Research map

Federated learning and privacy: research map

Federated training, differential privacy and privacy attacks.

2,258 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 4 topics. Within all five venues, its share held steady from 2.8% in 2023–24 to 2.0% in 2025–26 (743 → 913 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Federated learning and privacy in the interactive map

Topics

• Differential privacy · 774 papers
  Privacy accounting and mechanisms, Private online and user-level learning, Local-DP and private estimation
• Personalized and heterogeneous FL · 738 papers
  Non-IID federated learning, Federated learning with pretrained models, Federated semi-supervised and graph learning
• Communication-efficient FL · 382 papers
  Client participation analysis, Federated optimization algorithms, Local drift correction
• Privacy attacks and secure learning · 364 papers
  Encryption-based private learning, Private federated aggregation, Visual privacy and face de-identification

Most cited papers in Federated learning and privacy

• Model-Contrastive Federated Learning (CVPR 2021 · 1,518 citations)
• CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy (ICML 2016 · 1,289 citations)
• FedProto: Federated Prototype Learning across Heterogeneous Clients (AAAI 2022 · 751 citations)
• Learning Differentially Private Recurrent Language Models (ICLR 2018 · 743 citations)
• SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (ICML 2020 · 709 citations)
• SplitFed: When Federated Learning Meets Split Learning (AAAI 2022 · 696 citations)
• Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization (NeurIPS 2020 · 565 citations)
• FedALA: Adaptive Local Aggregation for Personalized Federated Learning (AAAI 2023 · 414 citations)
• Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach (NeurIPS 2020 · 373 citations)
• Scalable Private Learning with PATE (ICLR 2018 · 313 citations)
• PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees (ICLR 2019 · 278 citations)
• Collecting Telemetry Data Privately (NeurIPS 2017 · 262 citations)