Search Results for author:
Found 4 papers, 1 papers with code
SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Specifically, SiDA attains a remarkable speedup in MoE inference with up to 3. 93X throughput increasing, up to 75% latency reduction, and up to 80% GPU memory saving with down to 1% performance drop.
Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties
In this paper, we propose \textbf{Party-wise Dropout} to improve the VFL model's robustness against the unexpected exit of passive parties and a defense method called \textbf{DIMIP} to protect the active party's IP in the deployment phase.
Rethinking Normalization Methods in Federated Learning
We also show that layer normalization is a better choice in FL which can mitigate the external covariate shift and improve the performance of the global model.
Improved Input Reprogramming for GAN Conditioning
Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm.
