REVIEW 5 cited by
Personalized Federated Learning with Feature Alignment and Classifier Collaboration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Data heterogeneity is one of the most challenging issues in federated learning, which motivates a variety of approaches to learn personalized models for participating clients. One such approach in deep neural networks based tasks is employing a shared feature representation and learning a customized classifier head for each client. However, previous works do not utilize the global knowledge during local representation learning and also neglect the fine-grained collaboration between local classifier heads, which limit the model generalization ability. In this work, we conduct explicit local-global feature alignment by leveraging global semantic knowledge for learning a better representation. Moreover, we quantify the benefit of classifier combination for each client as a function of the combining weights and derive an optimization problem for estimating optimal weights. Finally, extensive evaluation results on benchmark datasets with various heterogeneous data scenarios demonstrate the effectiveness of our proposed method. Code is available at https://github.com/JianXu95/FedPAC
Forward citations
Cited by 5 Pith papers
-
X-VFL: A New Vertical Federated Learning Framework with Cross Completion and Decision Subspace Alignment
X-VFL proposes cross-client feature completion plus decision-subspace alignment for vertical federated learning with partially missing features, but the claimed independent inference with missing features contradicts ...
-
Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
Proto-EVFL selects useful unaligned data in vertical federated learning with a dual optimal transport cost and class priors, then aggregates party features with learned gates, improving accuracy on rare and unseen classes.
-
Hypernetworks for Model-Heterogeneous Personalized Federated Learning
A server-side multi-head hypernetwork generates personalized parameters for clients with heterogeneous model architectures, plus an optional global-model distillation variant, and beats several pFL baselines on four b...
-
Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach
SFMTL-Graph builds a dynamic client similarity graph, partitions it with Louvain community detection, and restricts federated model aggregation to within communities to personalize learning while cutting communication.
-
Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion
pFedDC combines global and local text and vision prompts with cross-attention fusion to personalize federated CLIP models under label and domain shift.
Discussion (0). Sign in to comment.