AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

DeepAFL: Deep Analytic Federated Learning

Jianheng Tang, Yajiang Huang, Kejia Fan, Feijiang Han, Jiaxu Li, Jinfeng Xu, Run He, Anfeng Liu, Houbing Herbert Song, Huiping Zhuang, Yunhuai Liu

ICLR 2026 · Federated learning and privacy › Communication-efficient FL · approach: Local drift correction · 2 citations (OpenAlex)

This paper tried a common change: Add residual connections

add residual skip connection to deep analytic layers · CIFAR-100, Tiny-ImageNet, CIFAR-10 · accuracy vs layers T Improved

What 546 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 residual skip connection to deep analytic layers (ablation)DeepAFL · CIFAR-100, Tiny-ImageNet, CIFAR-10accuracy vs layers TImproved
add per-layer random projection B_t instead of identity (ablation)DeepAFL · CIFAR-100, Tiny-ImageNet, CIFAR-10accuracyImproved
add activation function in residual block (ablation)DeepAFL · CIFAR-100, Tiny-ImageNet, CIFAR-10accuracyImproved
add trainable transformation Omega_{t+1} in residual block (ablation)DeepAFL · CIFAR-100, Tiny-ImageNet, CIFAR-10accuracyImproved
stack analytic layers with random projections only (no activation)naive deepening · CIFAR-100accuracyNo clear effect
add activation after random projection in stacked layers (no residual)naive deepening · CIFAR-100accuracy vs layersMixed
add activated random projection to form zero-layer features Phi_0AFL · CIFAR-100accuracy: about 2.1%Improved
increase layers T from 5 to 20DeepAFL · CIFAR-100top-1 accuracy (%): 64.72 -> 66.98Improved
increase layers T from 5 to 20DeepAFL · Tiny-ImageNettop-1 accuracy (%): 60.31 -> 62.35Improved
increase layers T from 20 to 50DeepAFL · CIFAR-100 and Tiny-ImageNettesting accuracy: over 1.5%Improved
use GELU instead of weaker activations (Softshrink, none) (ablation)DeepAFL · activation studyaccuracy: about 2%Improved
increase projection dimensions d_Phi and d_F to 2^13DeepAFL · dimension studynumerical stabilityHurt

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