Abstract:Graph contrastive learning (GCL) has become a central paradigm for self-supervised representation learning in computational intelligence, with applications spanning recommendation, anomaly detection, and personalization. A key limitation of existing methods is their reliance on static negative sampling, which fails to account for the dynamic informativeness and computational cost of negatives during training. We propose AdNGCL, an adaptive negative scheduling framework with a hardness-aware scheduler (HANS) that formulates negative selection as a loss-gated, budget-constrained process across hard, intermediate, and easy strata. The scheduler dynamically adjusts step sizes based on contrastive loss trends under both global and per-category budgets, while periodically refreshing samples to maintain diversity without exceeding compute constraints. Experiments on nine benchmark graph datasets demonstrate that AdNGCL consistently advances state-of-the-art performance, achieving the best accuracy on seven datasets and second-best on the remaining two, while offering explicit control over computational cost. These results highlight the value of budget-aware, loss-sensitive scheduling as a general strategy for improving the robustness and efficiency of representation learning in emerging computational intelligence applications.
| Comments: | 14 pages, 5 figures, 9 benchmark datasets, code available at GitHub |
| Subjects: | Machine Learning (cs.LG) |
| MSC classes: | 68T07, 68T09 |
| ACM classes: | I.2.6; I.5.1; H.2.8 |
| Cite as: | arXiv:2605.03076 [cs.LG] |
| (or arXiv:2605.03076v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.03076 arXiv-issued DOI via DataCite (pending registration) |
From: Adnan Ali [view email]
[v1]
Mon, 4 May 2026 18:45:51 UTC (684 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。