Zobrazeno 1 - 10
of 133
pro vyhledávání: '"Ma, Fenglong"'
This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces small identical proxy models for clients, serving as agents for inform
Externí odkaz:
http://arxiv.org/abs/2407.03247
Autor:
Zhong, Yuan, Wang, Xiaochen, Wang, Jiaqi, Zhang, Xiaokun, Wang, Yaqing, Huai, Mengdi, Xiao, Cao, Ma, Fenglong
Synthesizing electronic health records (EHR) data has become a preferred strategy to address data scarcity, improve data quality, and model fairness in healthcare. However, existing approaches for EHR data generation predominantly rely on state-of-th
Externí odkaz:
http://arxiv.org/abs/2406.13942
Federated learning (FL) has obtained tremendous progress in providing collaborative training solutions for distributed data silos with privacy guarantees. However, few existing works explore a more realistic scenario where the clients hold multiple d
Externí odkaz:
http://arxiv.org/abs/2406.11048
Autor:
Li, Changjiang, Pang, Ren, Cao, Bochuan, Chen, Jinghui, Ma, Fenglong, Ji, Shouling, Wang, Ting
Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial robustness. However
Externí odkaz:
http://arxiv.org/abs/2406.09669
Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial computational reso
Externí odkaz:
http://arxiv.org/abs/2406.00045
Autor:
Liu, Han, Zhao, Siyang, Zhang, Xiaotong, Zhang, Feng, Wang, Wei, Ma, Fenglong, Chen, Hongyang, Yu, Hong, Zhang, Xianchao
Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen classes t
Externí odkaz:
http://arxiv.org/abs/2405.03565
Sequential recommendation is dedicated to offering items of interest for users based on their history behaviors. The attribute-opinion pairs, expressed by users in their reviews for items, provide the potentials to capture user preferences and item c
Externí odkaz:
http://arxiv.org/abs/2404.12975
Session-based recommendation aims to predict intents of anonymous users based on their limited behaviors. Modeling user behaviors involves two distinct rationales: co-occurrence patterns reflected by item IDs, and fine-grained preferences represented
Externí odkaz:
http://arxiv.org/abs/2404.12969
Propelled by their remarkable capabilities to generate novel and engaging content, Generative Artificial Intelligence (GenAI) technologies are disrupting traditional workflows in many industries. While prior research has examined GenAI from a techno-
Externí odkaz:
http://arxiv.org/abs/2404.04101
Automatic International Classification of Diseases (ICD) coding plays a crucial role in the extraction of relevant information from clinical notes for proper recording and billing. One of the most important directions for boosting the performance of
Externí odkaz:
http://arxiv.org/abs/2402.15700