{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:42Z","timestamp":1786120842566,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0115903"],"award-info":[{"award-number":["2022ZD0115903"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3816448","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"13379-13382","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Graph Distribution Shifts: LLMs, Adaptation, and Generalization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3544-5563","authenticated-orcid":false,"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0608-0111","authenticated-orcid":false,"given":"Haibo","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Hong Chen Yudong Chen Xin Wang Ruobin Xie Rui Wang Feng Xia and Wenwu Zhu. 2021. Curriculum Disentangled Recommendation with Noisy Multi-feedback. In NeurIPS."},{"key":"e_1_3_2_1_2_1","volume-title":"Adaptive Mixture of Disentangled Experts for Dynamic Graph Out-of-Distribution Generalization. In The Fourteenth International Conference on Learning Representations.","author":"Chen Haibo","unstructured":"Haibo Chen, Xin Wang, Guanheng Chen, Yuan Meng, Haoyang Li, Yang Yao, Zeyang Zhang, Zhiqiang Zhang, Jun Zhou, Ling Feng, et al., [n.d.]. Adaptive Mixture of Disentangled Experts for Dynamic Graph Out-of-Distribution Generalization. In The Fourteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","unstructured":"Hong Chen Xin Wang Chaoyu Guan Yue Liu and Wenwu Zhu. 2022a. Auxiliary Learning with Joint Task and Data Scheduling. In ICML."},{"key":"e_1_3_2_1_4_1","volume-title":"Chaoyu Guan, and Wenwu Zhu.","author":"Chen Hong","year":"2022","unstructured":"Hong Chen, Xin Wang, Yue Liu, yuwei zhou, Chaoyu Guan, and Wenwu Zhu. 2022b. Module-Aware Optimization for Auxiliary Learning. NeurIPS (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Autogfm: Automated graph foundation model with adaptive architecture customization. In ICML.","author":"Chen Haibo","year":"2025","unstructured":"Haibo Chen, Xin Wang, Zeyang Zhang, Haoyang Li, Ling Feng, and Wenwu Zhu. 2025. Autogfm: Automated graph foundation model with adaptive architecture customization. In ICML."},{"key":"e_1_3_2_1_6_1","unstructured":"Haoyang Li Xin Wang Zeyang Zhang Haibo Chen Ziwei Zhang and Wenwu Zhu. 2024. Disentangled graph self-supervised learning for out-of-distribution generalization. In ICML."},{"key":"e_1_3_2_1_7_1","unstructured":"Haoyang Li Xin Wang Zeyang Zhang Zongyuan Wu Linxin Xiao Yaofei Wu and Wenwu Zhu. 2025c. Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum. (2025)."},{"key":"e_1_3_2_1_8_1","unstructured":"Haoyang Li Xin Wang Ziwei Zhang and Wenwu Zhu. 2021. Disentangled Contrastive Learning on Graphs. In NeurIPS."},{"key":"e_1_3_2_1_9_1","volume-title":"OOD-GNN: Out-of-distribution generalized graph neural network. TKDE","author":"Li Haoyang","year":"2022","unstructured":"Haoyang Li, Xin Wang, Ziwei Zhang, and Wenwu Zhu. 2022a. OOD-GNN: Out-of-distribution generalized graph neural network. TKDE (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Out-of-distribution generalization on graphs: A survey. TPAMI","author":"Li Haoyang","year":"2025","unstructured":"Haoyang Li, Xin Wang, Ziwei Zhang, and Wenwu Zhu. 2025a. Out-of-distribution generalization on graphs: A survey. TPAMI (2025)."},{"key":"e_1_3_2_1_11_1","unstructured":"Haoyang Li Xin Wang Xueling Zhu Weigao Wen and Wenwu Zhu. 2025d. Disentangling invariant subgraph via variance contrastive estimation under distribution shifts. In ICML."},{"key":"e_1_3_2_1_12_1","volume-title":"Disentangled Graph Contrastive Learning With Independence Promotion. TKDE","author":"Li Haoyang","year":"2022","unstructured":"Haoyang Li, Ziwei Zhang, Xin Wang, and Wenwu Zhu. 2022b. Disentangled Graph Contrastive Learning With Independence Promotion. TKDE (2022)."},{"key":"e_1_3_2_1_13_1","unstructured":"Haoyang Li Ziwei Zhang Xin Wang and Wenwu Zhu. 2022c. Learning Invariant Graph Representations Under Distribution Shifts. In NeurIPS."