{"type":"ScholarlyArticle","title":"Mitigating Dynamic Graph Distribution Shifts via Spectral Augmentation","authors":[{"name":"Qianyu Song","slug":"qianyu-song","given":"Qianyu","family":"Song","affiliation":""},{"name":"Chao Li","slug":"chao-li","given":"Chao","family":"Li","affiliation":""},{"name":"Zhongying Zhao","slug":"zhongying-zhao","given":"Zhongying","family":"Zhao","affiliation":""},{"name":"Hua Duan","slug":"hua-duan","given":"Hua","family":"Duan","affiliation":""},{"name":"Qingtian Zeng","slug":"qingtian-zeng","given":"Qingtian","family":"Zeng","affiliation":""}],"abstract":"Dynamic Graph Neural Networks (DyGNNs) are facing challenges with distribution shifts between training and test data that are similar but not identical. Existing DyGNNs for out-of-distribution scenarios primarily focus on discovering invariant patterns in the spatial domain, overlooking its impact on the structural properties in the spectral domain. In this paper, we propose a spectral-based graph augmentation framework designed to investigate and improve generalization behavior in dynamic graphs under distribution shifts. Specifically, we augment the input graph spectra into a mixture of shift components by maximizing the variance of spectral distance and propose an efficient approximation to reduce the computational cost brought by eigen-decomposition. Building on this, we develop a multi-encoder architecture in which each encoder targets a specific spectral shift component to generate referential representations. Our method adopts a new learning objective to encourage the model to rely on robust spectral properties for better generalization under distribution shifts. Extensive experiments on both real-world and synthetic datasets demonstrate that our proposed method significantly outperforms state-of-the-art approaches in node classification and link prediction tasks. Source codes are available at https://github.com/SSQiana/DSPA.","doi":"10.24963/ijcai.2026/335","url":"https://ijcai.org/proceedings/2026/335","pdf":"https://ijcai.org/proceedings/2026/0335.pdf","markdown":"https://ijcai.org/proceedings/2026/335.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/335","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Data Mining","track":"Main Track","number":335,"pages":{"first":3015,"last":3023},"keywords":["Data Mining: Mining spatial and/or temporal data","Data Mining: Mining graphs"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}