AdaDGL: Adaptive Distributional Negative Sampling for Robust Dynamic Graph Learning

Dynamic graph models are commonly trained and evaluated with sampled negative edges, making their performance inherently dependent on the underlying negative sampling distribution. However, existing methods typically rely on a fixed distribution, such as random, historical, or inductive sampling. This creates a negative sampling distribution shift: models trained under one distribution can degrade substantially when evaluated under another, while evaluation with easy random negatives can overestimate model performance. We propose $\mathbf{AdaDGL}$, an adaptive distributional negative sampling framework for robust dynamic graph learning under such shifts. During training, AdaDGL samples similarity-aware negatives from broadly covered candidates to balance hardness and coverage. At inference, it constructs hard negatives for reliable evaluation when the target distribution is unknown, and efficiently adapts the prediction head when the target distribution is known. Experiments across multiple datasets and backbones show consistent gains under different negative sampling distributions, with up to $7.41\%$ average precision improvement and $2.98\times$ training acceleration when supporting multiple target distributions.