CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model

• URL: http://arxiv.org/abs/2503.06993v1
• Date: Mon, 10 Mar 2025 07:17:15 GMT
• Title: CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
• Authors: Shihao Hou, Xinyi Shang, Shreyank N Gowda, Yang Lu, Chao Wu, Yan Yan, Hanzi Wang,
• Abstract summary: Class-Aware Prompt Learning for Federated Long-tailed Learning (CAPT) is a novel framework that leverages a pre-trained VLM to handle both data heterogeneity and long-tailed distributions.<n>CAPT significantly improves tail class performance without compromising overall accuracy, outperforming state-of-the-art methods in federated long-tailed learning scenarios.
• Score: 32.36927984925236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Effectively handling the co-occurrence of non-IID data and long-tailed distributions remains a critical challenge in federated learning. While fine-tuning vision-language models (VLMs) like CLIP has shown to be promising in addressing non-IID data challenges, this approach leads to severe degradation of tail classes in federated long-tailed scenarios. Under the composite effects of strong non-IID data distribution and long-tailed class imbalances, VLM fine-tuning may even fail to yield any improvement. To address this issue, we propose Class-Aware Prompt Learning for Federated Long-tailed Learning (CAPT), a novel framework that leverages a pre-trained VLM to effectively handle both data heterogeneity and long-tailed distributions. CAPT introduces a dual-prompt mechanism that synergizes general and class-aware prompts, enabling the framework to capture global trends while preserving class-specific knowledge. To better aggregate and share knowledge across clients, we introduce a heterogeneity-aware client clustering strategy that groups clients based on their data distributions, enabling efficient collaboration and knowledge sharing. Extensive experiments on various long-tailed datasets with different levels of data heterogeneity demonstrate that CAPT significantly improves tail class performance without compromising overall accuracy, outperforming state-of-the-art methods in federated long-tailed learning scenarios.

Related papers

• FedLF: Adaptive Logit Adjustment and Feature Optimization in Federated Long-Tailed Learning [5.23984567704876]
  Federated learning offers a paradigm to the challenge of preserving privacy in distributed machine learning. Traditional approach fails to address the phenomenon of class-wise bias in global long-tailed data. New method FedLF introduces three modifications in the local training phase: adaptive logit adjustment, continuous class centred optimization, and feature decorrelation.
  arXiv  Detail & Related papers  (2024-09-18T16:25:29Z)
• What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights [67.72413262980272]
  Severe data imbalance naturally exists among web-scale vision-language datasets. We find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning. The robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts.
  arXiv  Detail & Related papers  (2024-05-31T17:57:24Z)
• Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data [9.045647166114916]
  Federated Learning (FL) is a promising paradigm for decentralized and collaborative model training. FL struggles with a significant performance reduction and poor convergence when confronted with Non-Independent and Identically Distributed (Non-IID) data distributions. We introduce Gen-FedSD, a novel approach that harnesses the powerful capability of state-of-the-art text-to-image foundation models.
  arXiv  Detail & Related papers  (2024-05-13T16:57:48Z)
• Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics [20.781607752797445]
  We propose a two-stage Decoupled Federated learning framework using Feature Statistics (DFL-FS) In the first stage, the server estimates the client's class coverage distributions through masked local feature statistics clustering. In the second stage, DFL-FS employs federated feature regeneration based on global feature statistics to enhance the model's adaptability to long-tailed data distributions.
  arXiv  Detail & Related papers  (2024-03-13T09:24:59Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [54.80435317208111]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm. It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities. It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)
• CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularization [3.3711670942444014]
  Federated learning enables edge devices to train a global model collaboratively without exposing their data. We tackle a new type of Non-IID data, called cluster-skewed non-IID, discovered in actual data sets. We propose an aggregation scheme that guarantees equality between clusters.
  arXiv  Detail & Related papers  (2023-02-21T02:53:37Z)
• FedABC: Targeting Fair Competition in Personalized Federated Learning [76.9646903596757]
  Federated learning aims to collaboratively train models without accessing their client's local private data. We propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the one-vs-all'' training strategy in each client to alleviate the unfair competition between classes.
  arXiv  Detail & Related papers  (2023-02-15T03:42:59Z)
• Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks [65.34113135080105]
  We show that not only the issue of data heterogeneity in current setups is not necessarily a problem but also in fact it can be beneficial for the FL participants. Our observations are intuitive. Our code is available at https://github.com/MMorafah/FL-SC-NIID.
  arXiv  Detail & Related papers  (2022-09-30T17:15:19Z)
• FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation [54.2658887073461]
  Dealing with non-IID data is one of the most challenging problems for federated learning. This paper studies the joint problem of non-IID and long-tailed data in federated learning and proposes a corresponding solution called Federated Ensemble Distillation with Imbalance (FEDIC) FEDIC uses model ensemble to take advantage of the diversity of models trained on non-IID data.
  arXiv  Detail & Related papers  (2022-04-30T06:17:36Z)
• Distributed Unsupervised Visual Representation Learning with Fused Features [13.935997509072669]
  Federated learning (FL) enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. We propose a federated contrastive learning framework consisting of two approaches: feature fusion and neighborhood matching. It outperforms other methods by 11% on IID data and matches the performance of centralized learning.
  arXiv  Detail & Related papers  (2021-11-21T08:36:31Z)
• ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning [52.831894583501395]
  Continual learning assumes the incoming data are fully labeled, which might not be applicable in real applications. We propose deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN) We show ORDisCo achieves significant performance improvement on various semi-supervised learning benchmark datasets for SSCL.
  arXiv  Detail & Related papers  (2021-01-02T09:04:14Z)

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.