Prediction-space knowledge markets for communication-efficient federated learning on multimedia tasks
By: Wenzhang Du
Potential Business Impact:
Lets computers learn from private data without sharing it.
Federated learning (FL) enables collaborative training over distributed multimedia data but suffers acutely from statistical heterogeneity and communication constraints, especially when clients deploy large models. Classic parameter-averaging methods such as FedAvg transmit full model weights and can diverge under nonindependent and identically distributed (non-IID) data. We propose KTA v2, a prediction-space knowledge trading market for FL. Each round, clients locally train on their private data, then share only logits on a small public reference set. The server constructs a client-client similarity graph in prediction space, combines it with reference-set accuracy to form per-client teacher ensembles, and sends back personalized soft targets for a second-stage distillation update. This two-stage procedure can be interpreted as approximate block-coordinate descent on a unified objective with prediction-space regularization. Experiments on FEMNIST, CIFAR-10 and AG News show that, under comparable or much lower communication budgets, KTA v2 consistently outperforms a local-only baseline and strong parameter-based methods (FedAvg, FedProx), and substantially improves over a FedMD-style global teacher. On CIFAR-10 with ResNet-18, KTA v2 reaches 57.7% test accuracy using approximately 1/1100 of FedAvg's communication, while on AG News it attains 89.3% accuracy with approximately 1/300 of FedAvg's traffic.
Similar Papers
A Novel Algorithm for Personalized Federated Learning: Knowledge Distillation with Weighted Combination Loss
Machine Learning (Stat)
Teaches computers to learn from private data better.
FedProtoKD: Dual Knowledge Distillation with Adaptive Class-wise Prototype Margin for Heterogeneous Federated Learning
Machine Learning (CS)
Helps computers learn better from different data.
FedProtoKD: Dual Knowledge Distillation with Adaptive Class-wise Prototype Margin for Heterogeneous Federated Learning
Machine Learning (CS)
Improves AI learning from different data sources.