Picture for Yue Niu

Yue Niu

Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training

Add code
Jun 21, 2024
Viaarxiv icon

Ethos: Rectifying Language Models in Orthogonal Parameter Space

Add code
Apr 01, 2024
Figure 1 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Figure 2 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Figure 3 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Figure 4 for Ethos: Rectifying Language Models in Orthogonal Parameter Space
Viaarxiv icon

Edge Private Graph Neural Networks with Singular Value Perturbation

Add code
Mar 16, 2024
Figure 1 for Edge Private Graph Neural Networks with Singular Value Perturbation
Figure 2 for Edge Private Graph Neural Networks with Singular Value Perturbation
Figure 3 for Edge Private Graph Neural Networks with Singular Value Perturbation
Figure 4 for Edge Private Graph Neural Networks with Singular Value Perturbation
Viaarxiv icon

ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys

Add code
Mar 01, 2024
Figure 1 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Figure 2 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Figure 3 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Figure 4 for ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Viaarxiv icon

All Rivers Run to the Sea: Private Learning with Asymmetric Flows

Add code
Dec 05, 2023
Figure 1 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Figure 2 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Figure 3 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Figure 4 for All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Viaarxiv icon

Reuse Kernels or Activations? A Flexible Dataflow for Low-latency Spectral CNN Acceleration

Add code
Oct 17, 2023
Figure 1 for Reuse Kernels or Activations? A Flexible Dataflow for Low-latency Spectral CNN Acceleration
Figure 2 for Reuse Kernels or Activations? A Flexible Dataflow for Low-latency Spectral CNN Acceleration
Figure 3 for Reuse Kernels or Activations? A Flexible Dataflow for Low-latency Spectral CNN Acceleration
Figure 4 for Reuse Kernels or Activations? A Flexible Dataflow for Low-latency Spectral CNN Acceleration
Viaarxiv icon

mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization

Add code
Jul 25, 2023
Figure 1 for mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization
Figure 2 for mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization
Figure 3 for mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization
Figure 4 for mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization
Viaarxiv icon

Federated Learning of Large Models at the Edge via Principal Sub-Model Training

Add code
Aug 28, 2022
Figure 1 for Federated Learning of Large Models at the Edge via Principal Sub-Model Training
Figure 2 for Federated Learning of Large Models at the Edge via Principal Sub-Model Training
Figure 3 for Federated Learning of Large Models at the Edge via Principal Sub-Model Training
Figure 4 for Federated Learning of Large Models at the Edge via Principal Sub-Model Training
Viaarxiv icon

Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge

Add code
Aug 27, 2022
Figure 1 for Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge
Figure 2 for Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge
Figure 3 for Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge
Figure 4 for Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge
Viaarxiv icon

SPEC2: SPECtral SParsE CNN Accelerator on FPGAs

Add code
Oct 16, 2019
Figure 1 for SPEC2: SPECtral SParsE CNN Accelerator on FPGAs
Figure 2 for SPEC2: SPECtral SParsE CNN Accelerator on FPGAs
Figure 3 for SPEC2: SPECtral SParsE CNN Accelerator on FPGAs
Figure 4 for SPEC2: SPECtral SParsE CNN Accelerator on FPGAs
Viaarxiv icon