Zobrazeno 1 - 10
of 1 021
pro vyhledávání: '"WANG, YILI"'
During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into their parameters. These parameterized facts enable realistic image generation, but they may become obsolete over time, thereby misrepresenting the current sta
Externí odkaz:
http://arxiv.org/abs/2409.17928
Autor:
Wang, Yili, Liu, Yixin, Shen, Xu, Li, Chenyu, Ding, Kaize, Miao, Rui, Wang, Ying, Pan, Shirui, Wang, Xin
To build safe and reliable graph machine learning systems, unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection (GLOD) have received significant attention in recent years. Though those two
Externí odkaz:
http://arxiv.org/abs/2406.15523
Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation. However, SAM requires two sequenti
Externí odkaz:
http://arxiv.org/abs/2406.13137
Social recommendation models weave social interactions into their design to provide uniquely personalized recommendation results for users. However, social networks not only amplify the popularity bias in recommendation models, resulting in more freq
Externí odkaz:
http://arxiv.org/abs/2405.16772
Publikováno v:
ICML 2024
Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learning simply sums up cross-entro
Externí odkaz:
http://arxiv.org/abs/2405.15564
Autor:
Wang, Yili
In recent years, heterogeneous graph neural networks (HGNNs) have achieved excellent performance in handling heterogeneous information networks (HINs). Curriculum learning is a machine learning strategy where training examples are presented to a mode
Externí odkaz:
http://arxiv.org/abs/2405.06522
The open-world test dataset is often mixed with out-of-distribution (OOD) samples, where the deployed models will struggle to make accurate predictions. Traditional detection methods need to trade off OOD detection and in-distribution (ID) classifica
Externí odkaz:
http://arxiv.org/abs/2404.15625
There is growing interest in generating skeleton-based human motions from natural language descriptions. While most efforts have focused on developing better neural architectures for this task, there has been no significant work on determining the pr
Externí odkaz:
http://arxiv.org/abs/2309.10248
Publikováno v:
Acta Biochimica et Biophysica Sinica, Vol 56, Pp 1108-1117 (2024)
Protein glycosylation is a type of protein post-translational modification. One specific example is the modification of proteins with O-linked β-N-acetylglucosamine (O-GlcNAc) and O-linked α-N-acetylgalactosamine (O-GalNAc). Enhanced levels of both
Externí odkaz:
https://doaj.org/article/13db7865abf24c50a5235741e17972ce
Autor:
Li, Daojie1 (AUTHOR), Wang, Yili1 (AUTHOR), Li, Xi1 (AUTHOR), Zhang, Zimo1 (AUTHOR), Wang, Guoming1 (AUTHOR), Zhang, Yunhua2 (AUTHOR), Chen, Lijuan1 (AUTHOR) zhangchenlijuan@163.com
Publikováno v:
Scientific Reports. 9/18/2024, Vol. 14 Issue 1, p1-10. 10p.