a novel approach to bridging the gap between pre-trained graph models and the diverse tasks they’re applied to, inspired by the success of prompt learning in NLP. Recognizing the challenge of aligning pre-trained models with varied graph tasks (node level, edge level, and graph level), which can lead to negative transfer and poor performance, we propose a multi-task prompting method for graphs. This method involves unifying graph and language prompt formats, enabling NLP’s prompting strategies to be adapted for graph tasks. By analyzing the task space of graph applications, we reformulate problems to fit graph-level tasks and apply meta-learning to improve prompt initialization for multiple tasks. Experiments show our method’s effectiveness in enhancing model performance across different graph tasks. Beyond the original work, in this extended abstract, we further discuss the graph prompt from a bigger picture and provide some of the latest work toward this area.","doi":"10.24963/ijcai.2024/942","url":"https://ijcai.org/proceedings/2024/942","pdf":"https://ijcai.org/proceedings/2024/0942.pdf","markdown":"https://ijcai.org/proceedings/2024/942.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/942","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":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":942,"pages":{"first":8460,"last":8465},"keywords":["Data Mining: DM: Networks","Data Mining: DM: Mining graphs","Multidisciplinary Topics and Applications: MTA: Web and social networks","Machine Learning: ML: Representation learning"],"videos":[],"references":[{"position":1,"raw":"[Chen et al., 2020] Hongxu Chen, Hongzhi Yin, Xiangguo Sun, Tong Chen, Bogdan Gabrys, and Katarzyna Mu- sial. Multi-level graph convolutional networks for cross- platform anchor link prediction. In Proceedings of the 26th ACM SIGKDD international conference on knowl- edge discovery & data mining, pages 1503-1511, 2020.","title":"Multi-level graph convolutional networks for crossplatform anchor link prediction","authors":"Chen","year":"2020","venue":"Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2024] Xi Chen, Siwei Zhang, Yun Xiong, Xixi Wu, Jiawei Zhang, Xiangguo Sun, Yao Zhang, Yinglong Zhao, and Yulin Kang. Prompt learning on temporal inter- action graphs. arXiv:2402.06326, 2024.","title":"Prompt learning on temporal interaction graphs","authors":"Xi Chen, Siwei Zhang, Yun Xiong, Xixi Wu, Jiawei Zhang, Xiangguo Sun, Yao Zhang, Yinglong Zhao, Yulin Kang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cui et al., 2023] Zhihong Cui, Xiangguo Sun, Hongxu Chen, Li Pan, Lizhen Cui, Shijun Liu, and Guandong Xu. Dynamic recommendation based on graph diffusion and ebbinghaus curve. IEEE Transactions on Computational Social Systems, 2023.","title":"Dynamic recommendation based on graph diffusion and ebbinghaus curve","authors":"Zhihong Cui, Xiangguo Sun, Hongxu Chen, Li Pan, Lizhen Cui, Shijun Liu, Guandong Xu","year":"2023","venue":"IEEE Transactions on Computational Social Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fang et al., 2022] Taoran Fang, Yunchao Zhang, Yang Yang, and Chunping Wang. Prompt tuning for graph neu- ral networks. arXiv preprint arXiv:2209.15240, 2022.","title":"Prompt tuning for graph neural networks","authors":"Fang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2024] Ziqi Gao, Xiangguo Sun, Zijing Liu, Yu Li, Hong Cheng, and Jia Li. Protein multimer struc- ture prediction via PPI-guided prompt learning. In The Twelfth International Conference on Learning Represen- tations (ICLR), 2024.","title":"Protein multimer structure prediction via PPI-guided prompt learning","authors":"Ziqi Gao, Xiangguo Sun, Zijing Liu, Yu Li, Hong Cheng, Jia Li","year":"2024","venue":"The Twelfth International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. Advances in neural information processing sys- tems, 30, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Jin et al., 2020] Wei Jin, Tyler Derr, Haochen Liu, Yiqi Wang, Suhang Wang, Zitao Liu, and Jiliang Tang. Self- supervised learning on graphs: Deep insights and new di- rection. arXiv preprint arXiv:2006.10141, 2020.","title":"Selfsupervised learning on graphs: Deep insights and new direction","authors":"Wei Jin, Tyler Derr, Haochen Liu, Yiqi Wang, Suhang Wang, Zitao Liu, Jiliang Tang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2024a] Yicong Li, Xiangguo Sun, Hongxu Chen, Sixiao Zhang, Yu Yang, and Guandong Xu. Attention is not the only choice: Counterfactual reasoning for path- based explainable recommendation. IEEE Transactions on Knowledge and Data Engineering, 