Zobrazeno 1 - 10
of 636
pro vyhledávání: '"Li Ruixuan"'
Cross-Domain Few-Shot Learning (CDFSL) requires the model to transfer knowledge from the data-abundant source domain to data-scarce target domains for fast adaptation, where the large domain gap makes CDFSL a challenging problem. Masked Autoencoder (
Externí odkaz:
http://arxiv.org/abs/2412.19101
Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images
Externí odkaz:
http://arxiv.org/abs/2412.18513
Autor:
Li, Yichen, Wang, Haozhao, Xu, Wenchao, Xiao, Tianzhe, Liu, Hong, Tu, Minzhu, Wang, Yuying, Yang, Xin, Zhang, Rui, Yu, Shui, Guo, Song, Li, Ruixuan
Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and scalability in d
Externí odkaz:
http://arxiv.org/abs/2412.13840
Continual Federated Learning (CFL) allows distributed devices to collaboratively learn novel concepts from continuously shifting training data while avoiding knowledge forgetting of previously seen tasks. To tackle this challenge, most current CFL ap
Externí odkaz:
http://arxiv.org/abs/2412.13779
Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domain datasets for pixel-level segmentation. The significant domain gap be
Externí odkaz:
http://arxiv.org/abs/2410.22135
Autor:
Wang, Renhong, Wang, Cong, Li, Ruixuan, Guo, Deping, Dai, Jiaqi, Zong, Canbo, Zhang, Weihan, Ji, Wei
Kagome materials are known for hosting exotic quantum states, including quantum spin liquids, charge density waves, and unconventional superconductivity. The search for kagome monolayers is driven by their ability to exhibit neat and well-defined kag
Externí odkaz:
http://arxiv.org/abs/2410.08501
An important line of research in the field of explainability is to extract a small subset of crucial rationales from the full input. The most widely used criterion for rationale extraction is the maximum mutual information (MMI) criterion. However, i
Externí odkaz:
http://arxiv.org/abs/2410.06003
Autor:
Li, Shiwei, Hu, Zhuoqi, Tang, Xing, Wang, Haozhao, Xu, Shijie, Luo, Weihong, Li, Yuhua, He, Xiuqiang, Li, Ruixuan
Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient storage, retri
Externí odkaz:
http://arxiv.org/abs/2409.20305
This article introduces PAGE, a parameterized generative interpretive framework. PAGE is capable of providing faithful explanations for any graph neural network without necessitating prior knowledge or internal details. Specifically, we train the aut
Externí odkaz:
http://arxiv.org/abs/2408.14042
Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Unsupervised Few-Shot Learning (U-FSL) seeks to bridge this divide by re
Externí odkaz:
http://arxiv.org/abs/2408.13385