Temporal networks are effective in capturing the evolving interactions of networks over time, such as social networks and e-commerce networks. In recent years, researchers have primarily concentrated on developing specific model architectures for Temporal Graph Neural Networks (TGNNs) in order to improve the representation quality of temporal nodes and edges. However, limited attention has been given to the quality of negative samples during the training of TGNNs. When compared with static networks, temporal networks present two specific challenges for negative sampling: positive sparsity and positive shift. Positive sparsity refers to the presence of a single positive sample amidst numerous negative samples at each timestamp, while positive shift relates to the variations in positive samples across different timestamps. To robustly address these challenges in training TGNNs, we introduce Curriculum Negative Mining (CurNM), a model-aware curriculum learning framework that adaptively adjusts the difficulty of negative samples. Within this framework, we first establish a dynamically updated negative pool that balances random, historical, and hard negatives to address the challenges posed by positive sparsity. Secondly, we implement a temporal-aware negative selection module that focuses on learning from the disentangled factors of recently active edges, thus accurately capturing shifting preferences. Extensive experiments on 12 datasets and 3 TGNNs demonstrate that our method outperforms baseline methods by a significant margin. Additionally, thorough ablation studies and parameter sensitivity experiments verify the usefulness and robustness of our approach. Our code is available at https://github.com/zziyue83/CurNM.

翻译：时序网络能够有效捕捉网络随时间的演化交互，例如社交网络和电子商务网络。近年来，研究者主要致力于为时序图神经网络（TGNNs）开发特定的模型架构，以提高时序节点和边的表示质量。然而，在TGNNs训练过程中，负样本的质量问题受到的关注有限。与静态网络相比，时序网络在负采样方面面临两个特定挑战：正样本稀疏性和正样本偏移。正样本稀疏性指每个时间戳下大量负样本中仅存在单个正样本，而正样本偏移则涉及不同时间戳间正样本的变化。为稳健应对TGNNs训练中的这些挑战，我们提出课程负样本挖掘（CurNM），这是一种模型感知的课程学习框架，能够自适应调整负样本的难度。在该框架中，我们首先建立动态更新的负样本池，通过平衡随机负样本、历史负样本和困难负样本来应对正样本稀疏性带来的挑战。其次，我们实现了一个时序感知的负样本选择模块，该模块专注于从近期活跃边的解耦因子中学习，从而准确捕捉偏移偏好。在12个数据集和3种TGNNs上的大量实验表明，我们的方法显著优于基线方法。此外，详尽的消融研究和参数敏感性实验验证了我们方法的实用性和鲁棒性。代码已发布于https://github.com/zziyue83/CurNM。