Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Shao, Yunfeng"'
Generative Flow Networks (GFlowNets) aim to generate diverse trajectories from a distribution in which the final states of the trajectories are proportional to the reward, serving as a powerful alternative to reinforcement learning for exploratory co
Externí odkaz:
http://arxiv.org/abs/2408.06920
Autor:
Lin, Guopeng, Han, Weili, Ruan, Wenqiang, Zhou, Ruisheng, Song, Lushan, Li, Bingshuai, Shao, Yunfeng
Multi-party training frameworks for decision trees based on secure multi-party computation enable multiple parties to train high-performance models on distributed private data with privacy preservation. The training process essentially involves frequ
Externí odkaz:
http://arxiv.org/abs/2406.07948
Autor:
Li, Xin-Chun, Song, Shaoming, Li, Yinchuan, Li, Bingshuai, Shao, Yunfeng, Yang, Yang, Zhan, De-Chuan
In some real-world applications, data samples are usually distributed on local devices, where federated learning (FL) techniques are proposed to coordinate decentralized clients without directly sharing users' private data. FL commonly follows the pa
Externí odkaz:
http://arxiv.org/abs/2404.09232
Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small models). Despite their own advantages, neither paradigm can effective
Externí odkaz:
http://arxiv.org/abs/2311.11083
Autor:
Zhu, Didi, Li, Zexi, Zhang, Min, Yuan, Junkun, Shao, Yunfeng, Liu, Jiashuo, Kuang, Kun, Li, Yinchuan, Wu, Chao
Large-scale vision-language (V-L) models have demonstrated remarkable generalization capabilities for downstream tasks through prompt tuning. However, the mechanisms behind the learned text representations are unknown, limiting further generalization
Externí odkaz:
http://arxiv.org/abs/2306.15955
We propose the GFlowNets with Human Feedback (GFlowHF) framework to improve the exploration ability when training AI models. For tasks where the reward is unknown, we fit the reward function through human evaluations on different trajectories. The go
Externí odkaz:
http://arxiv.org/abs/2305.07036
Autor:
Zhu, Didi, Li, Yinchuan, Shao, Yunfeng, Hao, Jianye, Wu, Fei, Kuang, Kun, Xiao, Jun, Wu, Chao
We introduce a new problem in unsupervised domain adaptation, termed as Generalized Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target labels including unknown categories. GUDA bridges the gap between label dis
Externí odkaz:
http://arxiv.org/abs/2305.04466
Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However, these algori
Externí odkaz:
http://arxiv.org/abs/2304.11989
Modern multi-agent reinforcement learning (RL) algorithms hold great potential for solving a variety of real-world problems. However, they do not fully exploit cross-agent knowledge to reduce sample complexity and improve performance. Although transf
Externí odkaz:
http://arxiv.org/abs/2304.05632
Federated learning (FL) is a promising framework that models distributed machine learning while protecting the privacy of clients. However, FL suffers performance degradation from heterogeneous and limited data. To alleviate the degradation, we prese
Externí odkaz:
http://arxiv.org/abs/2303.04345