Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929719826448384 |
|---|---|
| author | Irureta, Jon Imaz, Jon Lojo, Aizea Fernandez-Marques, Javier González, Marco Perona, Iñigo |
| author_facet | Irureta, Jon Imaz, Jon Lojo, Aizea Fernandez-Marques, Javier González, Marco Perona, Iñigo |
| contents | Existing Vertical FL (VFL) methods often struggle with realistic and unaligned data partitions, and incur into high communication costs and significant operational complexity. This work introduces a novel approach to VFL, Active Participant Centric VFL (APC-VFL), that excels in scenarios when data samples among participants are partially aligned at training. Among its strengths, APC-VFL only requires a single communication step with the active participant. This is made possible through a local and unsupervised representation learning stage at each participant followed by a knowledge distillation step in the active participant. Compared to other VFL methods such as SplitNN or VFedTrans, APC-VFL consistently outperforms them across three popular VFL datasets in terms of F1, accuracy and communication costs as the ratio of aligned data is reduced. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need Irureta, Jon Imaz, Jon Lojo, Aizea Fernandez-Marques, Javier González, Marco Perona, Iñigo Machine Learning Existing Vertical FL (VFL) methods often struggle with realistic and unaligned data partitions, and incur into high communication costs and significant operational complexity. This work introduces a novel approach to VFL, Active Participant Centric VFL (APC-VFL), that excels in scenarios when data samples among participants are partially aligned at training. Among its strengths, APC-VFL only requires a single communication step with the active participant. This is made possible through a local and unsupervised representation learning stage at each participant followed by a knowledge distillation step in the active participant. Compared to other VFL methods such as SplitNN or VFedTrans, APC-VFL consistently outperforms them across three popular VFL datasets in terms of F1, accuracy and communication costs as the ratio of aligned data is reduced. |
| title | Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.17648 |