Machine Learning (ML) are used in an increasing number of applications as they continue to deliver state-of-the-art performance across many areas including computer vision natural language processing (NLP), robotics, autonomous driving, and healthcare. While rapid progress in all aspects of ML dev...
A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacy. [paper] Adversarial Machine Learning: A Systematic Survey of Backdoor Attack, Weight Attack and Adversarial Example. [paper] Out-of-Distribution Generalization Simple and Fast Group Robustness by Automatic...
Doshi-Velez F, Kim B (2017) Towards a rigorous science of interpretable machine learning. arXiv:1702.08608 Draws T, Rieger A, Inel O et al (2021) A checklist to combat cognitive biases in crowdsourcing. In: Proceedings of the AAAI conference on human computation and crowdsourcing (HCOMP), ...
Strategic machine learning 通过对“用户对模型的回应”做建模和预测,并将此带入训练步骤中。还有根据长期使用修改训练目标的方法。这些方法的主要挑战是理解和预测动态的用户和模型的交互。 还有一些研究专注于开发debiasing techniques(去偏差技术)来缓解feedback loop effect,有研究发现以最小化用户反馈数据的损失训练...
machine-learning awesome research paper academic survey human-in-the-loop interpretability human-in-the-loop-machine-learning explanations interpretable-ml explainable-ml xai explainability counterfactual-explanations interpretable-models recourse trustworthy-machine-learning human-ai-interaction Updated Jun 25, ...
Patel R, Acharya S (2023) A fuzzy logic based trust evaluation model for IoT. In: International conference on machine learning, IoT and big data. Springer, Berlin, pp 147–156 Paul T, Famulari A, Strufe T (2014) A survey on decentralized online social networks. Comput Netw 75:437–452...
Chapter 1. Privacy If you’ve been paying any attention to the media, then you’re at least somewhat aware of the damage that can follow when a company’s customer data or … - Selection from Practicing Trustworthy Machine Learning [Book]
1”Workday Global Survey: 98% of CEOs Say Their Organizations Would Benefit from Implementing AI, But Trust Remains a Concern.” Workday. 14 September 2023. 2“Adverse impacts of revealing the presence of “Artificial Intelligence (AI)” technology in product and service descriptions on purchase...
The security of machine learning in an adversarial setting: A survey Xianmin WangJing LiXiaohui KuangYuan Tan Journal of Parallel and Distributed Computing Aug 2019 Machine learning (ML) methods have demonstrated impressive performance in many application fields such as autopilot, facial recognition, and...
This revolutionary move in RS is the adoption of machine learning algorithms from the field of artificial intelligence to produce the personalized recommendation of products or services. This literature presents an exhaustive survey on RS to emphasizes its taxonomy pertaining to diverse perspectives. This...