Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Luo, Yingtao"'
Diffusion models learn to denoise data and the trained denoiser is then used to generate new samples from the data distribution. In this paper, we revisit the diffusion sampling process and identify a fundamental cause of sample quality degradation:
Externí odkaz:
http://arxiv.org/abs/2407.08946
Autor:
Deuschel, Jannik, Ellington, Caleb N., Luo, Yingtao, Lengerich, Benjamin J., Friederich, Pascal, Xing, Eric P.
Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models force a tradeoff between accuracy and interpretability, limiting data-driven interpretations of human decision-making proce
Externí odkaz:
http://arxiv.org/abs/2310.07918
Autor:
Li, Zhixun, Wang, Liang, Sun, Xin, Luo, Yifan, Zhu, Yanqiao, Chen, Dingshuo, Luo, Yingtao, Zhou, Xiangxin, Liu, Qiang, Wu, Shu, Yu, Jeffrey Xu
Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL method
Externí odkaz:
http://arxiv.org/abs/2310.05174
In real-world scenarios like traffic and energy, massive time-series data with missing values and noises are widely observed, even sampled irregularly. While many imputation methods have been proposed, most of them work with a local horizon, which me
Externí odkaz:
http://arxiv.org/abs/2308.14906
Modeling sequential patterns from data is at the core of various time series forecasting tasks. Deep learning models have greatly outperformed many traditional models, but these black-box models generally lack explainability in prediction and decisio
Externí odkaz:
http://arxiv.org/abs/2209.01491
Publikováno v:
2022 IEEE International Conference on Data Mining (ICDM)
Deep learning models have achieved promising disease prediction performance of the Electronic Health Records (EHR) of patients. However, most models developed under the I.I.D. hypothesis fail to consider the agnostic distribution shifts, diminishing
Externí odkaz:
http://arxiv.org/abs/2209.01321
Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems. Due to the diverse nature of user interests, recent advances propose the multi-interest networks to encode historical behaviors into multipl
Externí odkaz:
http://arxiv.org/abs/2207.07910
In financial credit scoring, loan applications may be approved or rejected. We can only observe default/non-default labels for approved samples but have no observations for rejected samples, which leads to missing-not-at-random selection bias. Machin
Externí odkaz:
http://arxiv.org/abs/2206.00568
Autor:
Jiang, Juyong, Zhang, Peiyan, Luo, Yingtao, Li, Chaozhuo, Kim, Jae Boum, Zhang, Kai, Wang, Senzhang, Xie, Xing, Kim, Sunghun
Sequential recommendation (SR) aims to model users dynamic preferences from a series of interactions. A pivotal challenge in user modeling for SR lies in the inherent variability of user preferences. An effective SR model is expected to capture both
Externí odkaz:
http://arxiv.org/abs/2205.08776
Autor:
Jiang, Juyong, Zhang, Peiyan, Luo, Yingtao, Li, Chaozhuo, Kim, Jaeboum, Zhang, Kai, Wang, Senzhang, Kim, Sunghun
Sequential recommendation systems are integral to discerning temporal user preferences. Yet, the task of learning from abbreviated user interaction sequences poses a notable challenge. Data augmentation has been identified as a potent strategy to enh
Externí odkaz:
http://arxiv.org/abs/2112.06460