REVIEW 12 cited by
Personalized Federated Learning: A Meta-Learning Approach
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
Personalized Federated Learning: A Meta-Learning Approach
read the original abstract
In Federated Learning, we aim to train models across multiple computing units (users), while users can only communicate with a common central server, without exchanging their data samples. This mechanism exploits the computational power of all users and allows users to obtain a richer model as their models are trained over a larger set of data points. However, this scheme only develops a common output for all the users, and, therefore, it does not adapt the model to each user. This is an important missing feature, especially given the heterogeneity of the underlying data distribution for various users. In this paper, we study a personalized variant of the federated learning in which our goal is to find an initial shared model that current or new users can easily adapt to their local dataset by performing one or a few steps of gradient descent with respect to their own data. This approach keeps all the benefits of the federated learning architecture, and, by structure, leads to a more personalized model for each user. We show this problem can be studied within the Model-Agnostic Meta-Learning (MAML) framework. Inspired by this connection, we study a personalized variant of the well-known Federated Averaging algorithm and evaluate its performance in terms of gradient norm for non-convex loss functions. Further, we characterize how this performance is affected by the closeness of underlying distributions of user data, measured in terms of distribution distances such as Total Variation and 1-Wasserstein metric.
Forward citations
Cited by 12 Pith papers
-
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
-
Expectation Maximization (EM) Converges for General Agnostic Mixtures
Gradient EM converges exponentially to optimal population loss minimizers for agnostic fitting of k parametric functions under strong convexity and smoothness of the loss, proper initialization, and separation conditions.
-
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
-
FederatedSkill: Federated Learning for Agentic Skill Evolution
FederatedSkill aggregates client semantic skill diffs via a server evolution agent to enable strictly personalized skill evolution, reporting up to 44.4% higher success rates and 37.5% lower compute cost than self-evo...
-
PrivFusion: A Privacy-preserving Multi-Agent Framework for Harmonizing Distributed Datasets
PrivFusion deploys agents to cluster semantically similar features and iteratively recommend transformations for harmonizing heterogeneous structured datasets in a privacy-preserving manner, evaluated on four COVID-19...
-
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.
-
Personalized Digital Health Modeling with Adaptive Support Users
A framework for personalizing digital health models by jointly learning adaptive weights on support users, using similarity-weighted transfer from similar users and contrastive regularization from dissimilar users to ...
-
Personalized Digital Health Modeling with Adaptive Support Users
A new framework trains personal digital health models using adaptive weights on support users including dissimilar ones, achieving up to 25% lower RMSE in low-data settings.
-
A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning
A taxonomy of client-level disagreements in federated learning is presented together with a multi-track resolution strategy that enforces strict exclusion via isolated update paths, shown to handle permanent, temporal...
-
Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
Personalized local running-mean/variance observation normalization prevents weight-norm overshadowing in FedAvg and improves FedRL-PPO on heterogeneous MuJoCo morphology variants.
-
Exploring CKKS Parameter Trade-offs for Privacy-Preserving Personalized Federated Learning
pFedCKKS derives CKKS parameter constraints for PFL under 128-bit security reducing choices to inner and outer ciphertext primes and evaluates precision-cost trade-offs on FEMNIST, CelebA and Sentiment140.
-
A Survey on Foundation Models for Personalized Federated Intelligence
The survey introduces personalized federated intelligence (PFI) as a framework integrating federated learning and foundation models to support privacy-aware personalization of AI models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.