},{"key":"e_1_3_2_1_14_1","volume-title":"Causal-aware graph neural architecture search under distribution shifts. KDD","author":"Li Peiwen","year":"2025","unstructured":"Peiwen Li, Xin Wang, Zeyang Zhang, Yijian Qin, Ziwei Zhang, Jialong Wang, Yang Li, and Wenwu Zhu. 2025b. Causal-aware graph neural architecture search under distribution shifts. KDD (2025)."},{"key":"e_1_3_2_1_15_1","unstructured":"Jianxin Ma Peng Cui Kun Kuang Xin Wang and Wenwu Zhu. 2019a. Disentangled graph convolutional networks. In ICML."},{"key":"e_1_3_2_1_16_1","volume-title":"Learning disentangled representations for recommendation. NeurIPS","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, and Wenwu Zhu. 2019b. Learning disentangled representations for recommendation. NeurIPS (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403091"},{"key":"e_1_3_2_1_18_1","volume-title":"Multi-task graph neural architecture search with task-aware collaboration and curriculum. NeurIPS","author":"Qin Yijian","year":"2024","unstructured":"Yijian Qin, Xin Wang, Ziwei Zhang, Hong Chen, and Wenwu Zhu. 2024. Multi-task graph neural architecture search with task-aware collaboration and curriculum. NeurIPS (2024)."},{"key":"e_1_3_2_1_19_1","unstructured":"Yijian Qin Xin Wang Ziwei Zhang Pengtao Xie and Wenwu Zhu. 2022a. Graph Neural Architecture Search Under Distribution Shifts. In ICML."},{"key":"e_1_3_2_1_20_1","unstructured":"Yijian Qin Xin Wang Zeyang Zhang and Wenwu Zhu. 2021. Graph differentiable architecture search with structure learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_21_1","volume-title":"Disentangled representation learning with large language models for text-attributed graphs. arXiv preprint arXiv:2310.18152","author":"Qin Yijian","year":"2023","unstructured":"Yijian Qin, Xin Wang, Ziwei Zhang, and Wenwu Zhu. 2023. Disentangled representation learning with large language models for text-attributed graphs. arXiv preprint arXiv:2310.18152 (2023)."},{"key":"e_1_3_2_1_22_1","unstructured":"Yijian Qin Ziwei Zhang Xin Wang Zeyang Zhang and Wenwu Zhu. 2022b. NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_23_1","volume-title":"Disentangled Representation Learning for Recommendation. TPAMI","author":"Wang Xin","year":"2022","unstructured":"Xin Wang, Hong Chen, Yuwei Zhou, Jianxin Ma, and Wenwu Zhu. 2022. Disentangled Representation Learning for Recommendation. TPAMI (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Multimodal Disentangled Representation for Recommendation. In 2021 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1-6.","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Hong Chen, and Wenwu Zhu. 2021a. Multimodal Disentangled Representation for Recommendation. In 2021 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1-6."},{"key":"e_1_3_2_1_25_1","unstructured":"Xin Wang Shuyi Fan Kun Kuang and Wenwu Zhu. 2021b. Explainable Automated Graph Representation Learning with Hyperparameter Importance. In ICML."},{"key":"e_1_3_2_1_26_1","volume-title":"Uncertainty-aware Disentangled Dynamic Graph Attention Network for Out-of-Distribution Generalization. TPAMI","author":"Wang Xin","year":"2025","unstructured":"Xin Wang, Haoyang Li, Zeyang Zhang, Haibo Chen, Tong Xiao, Kehan Li, and Wenwu Zhu. 2025b. Uncertainty-aware Disentangled Dynamic Graph Attention Network for Out-of-Distribution Generalization. TPAMI (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models. arXiv preprint arXiv:2504.20020","author":"Wang Xin","year":"2025","unstructured":"Xin Wang, Haoyang Li, Zeyang Zhang, Haibo Chen, and Wenwu Zhu. 2025a. Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models. arXiv preprint arXiv:2504.20020 (2025)."