Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.12628 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917084408053760 |
|---|---|
| author | Hu, Ke Xiang, Liyao Tang, Peng Qiu, Weidong |
| author_facet | Hu, Ke Xiang, Liyao Tang, Peng Qiu, Weidong |
| contents | Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12628 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions Hu, Ke Xiang, Liyao Tang, Peng Qiu, Weidong Machine Learning Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines. |
| title | FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.12628 |