Zobrazeno 1 - 10
of 632
pro vyhledávání: '"Fan, Jiajun"'
Autor:
Li, Ye, Tang, Chen, Meng, Yuan, Fan, Jiajun, Chai, Zenghao, Ma, Xinzhu, Wang, Zhi, Zhu, Wenwu
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies for a cer
Externí odkaz:
http://arxiv.org/abs/2407.05010
Autor:
Wang, Hao, Chen, Zhichao, Shen, Yuan, Fan, Jiajun, Liu, Zhaoran, Yang, Degui, Liu, Xinggao, Li, Haoxuan
Heterogeneous treatment effect (HTE) estimation from observational data poses significant challenges due to treatment selection bias. Existing methods address this bias by minimizing distribution discrepancies between treatment groups in latent space
Externí odkaz:
http://arxiv.org/abs/2407.01111
Autor:
Wang, Hao, Chen, Zhichao, Fan, Jiajun, Li, Haoxuan, Liu, Tianqiao, Liu, Weiming, Dai, Quanyu, Wang, Yichao, Dong, Zhenhua, Tang, Ruiming
Estimating conditional average treatment effect from observational data is highly challenging due to the existence of treatment selection bias. Prevalent methods mitigate this issue by aligning distributions of different treatment groups in the laten
Externí odkaz:
http://arxiv.org/abs/2310.18286
Autor:
Wang, Hao, Lian, Jianxun, Wu, Mingqi, Li, Haoxuan, Fan, Jiajun, Xu, Wanyue, Li, Chaozhuo, Xie, Xing
Sequential user modeling, a critical task in personalized recommender systems, focuses on predicting the next item a user would prefer, requiring a deep understanding of user behavior sequences. Despite the remarkable success of Transformer-based mod
Externí odkaz:
http://arxiv.org/abs/2308.02925
Autor:
Fan, Jiajun, Zhuang, Yuzheng, Liu, Yuecheng, Hao, Jianye, Wang, Bin, Zhu, Jiangcheng, Wang, Hao, Xia, Shu-Tao
The exploration problem is one of the main challenges in deep reinforcement learning (RL). Recent promising works tried to handle the problem with population-based methods, which collect samples with diverse behaviors derived from a population of dif
Externí odkaz:
http://arxiv.org/abs/2305.05239
As a basic research problem for building effective recommender systems, post-click conversion rate (CVR) estimation has long been plagued by sample selection bias and data sparsity issues. To address the data sparsity issue, prevalent methods based o
Externí odkaz:
http://arxiv.org/abs/2210.11039
Autor:
Fan, Jiajun, Xiao, Changnan
To obtain higher sample efficiency and superior final performance simultaneously has been one of the major challenges for deep reinforcement learning (DRL). Previous work could handle one of these challenges but typically failed to address them concu
Externí odkaz:
http://arxiv.org/abs/2206.03192
Autor:
Fan, Jiajun
The Arcade Learning Environment (ALE) is proposed as an evaluation platform for empirically assessing the generality of agents across dozens of Atari 2600 games. ALE offers various challenging problems and has drawn significant attention from the dee
Externí odkaz:
http://arxiv.org/abs/2112.04145
Publikováno v:
In Construction and Building Materials 16 August 2024 439
Publikováno v:
In Structures July 2024 65