Zobrazeno 1 - 10
of 1 331
pro vyhledávání: '"Zhang Haipeng"'
Large language models (LLMs) have demonstrated impressive versatility across numerous tasks, yet their generalization capabilities remain poorly understood. To investigate these behaviors, arithmetic tasks serve as important venues. In previous studi
Externí odkaz:
http://arxiv.org/abs/2407.17963
Current directed graph embedding methods build upon undirected techniques but often inadequately capture directed edge information, leading to challenges such as: (1) Suboptimal representations for nodes with low in/out-degrees, due to the insufficie
Externí odkaz:
http://arxiv.org/abs/2406.05391
Position bias, i.e., users' preference of an item is affected by its placing position, is well studied in the recommender system literature. However, most existing methods ignore the widely coupled ranking bias, which is also related to the placing p
Externí odkaz:
http://arxiv.org/abs/2405.18971
The life trajectories of notable people have been studied to pinpoint the times and places of significant events such as birth, death, education, marriage, competition, work, speeches, scientific discoveries, artistic achievements, and battles. Under
Externí odkaz:
http://arxiv.org/abs/2406.00032
Autor:
Du, Xiaocong, Zhang, Haipeng
Achieving gender equality is a pivotal factor in realizing the UN's Global Goals for Sustainable Development. Gender bias studies work towards this and rely on name-based gender inference tools to assign individual gender labels when gender informati
Externí odkaz:
http://arxiv.org/abs/2405.06221
Autor:
Li, Ran, Zhang, Haipeng, Sun, Mingyang, Teng, Fei, Wan, Can, Pineda, Salvador, Kariniotakis, Georges
Better forecasts may not lead to better decision-making. To address this challenge, decision-oriented learning (DOL) has been proposed as a new branch of machine learning that replaces traditional statistical loss with a decision loss to form an end-
Externí odkaz:
http://arxiv.org/abs/2401.03680
Forecast-then-optimize is a widely-used framework for decision-making problems in power systems. Traditionally, statistical losses have been employed to train forecasting models, but recent research demonstrated that improved decision utility in down
Externí odkaz:
http://arxiv.org/abs/2312.13501
Publikováno v:
Proceedings of the 31st ACM International Conference on Information and Knowledge Management (2022) 4727-4731
Uplift modeling is widely used in performance marketing to estimate effects of promotion campaigns (e.g., increase of customer retention rate). Since it is impossible to observe outcomes of a recipient in treatment (e.g., receiving a certain promotio
Externí odkaz:
http://arxiv.org/abs/2312.09639