Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
hub
Proceedings of Machine learning and systems , volume=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 10roles
background 1polarities
background 1representative citing papers
BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
SeqLoRA applies bilevel optimization to sequential LoRA adaptation for continual multi-concept text-to-image generation with theoretical bounds on forgetting and interference.
DisAgg distributes secure aggregation to a client committee via secret sharing, eliminating local masking and homomorphic encryption while preserving privacy and delivering 4.6x speedup over OPA for 100k clients and 100k-dimensional updates.
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
FedNL reformulates federated learning as nested optimization with linear attention for collaborative test-time adaptation on non-IID data.
pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.
FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
DP-FLogTinyLLM combines federated learning, differential privacy, and LoRA-tuned tiny LLMs to match centralized log anomaly detection performance on Thunderbird and BGL datasets while preserving privacy.
citing papers explorer
-
Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
-
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
-
SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
SeqLoRA applies bilevel optimization to sequential LoRA adaptation for continual multi-concept text-to-image generation with theoretical bounds on forgetting and interference.
-
DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
DisAgg distributes secure aggregation to a client committee via secret sharing, eliminating local masking and homomorphic encryption while preserving privacy and delivering 4.6x speedup over OPA for 100k clients and 100k-dimensional updates.
-
FedSDR: Federated Self-Distillation with Rectification
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
-
Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation
FedNL reformulates federated learning as nested optimization with linear attention for collaborative test-time adaptation on non-IID data.
-
Personalized Federated Learning for Gradient Alignment
pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.
-
Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.
-
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
-
DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs
DP-FLogTinyLLM combines federated learning, differential privacy, and LoRA-tuned tiny LLMs to match centralized log anomaly detection performance on Thunderbird and BGL datasets while preserving privacy.