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.

You might think that it would be impossible for people to value a piece of hardware over human life, yet new research from Radboud University suggests that such circumstances may exist. Bizarrely, one of these circumstances might involve a perception that robots feel pain. "It is known that military personnel may mourn a robot that is used to clear mines in the army. Funerals are organized for them. We wanted to investigate how far this empathy for robots extends, and what moral principles influence this behavior towards robots. Little research has been done in this area as of yet, " the authors explain.

The Bank of England and the World Bank Chief are only two voices, in a growing network, that are concerned by the rise of AI and the loss of jobs. This continuing question is not surprising, according to John Gikopoulos, Global Head for automation and artificial intelligence AI at Infosys Consulting: fear and uncertainty make for good headlines. "The short answer is that no-one can accurately predict what tomorrow's job market will look like, any more than the first observers of Stephenson's Rocket could imagine the huge numbers of people employed by the global, multi-billion dollar railway industry of today," explains Gikopoulos. "We prefer to take our cue from other industrial revolutions to which we've somehow managed to adapt. And the most likely outcome of AI will be a positive shift in the nature of the work we do."