2024.","title":"Attention is not the only choice: Counterfactual reasoning for pathbased explainable recommendation","authors":"Li","year":"2024","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Li et al., 2024b] Yuhan Li, Zhixun Li, Peisong Wang, Jia Li, Xiangguo Sun, Hong Cheng, and Jeffrey Xu Yu. A survey of graph meets large language model: Progress and future directions. arXiv:2311.12399, 2024.","title":"A survey of graph meets large language model: Progress and future directions","authors":"Li","year":"2024","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2024/898"},{"position":10,"raw":"[Liu et al., 2022] Bo Liu, Xiangguo Sun, Qing Meng, Xinyan Yang, Yang Lee, Jiuxin Cao, Junzhou Luo, and Roy Ka-Wei Lee. Nowhere to hide: Online rumor de- tection based on retweeting graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2022.","title":"Nowhere to hide: Online rumor detection based on retweeting graph neural networks","authors":"Bo Liu, Xiangguo Sun, Qing Meng, Xinyan Yang, Yang Lee, Jiuxin Cao, Junzhou Luo, Roy Ka-Wei Lee","year":"2022","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Meng et al., 2023] Qing Meng, Hui Yan, Bo Liu, Xiangguo Sun, Mingrui Hu, and Jiuxin Cao. Recognize news transi- tion from collective behavior for news recommendation. ACM Transactions on Information Systems, 41(4):1-30, 2023.","title":"Recognize news transition from collective behavior for news recommendation","authors":"Qing Meng, Hui Yan, Bo Liu, Xiangguo Sun, Mingrui Hu, Jiuxin Cao","year":"2023","venue":"ACM Transactions on Information Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Piao et al., 2023] Chengzhi Piao, Tingyang Xu, Xiangguo Sun, Yu Rong, Kangfei Zhao, and Hong Cheng. Com- puting graph edit distance via neural graph matching. Proceedings of the VLDB Endowment, 16(8):1817-1829, 2023.","title":"Computing graph edit distance via neural graph matching","authors":"Chengzhi Piao, Tingyang Xu, Xiangguo Sun, Yu Rong, Kangfei Zhao, Hong Cheng","year":"2023","venue":"Proceedings of the VLDB Endowment","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Shchur et al., 2018] Oleksandr Shchur, Maximil- ian Mumme, Aleksandar Bojchevski, and Stephan Günnemann. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868, 2018.","title":"Pitfalls of graph neural network evaluation","authors":"Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, Stephan Günnemann","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shen et al., 2021] Zheyan Shen, Jiashuo Liu, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, and Peng Cui. To- wards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624, 2021.","title":"Towards out-of-distribution generalization: A survey","authors":"Shen","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sun et al., 2021a] Xiangguo Sun, Hongzhi Yin, Bo Liu, Hongxu Chen, Jiuxin Cao, Yingxia Shao, and Nguyen Quoc Viet Hung. Heterogeneous hypergraph embedding for graph classification. In Proceedings of the 14th acm international conference on web search and data mining, pages 725-733, 2021.","title":"Heterogeneous hypergraph embedding for graph classification","authors":"Sun","year":"2021","venue":"Proceedings of the 14th acm international conference on web search and data mining","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Sun et al., 2021b] Xiangguo Sun, Hongzhi Yin, Bo Liu, Hongxu Chen, Qing Meng, Wang Han, and Jiuxin Cao. Multi-level hyperedge distillation for social linking pre- diction on sparsely observed networks. In Proceedings of the Web Conference 2021, pages 2934-2945, 2021.","title":"Multi-level hyperedge distillation for social linking prediction on sparsely observed networks","authors":"Sun","year":"2021","venue":"Proceedings of the Web Conference 2021","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sun et al., 2022a] Mingchen Sun, Kaixiong Zhou, Xin He, Ying Wang, and Xin Wang. GPPT: Graph pre-training and prompt tuning to generalize graph neural networks. In Pro- ceedings of the 28th ACM SIGKDD Conference on Knowl- edge Discovery and Data Mining, pages 1717-1727, 2022.","title":"GPPT: Graph pre-training and prompt tuning to generalize graph neural networks","authors":"Sun","year":"2022","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sun et al., 2022b] Xiangguo Sun, Bo Liu, Liya Ai, Danni Liu, Qing Meng, and Jiuxin Cao. In your eyes: Modality disentangling for personality analysis in short video. IEEE Transactions on Computational Social Systems, 2022.","title":"In your eyes: Modality disentangling for personality analysis in short video","authors":"Sun","year":"2022","venue":"IEEE Transactions on Computational Social Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sun et al., 2022c] Xiangguo Sun, Hongzhi Yin, Bo Liu, Qing Meng, Jiuxin Cao, Alexander Zhou, and Hongxu Chen. Structure learning via meta-hyperedge for dynamic rumor detection. IEEE Transactions on Knowledge and Data Engineering, 2022.","title":"Structure learning via meta-hyperedge for dynamic rumor detection","authors":"Sun","year":"2022","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sun et al., 2023a] Xiangguo Sun, Hong Cheng, Hang Dong, Bo Qiao, Si Qin, and Qingwei Lin. Counter-empirical at- tacking based on adversarial reinforcement learning for time-relevant scoring system. IEEE Transactions on Knowledge and Data Engineering, 2023.","title":"Counter-empirical attacking based on adversarial reinforcement learning for time-relevant scoring system","authors":"Sun","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sun et al., 2023b] Xiangguo Sun, Hong Cheng, Bo Liu, Jia Li, Hongyang Chen, Guandong Xu, and Hongzhi Yin. Self-supervised hypergraph representation learning for so- ciological analysis. IEEE Transactions on Knowledge and Data Engineering, 2023.","title":"Self-supervised hypergraph representation learning for sociological analysis","authors":"Sun","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sun et al., 2023c] Xiangguo Sun, Jiawen Zhang, Xixi Wu, Hong Cheng, Yun Xiong, and Jia Li. Graph prompt learning: A comprehensive survey and beyond. arXiv:2311.16534, 2023.","title":"Graph prompt learning: A comprehensive survey and beyond","authors":"Sun","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Welling and Kipf, 2016] Max Welling and Thomas N Kipf. Semi-supervised classification with graph convolutional networks. In J. International Conference on Learning Rep- resentations (ICLR 2017), 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"Kipf Welling, Max Welling, Thomas N Kipf","year":"2016","venue":"J. International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xia et al., 2022] Jun Xia, Lirong Wu, Jintao Chen, Bozhen Hu, and Stan Z Li. Simgrace: A simple framework for graph contrastive learning without data augmentation. In Proceedings of the ACM Web Conference 2022, pages 1070-1079, 2022.","title":"Simgrace: A simple framework for graph contrastive learning without data augmentation","authors":"Jun Xia, Lirong Wu, Jintao Chen, Bozhen Hu, Stan Z Li","year":"2022","venue":"Proceedings of the ACM Web Conference 2022","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2023] Haoran Yang, Hongxu Chen, Sixiao Zhang, Xiangguo Sun, Qian Li, Xiangyu Zhao, and Guan- dong Xu. Generating counterfactual hard negative samples for graph contrastive learning. In Proceedings of the ACM Web Conference 2023, pages 621-629, 2023.","title":"Generating counterfactual hard negative samples for graph contrastive learning","authors":"Haoran Yang, Hongxu Chen, Sixiao Zhang, Xiangguo Sun, Qian Li, Xiangyu Zhao, Guandong Xu","year":"2023","venue":"Proceedings of the ACM Web Conference 2023","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[You et al., 2020] Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. Graph con- trastive learning with augmentations. Advances in Neural Information Processing Systems, 33:5812-5823, 2020.","title":"Graph contrastive learning with augmentations","authors":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2022a] Sixiao Zhang, Hongxu Chen, Xiang- guo Sun, Yicong Li, and Guandong Xu. Unsuper- vised graph poisoning attack via contrastive loss back- propagation. In Proceedings of the ACM Web Conference 2022, pages 1322-1330, 2022.","title":"Unsupervised graph poisoning attack via contrastive loss backpropagation","authors":"Zhang","year":"2022","venue":"Proceedings of the ACM Web Conference 2022","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2022b] Sixiao Zhang, Hongxu Chen, Haoran Yang, Xiangguo Sun, Philip S Yu, and Guandong Xu. Graph masked autoencoders with transformers. arXiv preprint arXiv:2202.08391, 2022.","title":"Graph masked autoencoders with transformers","authors":"Zhang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhao et al., 2024] Haihong Zhao, Aochuan Chen, Xiang- guo Sun, Hong Cheng, and Jia Li. All in one and one for all: A simple yet effective method towards cross-domain graph pretraining. 2024.","title":"All in one and one for all: A simple yet effective method towards cross-domain graph pretraining","authors":"Haihong Zhao, Aochuan Chen, Xiangguo Sun, Hong Cheng, Jia Li","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}