},{"key":"e_1_3_2_1_28_1","volume-title":"Towards Multi-modal Graph Large Language Model. arXiv preprint arXiv:2506.09738","author":"Wang Xin","year":"2025","unstructured":"Xin Wang, Zeyang Zhang, Linxin Xiao, Haibo Chen, Chendi Ge, and Wenwu Zhu. 2025c. Towards Multi-modal Graph Large Language Model. arXiv preprint arXiv:2506.09738 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3774904.3792464"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Yang Yao Xin Wang Yijian Qin Ziwei Zhang Wenwu Zhu and Hong Mei. 2024. Data-Augmented Curriculum Graph Neural Architecture Search Under Distribution Shifts. (2024).","DOI":"10.1609\/aaai.v38i15.29580"},{"key":"e_1_3_2_1_31_1","volume-title":"NeurIPS Workshop.","author":"Zhang Ziwei","year":"2023","unstructured":"Ziwei Zhang, Haoyang Li, Zeyang Zhang, Yijian Qin, Xin Wang, and Wenwu Zhu. 2023a. Graph meets llms: Towards large graph models. In NeurIPS Workshop."},{"key":"e_1_3_2_1_32_1","volume-title":"Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation. TOIS","author":"Zhang Zeyang","year":"2024","unstructured":"Zeyang Zhang, Xin Wang, Haibo Chen, Haoyang Li, and Wenwu Zhu. 2024a. Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation. TOIS (2024)."},{"key":"e_1_3_2_1_33_1","unstructured":"Zizhao Zhang Xin Wang Chaoyu Guan Ziwei Zhang Haoyang Li and Wenwu Zhu. 2023b. AutoGT: Automated Graph Transformer Architecture Search. In ICLR."},{"key":"e_1_3_2_1_34_1","unstructured":"Zeyang Zhang Xin Wang Yijian Qin Hong Chen Ziwei Zhang Xu Chu and Wenwu Zhu. 2024b. Disentangled continual graph neural architecture search with invariant modular supernet. In ICML."},{"key":"e_1_3_2_1_35_1","volume-title":"LLM4DyG: Can Large Language Models Solve Problems on Dynamic Graphs? arXiv preprint arXiv:2310.17110","author":"Zhang Zeyang","year":"2023","unstructured":"Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, Yijian Qin, Simin Wu, and Wenwu Zhu. 2023d. LLM4DyG: Can Large Language Models Solve Problems on Dynamic Graphs? arXiv preprint arXiv:2310.17110 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Zeyang Zhang Xin Wang Ziwei Zhang Haoyang Li Zhou Qin and Wenwu Zhu. 2022a. Dynamic graph neural networks under spatio-temporal distribution shift. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/068431-0440"},{"key":"e_1_3_2_1_37_1","volume-title":"Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion. arXiv preprint arXiv:2311.14255","author":"Zhang Zeyang","year":"2023","unstructured":"Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, and Wenwu Zhu. 2023c. Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion. arXiv preprint arXiv:2311.14255 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Zeyang Zhang Xin Wang Ziwei Zhang Zhou Qin Weigao Wen Hui Xue Haoyang Li and Wenwu Zhu. 2023 e. Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/075280-0290"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Zeyang Zhang Xin Wang Ziwei Zhang Guangyao Shen Shiqi Shen and Wenwu Zhu. 2023 f. Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/075280-3198"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Zeyang Zhang Ziwei Zhang Xin Wang Yijian Qin Zhou Qin and Wenwu Zhu. 2023 g. Dynamic Heterogeneous Graph Attention Neural Architecture Search. In AAAI.","DOI":"10.1609\/aaai.v37i9.26338"},{"key":"e_1_3_2_1_41_1","volume-title":"Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum. AAAI","author":"Zhang Zeyang","year":"2022","unstructured":"Zeyang Zhang, Ziwei Zhang, Xin Wang, and Wenwu Zhu. 2022b. Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum. AAAI (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Wenwu Zhu Xin Wang and Wenpeng Zhang. 2019. AutoML and Meta-learning for Multimedia. In MM.","DOI":"10.1145\/3343031.3350541"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:23:19Z","timestamp":1786065799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3816448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":42,"alternative-id":["10.1145\/3770855.3816448","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3816448","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}