Zobrazeno 1 - 10
of 872
pro vyhledávání: '"Zhao, Yuying"'
Autor:
Yang, Xiaodong, Chen, Huiyuan, Yan, Yuchen, Tang, Yuxin, Zhao, Yuying, Xu, Eric, Cai, Yiwei, Tong, Hanghang
The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence and suboptimal local optima,
Externí odkaz:
http://arxiv.org/abs/2406.16170
We consider weak convergence of one-step schemes for solving stochastic differential equations (SDEs) with one-sided Lipschitz conditions. It is known that the super-linear coefficients may lead to a blowup of moments of solutions and their numerical
Externí odkaz:
http://arxiv.org/abs/2406.14065
Recent years have witnessed the remarkable success of applying Graph machine learning (GML) to node/graph classification and link prediction. However, edge classification task that enjoys numerous real-world applications such as social network analys
Externí odkaz:
http://arxiv.org/abs/2406.11685
Autor:
Wang, Yu, Lipka, Nedim, Zhang, Ruiyi, Siu, Alexa, Zhao, Yuying, Ni, Bo, Wang, Xin, Rossi, Ryan, Derr, Tyler
Despite the impressive advancements of Large Language Models (LLMs) in generating text, they are often limited by the knowledge contained in the input and prone to producing inaccurate or hallucinated content. To tackle these issues, Retrieval-augmen
Externí odkaz:
http://arxiv.org/abs/2405.17602
Autor:
Zhao, Yuying, Xu, Minghua, Chen, Huiyuan, Chen, Yuzhong, Cai, Yiwei, Islam, Rashidul, Wang, Yu, Derr, Tyler
Recommender systems (RSs) have gained widespread applications across various domains owing to the superior ability to capture users' interests. However, the complexity and nuanced nature of users' interests, which span a wide range of diversity, pose
Externí odkaz:
http://arxiv.org/abs/2402.13495
Online dating platforms have gained widespread popularity as a means for individuals to seek potential romantic relationships. While recommender systems have been designed to improve the user experience in dating platforms by providing personalized r
Externí odkaz:
http://arxiv.org/abs/2402.12541
Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies aim to improve the overall LP performance of GNNs, none have explored its varying performance across different nodes an
Externí odkaz:
http://arxiv.org/abs/2310.04612
Autor:
Zhang, Yi, Zhao, Yuying, Li, Zhaoqing, Cheng, Xueqi, Wang, Yu, Kotevska, Olivera, Yu, Philip S., Derr, Tyler
Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data and the improvement in practical applications. However, many of these models prioritize high utility performance, such as accuracy,
Externí odkaz:
http://arxiv.org/abs/2308.16375
Recommender systems are effective tools for mitigating information overload and have seen extensive applications across various domains. However, the single focus on utility goals proves to be inadequate in addressing real-world concerns, leading to
Externí odkaz:
http://arxiv.org/abs/2307.04644
We present an error analysis of weak convergence of one-step numerical schemes for stochastic differential equations (SDEs) with super-linearly growing coefficients. Following Milstein's weak error analysis on the one-step approximation of SDEs, we p
Externí odkaz:
http://arxiv.org/abs/2303.14748