FedAWAC

Citation Author(s):
Benteng
Zhang
Submitted by:
Benteng Zhang
Last updated:
Wed, 02/05/2025 - 11:56
DOI:
10.21227/mr1q-fn43
Data Format:
License:
24 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

CIFAR-10 and CIFAR-100 datasets comprise images of 10 and 100 categories, respectively, with a fixed size of 32x32 pixels in color.

Tiny-ImageNet dataset consists of 200 categories with approximately 120,000 samples, where each class contains 500 training images, 50 validation images, and 50 test images, with each image sized at 64 x 64. 

AG News dataset consists of article titles and descriptions, comprising 4 categories with 127,600 samples.

Instructions: 

For more information on the data, see the paper: Overcoming Forgetting Using Adaptive Federated Learning for IIoT Devices with Non-IID Data

Grant Number: 
no

Dataset Files

LOGIN TO ACCESS DATASET FILES