AI Paper Atlas

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

GFedCL: Graph-Based Federated Continual Learning with Spatial and Temporal Awareness

Qingyang Yu, Yang Hua, Qizhen Zhang, Hao Wang

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning

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 temporal attention to the spatial relational graph (ablation)GFedCL · US-StatesMSE (x10^-2): 2.48 -> 2.41Improved
add the spatio-temporal relational graph (ablation)GFedCL · US-StatesMSE (x10^-2): 2.52 -> 2.41Improved
condition the generator on the relational graph (ablation)GFedCL · CIFAR-100 generation qualityIS and FIDImproved
use GFedCL instead of the best baseline AFLGFedCL · EMNIST-Lettersaccuracy (%): 75.17 -> 77.23Improved
use GFedCL instead of the best baselineGFedCL · CIFAR-100accuracy (%): 55.33 -> 73.67Improved
use GFedCL instead of the best baselineGFedCL · TinyImageNetaccuracy (%): 49.44 -> 77.39Improved
use GFedCL instead of AFLGFedCL · EMNIST-Lettersforgetting (%): 2.94 -> 3.34No clear effect
use GFedCL instead of AF-FCLGFedCL · TCGA-BRCAforgetting (%): 2.92 -> 3.93Hurt
use DP Laplace noise on encodings and graphsGFedCL · privacyequilibrium of synthetic dataNo clear effect

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