With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to...
详细信息
Clinical outcome prediction is critical to the condition prediction of patients and management of hospital capacities. There are two kinds of medical data, including time series signals recorded by various devices and...
详细信息
Image inpainting, which aims to reconstruct reasonably clear and realistic images from known pixel information, is one of the core problems in computer vision. However, due to the complexity and variability of the und...
详细信息
Federated learning, as a distributed machine learning paradigm, enhances privacy protection but faces the challenge of heterogeneity. data-free knowledge distillation (DFKD) methods attempt to overcome this challenge ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Federated learning, as a distributed machine learning paradigm, enhances privacy protection but faces the challenge of heterogeneity. data-free knowledge distillation (DFKD) methods attempt to overcome this challenge by using a generator to synthesize samples for fine-tuning a global model. However, these methods often suffer from significant shifts in output distribution, leading to catastrophic forgetting. To tackle these issues, we propose FedFLD, a novel federated forget-less distillation framework that mitigates catastrophic forgetting in DFKD while addressing the heterogeneity challenge. Specifically, FedFLD guides the generator’s training from three key aspects and constrains the output distribution with an elastic weight consolidation penalty term. By synthesizing diverse samples from different perspectives through additional generator updates, FedFLD facilitates effective knowledge distillation from local models to the global model. Additionally, the global model is further optimized via the heterogeneity fine-tuning process, mitigating the bias from heterogeneity and resulting in a more expressive and robust model.
Multimodal named entity recognition (MNER) on social media is a challenging task which aims to extract named entities in free text and incorporate images to classify them into user-defined types. The existing semi-sup...
详细信息
Scene Graph Generation (SGG) aims to detail the visual contents of images and present them as a compact summary graph. Although several approaches have made great progress in SGG, it's still faced with the long-ta...
详细信息
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performan...
In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image...
详细信息
Wireless power transfer (WPT) systems using magnetic resonant coupling (MRC) have made significant progress recently, leading to various optimization methods in scenarios involving multiple-input multiple-output (MIMO...
详细信息
For distributed network traffic prediction with data localization and privacy protection, Federated Learning (FL) enables collaborative training without raw data exchange across Base Stations (BSs). Nevertheless, traf...
详细信息
暂无评论