AI Paper Atlas

Research map / Benchmarks / CIFAR-10 (α=0.1)

CIFAR-10 (α=0.1) leaderboard

24 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-10 (α=0.1). Best accuracy: 94.74 (HiDFD, AAAI 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CIFAR-10 (α=0.1) · accuracy

24 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
194.74HiDFD
ResNet34 → ResNet18
Hybrid Data-Free Knowledge Distillation
AAAI 2025 · Table 1
Knowledge distillation
293.39PFPT
ViT
Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
NeurIPS 2024 · CIFAR-10 results table
Personalized and heterogeneous FL
393.09FedPLL-LAAR
ResNet-18
Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization
AAAI 2024 · Table 1
Personalized and heterogeneous FL
492.6LaGAM
CNN
Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
CVPR 2024 · Table 1
Recognition and long-tail
592.38FedType private (pFedBayes)
ResNet-18 proxy
Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning
ICML 2024 · Table 1
Personalized and heterogeneous FL
685.214Ditto + MMD-DAdaptive Latent-Space Constraints in Personalized Federated Learning
NeurIPS 2025 · Table 2
Personalized and heterogeneous FL
783.24FedDO
ResNet-18
FedDO: Dynamic Client Optimization for Adaptive Federated Learning
ECCV 2026 · Table 1
Communication-efficient FL
880.75AFL
ResNet-18 pretrained on ImageNet-1k
AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
CVPR 2025 · Table 1
Communication-efficient FL
980.6FedAvg + FedDecorr
MobileNetV2
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
ICLR 2023 · CIFAR10/100 Experiments table
Personalized and heterogeneous FL
1080.5FPS + SimSiam
ResNet20
On the Importance and Applicability of Pre-Training for Federated Learning
ICLR 2023 · Comparison on synthetic pre-tr
Personalized and heterogeneous FL
14 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.