Related papers: Adapter-based Selective Knowledge Distillation for…
Federated learning (FL) offers a privacy-preserving framework for distributed machine learning, enabling collaborative model training across diverse clients without centralizing sensitive data. However, statistical heterogeneity,…
Most current federated learning frameworks are modeled as static processes, ignoring the dynamic characteristics of the learning system. Under the limited communication budget of the central server, the flexible model architecture of a…
Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial…
As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional multimedia data, and federated learning provides a promising potential solution to this…
Data-free knowledge distillation (DFKD) is a widely-used strategy for Knowledge Distillation (KD) whose training data is not available. It trains a lightweight student model with the aid of a large pretrained teacher model without any…
Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a privacy-preserving framework that leverages complementary cross-modal information.…
Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can…
The success of large-scale visual language pretraining (VLP) models has driven widespread adoption of image-text retrieval tasks. However, their deployment on mobile devices remains limited due to large model sizes and computational…
We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between the student and multiple mentors with different knowledge levels. Unlike traditional…
The rapid proliferation of Internet of Things (IoT) applications across heterogeneous Cloud-Edge-IoT environments presents significant challenges in distributed scheduling optimization. Existing approaches face issues, including fixed…
Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on…
Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…
Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…
Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…
Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face are heterogeneity in data across clients and collaboration…
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained…
Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…
Federated distillation has emerged as a promising collaborative machine learning approach, offering enhanced privacy protection and reduced communication compared to traditional federated learning by exchanging model outputs (soft logits)…
Federated learning is a distributed machine learning paradigm designed to protect data privacy. However, data heterogeneity across various clients results in catastrophic forgetting, where the model rapidly forgets previous knowledge while…
This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization…