Federated learning (aka collaborative learning) is a machine learning technique that trains an algorithm across multiple decentralized edge devices or servers holding local data samples, without exchanging their data samples.
- Jie Xu, Zhenxing Xu, Peter Walke, Fei Wang. Federated Patient Hashing. The Thirty-Fourth AAAI Con-ference on Artificial Intelligence (AAAI-20), 2020.
- Jie Xu, Fei Wang. Federated Learning for Healthcare Informatics. arXiv preprint arXiv:1911.06270, 2019.
Similarity learning is an area of supervised machine learning in artificial intelligence. It is closely related to regression and classification, but the goal is to learn from a similarity function that measures how similar or related two objects are.
- Lei Luo, Jie Xu, Cheng Deng, Heng Huang. Robust Metric Learning on Grassmann Manifolds with Generalization Guarantees. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 2019.
- Lei Luo, Jie Xu, Cheng Deng, Heng Huang. Orthogonality-Promoting Dictionary Learning via Bayesian Inference. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 2019.
- Jie Xu, Lei Luo, Cheng Deng, Heng Huang. Bilevel Distance Metric Learning for Robust Image Recognition. Thirty-second Conference on Neural Information Processing Systems (NIPS), 2018.
- Jie Xu, Lei Luo, Cheng Deng, Heng Huang. New Robust Metric Learning Model Using Maximum Correntropy Criterion. SIGKDD: The community for data mining, data science and analytics (SIGKDD), 2018, 2555-2564, London, United Kingdom, 2018.8.19-8.23.
- Jie Xu, Lei Luo, Cheng Deng, Heng Huang. Multi-Level Metric Learning via Smoothed Wasserstein Distance. International Joint Conference on Artificial Intelligence (IJCAI), 2018, Stockholm, Sweden, 2018.7.13-7.19.
- Jie Xu, Cheng Deng, Xinbo Gao, Dinggang Shen, Heng Huang. Predicting Alzheimer’s Disease Cognitive Assessment via Robust Low-Rank Structured Sparse Model. 26th International Joint Conference on Artificial Intelligence (IJCAI), 2017, 3880-3886, Melbourne, Australia, 2017.8.17-8.25.
- Jie Xu, Xianglong Liu, Zhouyuan Huo, Cheng Deng, Feiping Nie, Heng Huang*. Multi-Class Support Vector Machine via Maximizing Multi-Class Margins. 26th International Joint Conference on Artificial Intelligence (IJCAI), 2017, 3154-3160, Melbourne, Australia, 2017.8.17-8.25.
Super-resolution imaging (SR) is a class of techniques that enhance (increase) the resolution of an imaging system. In optical SR the diffraction limit of systems is transcended, while in geometrical SR the resolution of digital imaging sensors is enhanced.
- Cheng Deng, Jie Xu, Kaibing Zhang, Dacheng Tao, Xinbo Gao, Xuelong Li. Similarity Constraints Based Structured Output Regression Machine: An Approach to Image Super-Resolution. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(12): 2472-2485. (JCR-I, IF = 6.108)
- Xinxia Fan, Yanhua Yang, Cheng Deng, Jie Xu, Xinbo Gao. Compressed Multi-scale Feature Fusion Network for Single Image Super-Resolution. Signal Processing, 2017. (JCR-II, IF = 3.110)
- Jie Xu, Cheng Deng*, Xinbo Gao, Dacheng Tao, Xuelong Li. Image super-resolution using multi-layer support vector regression. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, 5799-5803, Florence, Italy, 2014.5.4-5.9.
- Jie Xu, Cheng Deng, Xianglong Liu, Jie Li. Image Super-resolution Based on Sparse Representation With Joint Constraints. International Conference on Internet Multimedia Computing and Service (ICIMCS), 2014, 381-385, Xiamen, China, 2014.7.10-7.12.
- Songhang Ye, Cheng Deng, Jie Xu, Xinbo Gao. Coupled Fisher Discrimination Dictionary Learning for Single Image Super-resolution. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2015, 1196-1200, Queensland, Australia, 2015.4.19-2015.4.24.
- Fang Xie, Cheng Deng, Jie Xu, Jifei Yu, Jie Li. Image Super Resolution Using Gaussian Process Regression with Patch Clustering. International Conference on Internet Multimedia Computing and Service (ICIMCS), 2013, 109-112, Huang shan, China, 2013.8.17-8.18.