Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting

• URL: http://arxiv.org/abs/2501.15356v3
• Date: Thu, 13 Mar 2025 19:12:47 GMT
• Title: Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
• Authors: Milad Khademi Nori, Il-Min Kim, Guanghui Wang,
• Abstract summary: Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks.<n>We develop a mathematical framework for FCIL that formulates local and global forgetting.<n>We propose an approach called Hybrid Rehearsal which utilizes latent exemplars and data-free techniques to address local and global forgetting.
• Score: 10.061328213032088
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. FCIL is known to suffer from local forgetting due to class imbalance at each client and global forgetting due to class imbalance across clients. We develop a mathematical framework for FCIL that formulates local and global forgetting. Then, we propose an approach called Hybrid Rehearsal (HR), which utilizes latent exemplars and data-free techniques to address local and global forgetting, respectively. HR employs a customized autoencoder designed for both data classification and the generation of synthetic data. To determine the embeddings of new tasks for all clients in the latent space of the encoder, the server uses the Lennard-Jones Potential formulations. Meanwhile, at the clients, the decoder decodes the stored low-dimensional latent space exemplars back to the high-dimensional input space, used to address local forgetting. To overcome global forgetting, the decoder generates synthetic data. Furthermore, our mathematical framework proves that our proposed approach HR can, in principle, tackle the two local and global forgetting challenges. In practice, extensive experiments demonstrate that while preserving privacy, our proposed approach outperforms the state-of-the-art baselines on multiple FCIL benchmarks with low compute and memory footprints.

Related papers

• Hierarchical Knowledge Structuring for Effective Federated Learning in Heterogeneous Environments [0.6144680854063939]
  Federated learning enables collaborative model training across distributed entities while maintaining individual data privacy. Recent efforts leverage logit-based knowledge aggregation and distillation to overcome these issues. We propose a Hierarchical Knowledge Structuring (HKS) framework that formulates sample logits into a multi-granularity codebook.
  arXiv  Detail & Related papers  (2025-04-04T15:06:02Z)
• Subgraph Federated Learning for Local Generalization [41.64806982207585]
  Federated Learning (FL) on graphs enables collaborative model training to enhance performance without compromising privacy of each client. Existing methods often overlook the mutable nature of graph data, which frequently introduces new nodes and leads to shifts in label distribution. Our proposed method, FedLoG, effectively tackles this issue by mitigating local overfitting.
  arXiv  Detail & Related papers  (2025-03-06T01:08:01Z)
• Personalized federated learning based on feature fusion [2.943623084019036]
  Federated learning enables distributed clients to collaborate on training while storing their data locally to protect client privacy. We propose a personalized federated learning approach called pFedPM. In our process, we replace traditional gradient uploading with feature uploading, which helps reduce communication costs and allows for heterogeneous client models.
  arXiv  Detail & Related papers  (2024-06-24T12:16:51Z)
• FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data [46.29190753993415]
  Federated Long-Tailed Learning (Fed-LT) is a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution. This paper introduces an approach termed Federated Local and Generic Model Training in Fed-LT (FedLoGe), which enhances both local and generic model performance.
  arXiv  Detail & Related papers  (2024-01-17T05:04:33Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Personalized Federated Learning via Amortized Bayesian Meta-Learning [21.126405589760367]
  We introduce a new perspective on personalized federated learning through Amortized Bayesian Meta-Learning. Specifically, we propose a novel algorithm called emphFedABML, which employs hierarchical variational inference across clients. Our theoretical analysis provides an upper bound on the average generalization error and guarantees the generalization performance on unseen data.
  arXiv  Detail & Related papers  (2023-07-05T11:58:58Z)
• Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New Algorithms [29.636944156801327]
  Multiple clients collaboratively train one global model without sharing their semantic parsing data. Lorar adjusts each client's contribution to the global model update based on its training loss reduction during each round. Clients with smaller datasets enjoy larger performance gains.
  arXiv  Detail & Related papers  (2023-05-26T19:25:49Z)
• Subspace based Federated Unlearning [75.90552823500633]
  Federated unlearning (FL) aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten. Most existing federated unlearning algorithms require the server to store the history of the parameter updates. We propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, that lets the global model perform gradient ascent.
  arXiv  Detail & Related papers  (2023-02-24T04:29:44Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• No One Left Behind: Real-World Federated Class-Incremental Learning [111.77681016996202]
  Local-Global Anti-forgetting (LGA) model addresses local and global catastrophic forgetting. We develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation.
  arXiv  Detail & Related papers  (2023-02-02T06:41:02Z)
• DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics [60.60173139258481]
  Local training on non-iid distributed data results in deflected local optimum. A natural solution is to gather all client data onto the server, such that the server has a global view of the entire data distribution. In this paper, we put forth an idea to collect and leverage global knowledge on the server without hindering data privacy.
  arXiv  Detail & Related papers  (2022-11-20T06:13:06Z)
• Optimizing Server-side Aggregation For Robust Federated Learning via Subspace Training [80.03567604524268]
  Non-IID data distribution across clients and poisoning attacks are two main challenges in real-world federated learning systems. We propose SmartFL, a generic approach that optimize the server-side aggregation process. We provide theoretical analyses of the convergence and generalization capacity for SmartFL.
  arXiv  Detail & Related papers  (2022-11-10T13:20:56Z)
• Exploiting Shared Representations for Personalized Federated Learning [54.65133770989836]
  We propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client. Our algorithm harnesses the distributed computational power across clients to perform many local-updates with respect to the low-dimensional local parameters for every update of the representation. This result is of interest beyond federated learning to a broad class of problems in which we aim to learn a shared low-dimensional representation among data distributions.
  arXiv  Detail & Related papers  (2021-02-14T05:36:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.