AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FedTopo: Topology-Informed Representation Alignment in Federated Learning Under Non-I.I.D. Conditions

Ke Hu, Liyao Xiang, Peng Tang, Weidong Qiu

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add topological alignment loss (TAL) (ablation)FedTopo · CIFAR-10 Q-skew+K-skew (Setting A)accuracy (%): 53.90 -> 67.05Improved
add topological alignment loss (TAL) (ablation)FedTopo · FMNIST severe L-skew (Setting B)accuracy (%): 58.87 -> 73.67Improved
add topological alignment loss (TAL) (ablation)FedTopo · CIFAR-100 L-skew+N-skew (Setting C)accuracy (%): 47.23 -> 63.60Improved
select ResNet-18 block layer2 via TGBS instead of conv1 (ablation)FedTopo · ResNet-18 block selectionaccuracy (%): 80.62 -> 88.35Improved
select ResNet-18 block layer2 instead of deep layer4 (ablation)FedTopo · ResNet-18 block selectionaccuracy (%): 85.35 -> 88.35Improved
select CNN conv1 via TGBS instead of conv2 (ablation)FedTopo · CNN block selectionaccuracy (%): 86.16 -> 87.52Improved
use Smooth-Topo alpha schedule instead of Warm-up (ablation)FedTopo · CIFAR-10 Setting A, round 10accuracy (%): 73.52 -> 76.84Improved
use Smooth-Topo alpha schedule instead of Warm-up (ablation)FedTopo · CIFAR-10 Setting B, round 10accuracy (%): 67.21 -> 71.31Improved
use Linear-Topo alpha schedule instead of Warm-up in early training (ablation)FedTopo · CIFAR-10 Setting A, round 1accuracy (%): 65.13 -> 69.15Improved
use Linear-Topo rather than Smooth-Topo schedule (ablation)FedTopo · CIFAR-10 Setting A, round 10accuracy (%): 76.84 -> 75.27Hurt
FedTopo versus second-best baseline across partitionsFedTopo · FMNIST, CIFAR-10, CIFAR-100 non-IIDaccuracy (%): up to 8.69%, 11.05%, 8.44%Improved
FedTopo versus FedDC on FMNIST L-skewFedTopo · FMNIST L-skewaccuracy (%): 91.08 -> 91.30Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy