Federated Generalized Category Discovery

05/23/2023
by   Nan Pu, et al.
0

Generalized category discovery (GCD) aims at grouping unlabeled samples from known and unknown classes, given labeled data of known classes. To meet the recent decentralization trend in the community, we introduce a practical yet challenging task, namely Federated GCD (Fed-GCD), where the training data are distributively stored in local clients and cannot be shared among clients. The goal of Fed-GCD is to train a generic GCD model by client collaboration under the privacy-protected constraint. The Fed-GCD leads to two challenges: 1) representation degradation caused by training each client model with fewer data than centralized GCD learning, and 2) highly heterogeneous label spaces across different clients. To this end, we propose a novel Associated Gaussian Contrastive Learning (AGCL) framework based on learnable GMMs, which consists of a Client Semantics Association (CSA) and a global-local GMM Contrastive Learning (GCL). On the server, CSA aggregates the heterogeneous categories of local-client GMMs to generate a global GMM containing more comprehensive category knowledge. On each client, GCL builds class-level contrastive learning with both local and global GMMs. The local GCL learns robust representation with limited local data. The global GCL encourages the model to produce more discriminative representation with the comprehensive category relationships that may not exist in local data. We build a benchmark based on six visual datasets to facilitate the study of Fed-GCD. Extensive experiments show that our AGCL outperforms the FedAvg-based baseline on all datasets.

READ FULL TEXT
research
11/11/2022

More Generalized and Personalized Unsupervised Representation Learning In A Distributed System

Discriminative unsupervised learning methods such as contrastive learnin...
research
06/24/2021

Federated Noisy Client Learning

Federated learning (FL) collaboratively aggregates a shared global model...
research
08/31/2021

GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization

Since data is presented long-tailed in reality, it is challenging for Fe...
research
11/16/2022

Dual Class-Aware Contrastive Federated Semi-Supervised Learning

Federated semi-supervised learning (FSSL), facilitates labeled clients a...
research
10/18/2020

Federated Unsupervised Representation Learning

To leverage enormous unlabeled data on distributed edge devices, we form...
research
11/24/2022

Knowledge-Aware Federated Active Learning with Non-IID Data

Federated learning enables multiple decentralized clients to learn colla...
research
01/01/2023

Federated Learning with Client-Exclusive Classes

Existing federated classification algorithms typically assume the local ...

Please sign up or login with your details

Forgot password? Click here to reset