LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
Federated Learning for Emoji Prediction in a Mobile Keyboard
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
We show that a word-level recurrent neural network can predict emoji from text typed on a mobile keyboard. We demonstrate the usefulness of transfer learning for predicting emoji by pretraining the model using a language modeling task. We also propose mechanisms to trigger emoji and tune the diversity of candidates. The model is trained using a distributed on-device learning framework called federated learning. The federated model is shown to achieve better performance than a server-trained model. This work demonstrates the feasibility of using federated learning to train production-quality models for natural language understanding tasks while keeping users' data on their devices.
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
method 1polarities
use method 1representative citing papers
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
Federated Q-learning in heterogeneous environments achieves linear speedup in K agents for sampling error but is limited to Θ(E/T) convergence when averaging every E steps, with a two-phase error decay-then-rise behavior in experiments.
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
PEP-FedPT achieves generalization and personalization in federated ViT prompt tuning via adaptive mixing of class-specific prompts weighted by global class prototypes and client priors, without per-client trainable parameters.
Active party in VFL performs agnostic inference attacks via independent models on logistic regression and counters them with tunable distortion of passive-party parameters.
FedSteer constructs a gradient subspace from cached client updates, projects active gradients to obtain coordinates, and reuses those coordinates on the drifted subspace to correct extreme staleness in federated learning.
Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.
citing papers explorer
-
LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
-
Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
-
On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments
Federated Q-learning in heterogeneous environments achieves linear speedup in K agents for sampling error but is limited to Θ(E/T) convergence when averaging every E steps, with a two-phase error decay-then-rise behavior in experiments.
-
Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits
Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.
-
Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers
PEP-FedPT achieves generalization and personalization in federated ViT prompt tuning via adaptive mixing of class-specific prompts weighted by global class prototypes and client priors, without per-client trainable parameters.
-
Privacy Against Agnostic Inference Attacks in Vertical Federated Learning
Active party in VFL performs agnostic inference attacks via independent models on logistic regression and counters them with tunable distortion of passive-party parameters.
-
FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching
FedSteer constructs a gradient subspace from cached client updates, projects active gradients to obtain coordinates, and reuses those coordinates on the drifted subspace to correct extreme staleness in federated learning.
-
Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction
Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.