Adaptive Negative Scheduling for Graph Contrastive Learning

TL;DR

This paper introduces AdNGCL, an adaptive negative sampling framework for graph contrastive learning that dynamically balances informativeness and computational cost, leading to improved performance and efficiency.

Contribution

It proposes a novel hardness-aware scheduler that adaptively manages negative samples based on loss trends and budgets, enhancing GCL robustness and efficiency.

Findings

Achieves state-of-the-art accuracy on seven out of nine benchmark datasets.

Effectively balances performance and computational cost through budget-aware scheduling.

Demonstrates general applicability of adaptive negative sampling in graph representation learning.

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.