相关论文: Soft Separation and Distillation: Toward Global Un…

Big data scenarios, where massive, heterogeneous datasets are distributed across clients, demand scalable, privacy-preserving learning methods. Federated learning (FL) enables decentralized training of machine learning (ML) models across…

Federated learning has recently gained popularity as a framework for distributed clients to collaboratively train a machine learning model using local data. While traditional federated learning relies on a central server for model…

Score Distillation Sampling (SDS) has emerged as a prominent method for text-to-3D generation by leveraging the strengths of 2D diffusion models. However, SDS is limited to generation tasks and lacks the capability to edit existing 3D…

Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, due to the heterogeneity of the system and data, many…

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…

In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required…

Dataset distillation synthesizes a small dataset such that a model trained on this set approximates the performance of the original dataset. Recent studies on dataset distillation focused primarily on the design of the optimization process,…

Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query…

Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is…

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been…

Federated learning (FL) is an emerging distributed machine learning paradigm enabling collaborative model training on decentralized devices without exposing their local data. A key challenge in FL is the uneven data distribution across…

The heterogeneity of hardware and data is a well-known and studied problem in the community of Federated Learning (FL) as running under heterogeneous settings. Recently, custom-size client models trained with Knowledge Distillation (KD) has…

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high…

Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain…

Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-scale training data. Dataset distillation addresses this…

Federated learning (FL) is an emerging distributed machine learning paradigm that enables collaborative training of machine learning models over decentralized devices without exposing their local data. One of the major challenges in FL is…

In knowledge distillation, the knowledge from the teacher model is often too complex for the student model to thoroughly process. However, good teachers in real life always simplify complex material before teaching it to students. Inspired…

Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…

Heterogeneous Federated Learning (HFL) has gained significant attention for its capacity to handle both model and data heterogeneity across clients. Prototype-based HFL methods emerge as a promising solution to address statistical and model…

Federated learning (FL) has emerged with increasing popularity to collaborate distributed medical institutions for training deep networks. However, despite existing FL algorithms only allow the supervised training setting, most hospitals in…