REVIEW 5 cited by
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing
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
In Byzantine robust distributed or federated learning, a central server wants to train a machine learning model over data distributed across multiple workers. However, a fraction of these workers may deviate from the prescribed algorithm and send arbitrary messages. While this problem has received significant attention recently, most current defenses assume that the workers have identical data. For realistic cases when the data across workers are heterogeneous (non-iid), we design new attacks which circumvent current defenses, leading to significant loss of performance. We then propose a simple bucketing scheme that adapts existing robust algorithms to heterogeneous datasets at a negligible computational cost. We also theoretically and experimentally validate our approach, showing that combining bucketing with existing robust algorithms is effective against challenging attacks. Our work is the first to establish guaranteed convergence for the non-iid Byzantine robust problem under realistic assumptions.
Forward citations
Cited by 5 Pith papers
-
FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks
FLAegis defends federated learning by SAX-transforming client updates, spectral-clustering them to filter malicious clients, and applying FFT-based robust aggregation, outperforming several baselines on FEMNIST.
-
One-Bit Model Aggregation for Differentially Private and Byzantine-Robust Personalized Federated Learning
PRoBit+ combines one-bit stochastic quantization, ML-based aggregation, and an adaptive quantization range to achieve communication-efficient, differentially private, Byzantine-robust personalized federated learning.
-
FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix
A server that keeps one example per class can detect and drop malicious federated-learning clients by measuring how separated their learned embeddings are, via the norm of a Gram matrix.
-
A Comprehensive Survey of Electronic Health Record Modeling: From Deep Learning Approaches to Large Language Models
A survey that taxonomizes EHR modeling research into data-centric, architectural, learning-focused, multimodal, and LLM-based categories, with datasets and metrics.
-
UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data
UniVarFL adds a classifier variance regularizer and a hyperspherical uniformity regularizer to local federated training, reporting improved accuracy on some non-IID benchmarks but not consistently across its own experiments.
Discussion (0). Sign in to comment.