Machine Learning Model
Machine learning models aim to create systems that can learn from data and make predictions or decisions without explicit programming. Current research emphasizes improving model accuracy, interpretability, and robustness, focusing on architectures like deep neural networks, decision tree ensembles, and transformer models, as well as exploring decentralized learning and techniques for mitigating biases and vulnerabilities. These advancements are crucial for diverse applications, ranging from optimizing resource management (e.g., smart irrigation) to improving healthcare diagnostics and enhancing the security and trustworthiness of AI systems.
Papers
Monitoring and Adapting ML Models on Mobile Devices
Wei Hao, Zixi Wang, Lauren Hong, Lingxiao Li, Nader Karayanni, Chengzhi Mao, Junfeng Yang, Asaf Cidon
Learn to Unlearn: A Survey on Machine Unlearning
Youyang Qu, Xin Yuan, Ming Ding, Wei Ni, Thierry Rakotoarivelo, David Smith
Comparison of machine learning models applied on anonymized data with different techniques
Judith Sáinz-Pardo Díaz, Álvaro López García
Why not both? Complementing explanations with uncertainty, and the role of self-confidence in Human-AI collaboration
Ioannis Papantonis, Vaishak Belle
Oversampling Higher-Performing Minorities During Machine Learning Model Training Reduces Adverse Impact Slightly but Also Reduces Model Accuracy
Louis Hickman, Jason Kuruzovich, Vincent Ng, Kofi Arhin, Danielle Wilson
Multi-Source to Multi-Target Decentralized Federated Domain Adaptation
Su Wang, Seyyedali Hosseinalipour, Christopher G. Brinton
SQLi Detection with ML: A data-source perspective
Balazs Pejo, Nikolett Kapui
Incorporating Experts' Judgment into Machine Learning Models
Hogun Park, Aly Megahed, Peifeng Yin, Yuya Ong, Pravar Mahajan, Pei Guo