Search Results for author:
Found 10 papers, 5 papers with code
READ: Recurrent Adaptation of Large Transformers
However, fine-tuning all pre-trained model parameters becomes impractical as the model size and number of tasks increase.
Now It Sounds Like You: Learning Personalized Vocabulary On Device
In recent years, Federated Learning (FL) has shown significant advancements in its ability to perform various natural language processing (NLP) tasks.
On Noisy Evaluation in Federated Hyperparameter Tuning
In this work, we perform the first systematic study on the effect of noisy evaluation in federated hyperparameter tuning.
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity.
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity.
Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity
Federated learning (FL) is an effective mechanism for data privacy in recommender systems by running machine learning model training on-device.
Papaya: Practical, Private, and Scalable Federated Learning
Our work tackles the aforementioned issues, sketches of some of the system design challenges and their solutions, and touches upon principles that emerged from building a production FL system for millions of clients.
Opacus: User-Friendly Differential Privacy Library in PyTorch
We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus. ai).
Federated Learning with Buffered Asynchronous Aggregation
On the other hand, asynchronous aggregation of client updates in FL (i. e., asynchronous FL) alleviates the scalability issue.
Low-light Environment Neural Surveillance
The system uses a low-light video feed processed in real-time by an optical-flow network, spatial and temporal networks, and a Support Vector Machine to identify shootings, assaults, and thefts.
