paper-with-me

홈 › Papers

Federated Training of Dual Encoding Models on Small Non-IID Client Datasets

2022-09-30 · Raviteja Vemulapalli, Warren Richard Morningstar, Philip Andrew Mansfield, Hubert Eichner, Karan Singhal, Arash Afkanpour, Bradley Green

Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of encodings on centralized training data. However, in many scenarios, datasets are inherently decentralized across many clients (user devices or organizations) due to privacy concerns, motivating federated learning. In this work, we focus on federated training of dual encoding models on decentralized data composed of many small, non-IID (independent and identically distributed) client datasets. We show that existing approaches that work well in centralized settings perform poorly when naively adapted to this setting using federated averaging. We observe that, we can simulate large-batch loss computation on individual clients for loss functions that are based on encoding statistics. Based on this insight, we propose a novel federated training approach, Distributed Cross Correlation Optimization (DCCO), which trains dual encoding models using encoding statistics aggregated across clients, without sharing individual data samples. Our experimental results on two datasets demonstrate that the proposed DCCO approach outperforms federated variants of existing approaches by a large margin.

📄 PDF Abstract BibTeX arXiv:2210.00092

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningRepresentation Learning

Similar Papers 제목 키워드 기반

Controlling Participation in Federated Learning with Feedback

2024-11-28 · Michael Cummins, Guner Dilsad Er, Michael Muehlebach

We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training round. In contrast, we propose FedBack, …

Computational EfficiencyFederated Learningimage-classificationImage Classification

FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation

2026-07-08 · Chongkai Li, Bang Zhang, Wenjian Luo arxiv

Federated learning (FL) avoids explicit data exposure by keeping raw data on local clients, yet privacy risks remain in the training process and the learned model itself. Recently, centralized Taking Away Training Data (…

Federated Learning

Toward Understanding the Influence of Individual Clients in Federated Learning

2020-12-20 · Yihao Xue, Chaoyue Niu, Zhenzhe Zheng, Shaojie Tang 외

Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server. Extensive works have studied the performance guarantee of the global model, however, it is …

Federated Learning

FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning

2025-11-27 · Yuan Yao, Lixu Wang, Jiaqi Wu, Jin Song 외 arxiv

Federated learning (FL) enables collaborative training across clients while preserving privacy. While most existing FL methods assume homogeneous model architectures, client heterogeneity in both data and resources makes…

Federated Learning

Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

2023-07-11 · Sikai Bai, Shuaicheng Li, Weiming Zhuang, Jie Zhang 외

Federated learning has become a popular method to learn from decentralized heterogeneous data. Federated semi-supervised learning (FSSL) emerges to train models from a small fraction of labeled data due to label scarcity…

Federated Learning