Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Adaptive Negative Scheduling for Graph Contrastive Learning

About

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.

Adnan Ali, Jinlong Li, Syed Muhammad Israr, Ali Kashif Bashir• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationPubmed
Accuracy87.81
627
Node ClassificationCora
Accuracy88.05
583
Node ClassificationActor
Accuracy30.78
556
Node ClassificationAmazon Photo
Accuracy95.11
313
Node ClassificationAmazon Computers
Accuracy91.76
167
Node ClassificationCiteseer
Accuracy76.5
51
Node ClassificationDBLP
Accuracy86.28
31
Node ClassificationCoauthor CS
Accuracy94.3
15
Showing 8 of 8 rows

Other info

Follow for update