Ensemble weighting strategy for federated learning to handle heterogeneous data distributions (Record no. 19143)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | a |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | OSt |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20230714111456.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 230406b xxu||||| |||| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Original cataloging agency | AIKTC-KRRC |
| Transcribing agency | AIKTC-KRRC |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| 9 (RLIN) | 20421 |
| Author | Richter, Lucas |
| 245 ## - TITLE STATEMENT | |
| Title | Ensemble weighting strategy for federated learning to handle heterogeneous data distributions |
| 250 ## - EDITION STATEMENT | |
| Volume, Issue number | Vol.15(4), Oct |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Telangana |
| Name of publisher, distributor, etc. | IUP Publications |
| Year | 2022 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Pagination | 7-20p. |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Increasingly measured data in the context of smart cities can be used to develop new and innovative business models to increase efficiency and the value of life. A time-series classification algorithm can support to automatize many different processes such as forecasting services. In order to ensure data security and privacy, Federated Learning trains a global model collaboratively on multiple clients. Having different data-distributions and data-quantities across participating clients, neural networks suffer from slow convergence and overfitting. Based on different data-distributions, data-quantities and number of clients, we develop and evaluate different data-clustering strategies to update global model weights in comparison to the state of the art. We use public time-series data, generate various synthetic datasets and train a Relational-Regularized Autoencoder for classification purposes. Our results show an improvement of model performance concerning generalization. |
| 650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| 9 (RLIN) | 4623 |
| Topical term or geographic name entry element | Electrical Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| 9 (RLIN) | 20422 |
| Co-Author | Dontsov, Ilja |
| 773 0# - HOST ITEM ENTRY | |
| International Standard Serial Number | 0974-1704 |
| Place, publisher, and date of publication | Hyderabad IUP Publications |
| Title | IUP journal of electrical and electronics engineering |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| URL | https://www.preprints.org/manuscript/202209.0435/v1/download |
| Link text | Click here |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | Articles Abstract Database |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Shelving location | Date acquired | Total Checkouts | Barcode | Date last seen | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | School of Engineering & Technology | School of Engineering & Technology | Archieval Section | 06/04/2023 | 2023-0627 | 06/04/2023 | 06/04/2023 | Articles Abstract Database |