mlsanityData to 14 Oct 2026

Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning

arXiv 2109.00150 ↗First posted 1 Sep 2021cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

We describe federated reconnaissance, a class of learning problems in which distributed clients learn new concepts independently and communicate that knowledge efficiently. In particular, we propose an evaluation framework and methodological baseline for a system in which each client is expected to learn a growing set of classes and communicate knowledge of those classes efficiently with other clients, such that, after knowledge merging, the clients should be able to accurately discriminate between classes in the superset of classes observed by the set of clients. We compare a range of learning algorithms for this problem and find that prototypical networks are a strong approach in that they are robust to catastrophic forgetting while incorporating new information efficiently. Furthermore, we show that the online averaging of prototype vectors is effective for client model merging and requires only a small amount of communication overhead, memory, and update time per class with no gradient-based learning or hyperparameter tuning. Additionally, to put our results in context, we find that a simple, prototypical network with four convolutional layers significantly outperforms complex, state of the art continual learning algorithms, increasing the accuracy by over 22% after learning 600 Omniglot classes and over 33% after learning 20 mini-ImageNet classes incrementally. These results have important implications for federated reconnaissance and continual learning more generally by demonstrating that communicating feature vectors is an efficient, robust, and effective means for distributed, continual learning.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 1 Sep 2021.

Builds on

22 of 32 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2019Advances and Open Problems in Federated Learningcited by 3,046
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  12. 2017Continual Learning with Deep Generative Replaycited by 1,158
10 more
  1. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  2. 2019Three scenarios for continual learningcited by 614
  3. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 521
  4. 2019Orthogonal Gradient Descent for Continual Learningcited by 369
  5. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  6. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  7. 2019Meta-Learning Representations for Continual Learningcited by 189
  8. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  9. 2020Learning to Continually Learncited by 84
  10. 2018Prototypical Clustering Networks for Dermatological Disease Diagnosiscited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 6; 2024: 4; 2025: 1.

14 papers.

Sort:

By area:

  1. 2023Better Generative Replay for Continual Federated Learningcited by 55
  2. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  3. 2023Asynchronous Federated Continual Learningcited by 29
  4. 2023FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformercited by 23
  5. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
  6. 2022Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edgescited by 12
  7. 2021Ex-Model: Continual Learning from a Stream of Trained Modelscited by 11
  8. 2025Accurate Forgetting for Heterogeneous Federated Continual Learningcited by 11
  9. 2022Continual Horizontal Federated Learning for Heterogeneous Datacited by 8
  10. 2024Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyondcited by 5
  11. 2024On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradientscited by 5
  12. 2023On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directionscited by 4
2 more
  1. 2023Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memorycited by 4
  2. 2024Few-Shot Class-Incremental Learning with Non-IID Decentralized Datacited by 0