{"type":"ScholarlyArticle","title":"GraphSculptor: Sculpting Pre-training Core Sets for Graph Self-supervised Learning","authors":[{"name":"Chuang Liu","slug":"chuang-liu","given":"Chuang","family":"Liu","affiliation":""},{"name":"Zelin Yao","slug":"zelin-yao","given":"Zelin","family":"Yao","affiliation":""},{"name":"Xueqi Ma","slug":"xueqi-ma","given":"Xueqi","family":"Ma","affiliation":""},{"name":"Luzhi Wang","slug":"luzhi-wang","given":"Luzhi","family":"Wang","affiliation":""},{"name":"Mukun Chen","slug":"mukun-chen","given":"Mukun","family":"Chen","affiliation":""},{"name":"Pinghua Xu","slug":"pinghua-xu","given":"Pinghua","family":"Xu","affiliation":""},{"name":"Wenbin Hu","slug":"wenbin-hu","given":"Wenbin","family":"Hu","affiliation":""}],"abstract":"Graph self-supervised learning (SSL) typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets contain substantial redundancy—our analysis reveals that uniformly subsampling 50% of graphs retains over 96% of downstream performance. To exploit this redundancy, we introduce GraphSculptor for pre-training coreset construction. Unlike methods dependent on additional training-time signals or limited solely to topological statistics, GraphSculptor provides a label-free solution that constructs coresets via two complementary perspectives: intrinsic structure and contextual semantics. Concretely, structural diversity is quantified using intrinsic graph statistics, yielding a structural feature vector for each graph, while semantic diversity is captured by utilizing a pre-trained language model to encode descriptions generated via graph-to-text. GraphSculptor integrates these signals into a unified metric space and performs cluster-aware selection to preserve joint structural--semantic diversity. We further derive a theoretical bound on the loss gap between coreset and full-data pre-training, offering theoretical motivation for our selection formulation. Extensive experiments demonstrate that GraphSculptor effectively \"sculpts\" the dataset: a 10% coreset achieves 99.6% of full-data performance while reducing pre-training time by nearly 90%, offering a scalable solution for data-efficient graph pre-training.","doi":"10.24963/ijcai.2026/316","url":"https://ijcai.org/proceedings/2026/316","pdf":"https://ijcai.org/proceedings/2026/0316.pdf","markdown":"https://ijcai.org/proceedings/2026/316.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/316","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":316,"pages":{"first":2843,"last":2851},"keywords":["Data Mining: Mining graphs"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}