GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting
Federated Learning (FL) has emerged as a de facto machine learning area and received rapid increasing research interests from the community. However, catastrophic forgetting caused by data heterogeneity and partial participation poses distinctive challenges for FL, which are detrimental to the performance. To tackle the problems, we propose a new FL approach (namely GradMA), which takes inspiration from continual learning to simultaneously correct the server-side and worker-side update directions as well as take full advantage of server's rich computing and memory resources. Furthermore, we elaborate a memory reduction strategy to enable GradMA to accommodate FL with a large scale of workers. We then analyze convergence of GradMA theoretically under the smooth non-convex setting and show that its convergence rate achieves a linear speed up w.r.t the increasing number of sampled active workers. At last, our extensive experiments on various image classification tasks show that GradMA achieves significant performance gains in accuracy and communication efficiency compared to SOTA baselines.
Code (1)
Tasks
Continual LearningFederated Learningimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation
Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an a…
GradMask: Gradient-Guided Token Masking for Textual Adversarial Example Detection
We present a simple model-agnostic textual adversarial example detection scheme called GradMask. It uses gradient signals to detect adversarially perturbed tokens in an input sequence and occludes such tokens by a maskin…
GradMAP: Gradient-Based Multi-Agent Proximal Learning for Grid-Edge Flexibility
Coordinating large populations of grid-edge devices requires learning methods that remain fully decentralised in deployment while still respecting three-phase AC distribution-network physics. This paper proposes gradient…
Self-Supervised LearningGradMask: Effective Fine-tuning on Large-scale Pretrained Language Models via Gradient Masking
Pretrained language models have dominated a variety of NLP tasks. However, fine-tuning large pretrained models on downstream tasks tend to achieve degenerated and unstable results, especially when there are only a limite…
GradMax: Growing Neural Networks using Gradient Information
The architecture and the parameters of neural networks are often optimized independently, which requires costly retraining of the parameters whenever the architecture is modified. In this work we instead focus on growing…