REVIEW 14 cited by
Think Locally, Act Globally: Federated Learning with Local and Global Representations
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
Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that jointly learns compact local representations on each device and a global model across all devices. As a result, the global model can be smaller since it only operates on local representations, reducing the number of communicated parameters. Theoretically, we provide a generalization analysis which shows that a combination of local and global models reduces both variance in the data as well as variance across device distributions. Empirically, we demonstrate that local models enable communication-efficient training while retaining performance. We also evaluate on the task of personalized mood prediction from real-world mobile data where privacy is key. Finally, local models handle heterogeneous data from new devices, and learn fair representations that obfuscate protected attributes such as race, age, and gender.
Forward citations
Cited by 14 Pith papers
-
From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
FedSAF shifts prototype alignment in heterogeneous federated learning from coordinate matching to inter-class structural relations and reports up to 3.52% gains over prior methods.
-
FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling
FedOBP introduces a quantile-thresholded importance score based on a federated first-order Taylor approximation to select a small set of parameters for personalization, claiming better performance than prior PFL methods.
-
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
FedTSP builds class prototypes from LLM-generated text descriptions via PLMs and trainable prompts to preserve semantic relationships and reduce heterogeneity effects in federated learning.
-
FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning
Sharing class-relation topology with reliability weighting beats parameter, distillation, and prototype sharing under heterogeneous federated backbones on CIFAR and Tiny-ImageNet.
-
Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage
Proposes a covariance-aware tuning-free shrinkage framework and sequential algorithm for multi-source estimation that attains oracle risk asymptotically and improves on single-step methods.
-
FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs
FedCoE proposes a coordinated dual-level MoE framework for federated learning that improves global and personalized accuracy while enabling strong cold-start performance for new clients.
-
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Bidirectional Manifold Consistency (BMC) is a geometric, training-free metric that quantifies stability of reasoning trajectories in diffusion LLMs to enable self-verification, rejection sampling, and alignment withou...
-
FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
A federated LoRA fine-tuning method that builds a client-similarity tree and adapts aggregation depth layer-by-layer outperforms flat or global aggregation baselines on NLU and NLG tasks.
-
FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
FIRMA introduces Fibonacci ring aggregation protocols for server-free federated learning that maintain private heads and achieve higher accuracy than FedAvg under label skew across multiple benchmarks and heterogeneit...
-
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustn...
-
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Bidirectional Manifold Consistency measures geometric stability of dLLM trajectories and is claimed to indicate reasoning correctness for diagnosis, rejection sampling, and reward-based alignment.
-
PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes
A new federated transformer architecture uses personalized patch embeddings and a global variable-embedding table to forecast when different nodes have different sampling rates and variable sets.
-
Generalizable Federated Learning using Client Adaptive Focal Modulation
The abstract describes AdaptFED, a claimed federated learning method, but the full text is an unrelated graph theory paper, so the claimed results are absent from the submission.
-
From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning
A data-centric survey of federated learning that ranks non-IID data traits by influence on convergence, links splitting protocols to real phenomena, and examines data-related defenses under clean and adversarial conditions.
Discussion (0). Sign in to comment.