Search Results for author:
Found 3 papers, 1 papers with code
Multi-user Co-inference with Batch Processing Capable Edge Server
To deal with the coupled offloading and scheduling introduced by concurrent batch processing, we first consider an offline problem with a constant edge inference latency and the same latency constraint.
Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning
Then, a greedy device scheduling algorithm is introduced, which in each step selects the device consuming the least updating time obtained by the optimal bandwidth allocation, until the lower bound begins to increase, meaning that scheduling more devices will degrade the model accuracy.
Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning
Since the output data size of a DNN layer can be larger than that of the raw data, offloading intermediate data between layers can suffer from high transmission latency under limited wireless bandwidth.
