A5094046476- Privacy-Preserving Technologies in Data
- Stochastic Gradient Optimization Techniques
- Machine Learning and Data Classification
- Advanced Bandit Algorithms Research
- Recommender Systems and Techniques
- Wireless Communication Security Techniques
Tencent (China)
2024
Beijing University of Posts and Telecommunications
2024
Huazhong University of Science and Technology
2024
Peng Cheng Laboratory
2024
Multi-scenario recommender systems (MSRSs) have been increasingly used in real-world industrial platforms for their excellent advantages mitigating data sparsity and reducing maintenance costs. However, conventional MSRSs usually use all relevant features indiscriminately ignore that different kinds of varying importance under scenarios, which may cause confusion performance degradation. In addition, existing feature selection methods deep lack the exploration scenario relations. this paper,...
Federated learning is a promising distributed machine paradigm that can effectively exploit large-scale data without exposing users' privacy. However, it may incur significant communication overhead, thereby potentially impairing the training efficiency. To address this challenge, numerous studies suggest binarizing model updates. Nonetheless, traditional methods usually binarize updates in post-training manner, resulting approximation errors and consequent degradation accuracy. end, we...
Federated learning is a promising distributed training paradigm that effectively safeguards data privacy. However, it may involve significant communication costs, which hinders efficiency. In this paper, we aim to enhance efficiency from new perspective. Specifically, request the clients find optimal model updates relative global parameters within predefined random noise. For purpose, propose Masked Random Noise (FedMRN), novel framework enables learn 1-bit mask for each parameter and apply...