NAUT
发表于 2025-3-28 15:58:19
Causal Inference on Graphsct fields, such as social network analysis, bioinformatics, crime forecasting, economics, and recommender systems. Different from most traditional causal inference studies, which focus on independent and identically distributed (i.i.d.) data, causal inference on graphs has recently attracted increas
DEBT
发表于 2025-3-28 19:28:31
http://reply.papertrans.cn/63/6206/620589/620589_42.png
安抚
发表于 2025-3-29 00:24:15
Fair Machine Learning Through the Lens of Causality09) Causality. Cambridge University Press), this framework defines fairness in the categories of direct/indirect discrimination, system/group/individual-level discrimination, and their derivatives, e.g., indirect individual-level discrimination. The framework can unify various causal fairness notion
危险
发表于 2025-3-29 05:31:58
Causal Explainable AIance measurements such as accuracy. However, as machine learning techniques have been applied to fields that are highly sensitive to risk, such as healthcare, law enforcement, and finance, the trustworthiness of models, especially their explainability, has become an increasingly important concern. F
Cubicle
发表于 2025-3-29 08:19:03
Causal Domain Generalization. assumption, independent and identically distributed assumption, states that the training and test data are sampled from the same distribution. On the other hand, real-world scenarios are more dynamic, with training and test data not always coming from the same distribution. In such cases, models b
一再困扰
发表于 2025-3-29 12:14:32
Causal Inference and Natural Language Processingl questions: (1) how can NLP aid in causal inference when working with textual data, and (2) how can causal inference theory enhance the robustness and interpretability of NLP models? We present the latest developments and challenges in each area. Firstly, we discuss the difficulties associated with
引导
发表于 2025-3-29 19:19:41
http://reply.papertrans.cn/63/6206/620589/620589_47.png
注意到
发表于 2025-3-29 23:31:32
http://reply.papertrans.cn/63/6206/620589/620589_48.png